2023-08-26 更新
GIST: Generating Image-Specific Text for Fine-grained Object Classification
Authors:Kathleen M. Lewis, Emily Mu, Adrian V. Dalca, John Guttag
Recent vision-language models outperform vision-only models on many image classification tasks. However, because of the absence of paired text/image descriptions, it remains difficult to fine-tune these models for fine-grained image classification. In this work, we propose a method, GIST, for generating image-specific fine-grained text descriptions from image-only datasets, and show that these text descriptions can be used to improve classification. Key parts of our method include 1. prompting a pretrained large language model with domain-specific prompts to generate diverse fine-grained text descriptions for each class and 2. using a pretrained vision-language model to match each image to label-preserving text descriptions that capture relevant visual features in the image. We demonstrate the utility of GIST by fine-tuning vision-language models on the image-and-generated-text pairs to learn an aligned vision-language representation space for improved classification. We evaluate our learned representation space in full-shot and few-shot scenarios across four diverse fine-grained classification datasets, each from a different domain. Our method achieves an average improvement of $4.1\%$ in accuracy over CLIP linear probes and an average of $1.1\%$ improvement in accuracy over the previous state-of-the-art image-text classification method on the full-shot datasets. Our method achieves similar improvements across few-shot regimes. Code is available at https://github.com/emu1729/GIST.
PDF The first two authors contributed equally to this work and are listed in alphabetical order
点此查看论文截图
Why Is Prompt Tuning for Vision-Language Models Robust to Noisy Labels?
Authors:Cheng-En Wu, Yu Tian, Haichao Yu, Heng Wang, Pedro Morgado, Yu Hen Hu, Linjie Yang
Vision-language models such as CLIP learn a generic text-image embedding from large-scale training data. A vision-language model can be adapted to a new classification task through few-shot prompt tuning. We find that such a prompt tuning process is highly robust to label noises. This intrigues us to study the key reasons contributing to the robustness of the prompt tuning paradigm. We conducted extensive experiments to explore this property and find the key factors are: 1) the fixed classname tokens provide a strong regularization to the optimization of the model, reducing gradients induced by the noisy samples; 2) the powerful pre-trained image-text embedding that is learned from diverse and generic web data provides strong prior knowledge for image classification. Further, we demonstrate that noisy zero-shot predictions from CLIP can be used to tune its own prompt, significantly enhancing prediction accuracy in the unsupervised setting. The code is available at https://github.com/CEWu/PTNL.
PDF Accepted by ICCV2023
点此查看论文截图
Foundational Models Defining a New Era in Vision: A Survey and Outlook
Authors:Muhammad Awais, Muzammal Naseer, Salman Khan, Rao Muhammad Anwer, Hisham Cholakkal, Mubarak Shah, Ming-Hsuan Yang, Fahad Shahbaz Khan
Vision systems to see and reason about the compositional nature of visual scenes are fundamental to understanding our world. The complex relations between objects and their locations, ambiguities, and variations in the real-world environment can be better described in human language, naturally governed by grammatical rules and other modalities such as audio and depth. The models learned to bridge the gap between such modalities coupled with large-scale training data facilitate contextual reasoning, generalization, and prompt capabilities at test time. These models are referred to as foundational models. The output of such models can be modified through human-provided prompts without retraining, e.g., segmenting a particular object by providing a bounding box, having interactive dialogues by asking questions about an image or video scene or manipulating the robot’s behavior through language instructions. In this survey, we provide a comprehensive review of such emerging foundational models, including typical architecture designs to combine different modalities (vision, text, audio, etc), training objectives (contrastive, generative), pre-training datasets, fine-tuning mechanisms, and the common prompting patterns; textual, visual, and heterogeneous. We discuss the open challenges and research directions for foundational models in computer vision, including difficulties in their evaluations and benchmarking, gaps in their real-world understanding, limitations of their contextual understanding, biases, vulnerability to adversarial attacks, and interpretability issues. We review recent developments in this field, covering a wide range of applications of foundation models systematically and comprehensively. A comprehensive list of foundational models studied in this work is available at \url{https://github.com/awaisrauf/Awesome-CV-Foundational-Models}.
PDF Project page: https://github.com/awaisrauf/Awesome-CV-Foundational-Models
点此查看论文截图
AViT: Adapting Vision Transformers for Small Skin Lesion Segmentation Datasets
Authors:Siyi Du, Nourhan Bayasi, Ghassan Harmarneh, Rafeef Garbi
Skin lesion segmentation (SLS) plays an important role in skin lesion analysis. Vision transformers (ViTs) are considered an auspicious solution for SLS, but they require more training data compared to convolutional neural networks (CNNs) due to their inherent parameter-heavy structure and lack of some inductive biases. To alleviate this issue, current approaches fine-tune pre-trained ViT backbones on SLS datasets, aiming to leverage the knowledge learned from a larger set of natural images to lower the amount of skin training data needed. However, fully fine-tuning all parameters of large backbones is computationally expensive and memory intensive. In this paper, we propose AViT, a novel efficient strategy to mitigate ViTs’ data-hunger by transferring any pre-trained ViTs to the SLS task. Specifically, we integrate lightweight modules (adapters) within the transformer layers, which modulate the feature representation of a ViT without updating its pre-trained weights. In addition, we employ a shallow CNN as a prompt generator to create a prompt embedding from the input image, which grasps fine-grained information and CNN’s inductive biases to guide the segmentation task on small datasets. Our quantitative experiments on 4 skin lesion datasets demonstrate that AViT achieves competitive, and at times superior, performance to SOTA but with significantly fewer trainable parameters. Our code is available at https://github.com/siyi-wind/AViT.
PDF 10 pages, 2 figures, accepted by MICCAI ISIC Workshop 2023
点此查看论文截图
PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization
Authors:Junhyeong Cho, Gilhyun Nam, Sungyeon Kim, Hunmin Yang, Suha Kwak
In a joint vision-language space, a text feature (e.g., from “a photo of a dog”) could effectively represent its relevant image features (e.g., from dog photos). Also, a recent study has demonstrated the cross-modal transferability phenomenon of this joint space. From these observations, we propose PromptStyler which simulates various distribution shifts in the joint space by synthesizing diverse styles via prompts without using any images to deal with source-free domain generalization. The proposed method learns to generate a variety of style features (from “a S style of a”) via learnable style word vectors for pseudo-words S. To ensure that learned styles do not distort content information, we force style-content features (from “a S* style of a [class]”) to be located nearby their corresponding content features (from “[class]”) in the joint vision-language space. After learning style word vectors, we train a linear classifier using synthesized style-content features. PromptStyler achieves the state of the art on PACS, VLCS, OfficeHome and DomainNet, even though it does not require any images for training.
PDF Accepted to ICCV 2023, Project Page: https://promptstyler.github.io/
点此查看论文截图
DualCoOp++: Fast and Effective Adaptation to Multi-Label Recognition with Limited Annotations
Authors:Ping Hu, Ximeng Sun, Stan Sclaroff, Kate Saenko
Multi-label image recognition in the low-label regime is a task of great challenge and practical significance. Previous works have focused on learning the alignment between textual and visual spaces to compensate for limited image labels, yet may suffer from reduced accuracy due to the scarcity of high-quality multi-label annotations. In this research, we leverage the powerful alignment between textual and visual features pretrained with millions of auxiliary image-text pairs. We introduce an efficient and effective framework called Evidence-guided Dual Context Optimization (DualCoOp++), which serves as a unified approach for addressing partial-label and zero-shot multi-label recognition. In DualCoOp++ we separately encode evidential, positive, and negative contexts for target classes as parametric components of the linguistic input (i.e., prompts). The evidential context aims to discover all the related visual content for the target class, and serves as guidance to aggregate positive and negative contexts from the spatial domain of the image, enabling better distinguishment between similar categories. Additionally, we introduce a Winner-Take-All module that promotes inter-class interaction during training, while avoiding the need for extra parameters and costs. As DualCoOp++ imposes minimal additional learnable overhead on the pretrained vision-language framework, it enables rapid adaptation to multi-label recognition tasks with limited annotations and even unseen classes. Experiments on standard multi-label recognition benchmarks across two challenging low-label settings demonstrate the superior performance of our approach compared to state-of-the-art methods.
PDF This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible. arXiv admin note: substantial text overlap with arXiv:2206.09541
点此查看论文截图
Unmasking the Invisible: Finding Location-Specific Aggregated Air Quality Index with Smartphone-Captured Images
Authors:Joyanta Jyoti Mondal, Md. Farhadul Islam, Raima Islam, Nowsin Kabir Rhidi, A. B. M. Alim Al Islam, Meem Arafat Manab, Jannatun Noor
The prevalence and mobility of smartphones make these a widely used tool for environmental health research. However, their potential for determining aggregated air quality index (AQI) based on PM2.5 concentration in specific locations remains largely unexplored in the existing literature. In this paper, we thoroughly examine the challenges associated with predicting location-specific PM2.5 concentration using images taken with smartphone cameras. The focus of our study is on Dhaka, the capital of Bangladesh, due to its significant air pollution levels and the large population exposed to it. Our research involves the development of a Deep Convolutional Neural Network (DCNN), which we train using over a thousand outdoor images taken and annotated. These photos are captured at various locations in Dhaka, and their labels are based on PM2.5 concentration data obtained from the local US consulate, calculated using the NowCast algorithm. Through supervised learning, our model establishes a correlation index during training, enhancing its ability to function as a Picture-based Predictor of PM2.5 Concentration (PPPC). This enables the algorithm to calculate an equivalent daily averaged AQI index from a smartphone image. Unlike, popular overly parameterized models, our model shows resource efficiency since it uses fewer parameters. Furthermore, test results indicate that our model outperforms popular models like ViT and INN, as well as popular CNN-based models such as VGG19, ResNet50, and MobileNetV2, in predicting location-specific PM2.5 concentration. Our dataset is the first publicly available collection that includes atmospheric images and corresponding PM2.5 measurements from Dhaka. Our code and dataset will be made public when publishing the paper.
PDF 15 pages, 7 figures, submitted to Nature Scientific Reports
点此查看论文截图
Empowering Vision-Language Models to Follow Interleaved Vision-Language Instructions
Authors:Juncheng Li, Kaihang Pan, Zhiqi Ge, Minghe Gao, Hanwang Zhang, Wei Ji, Wenqiao Zhang, Tat-Seng Chua, Siliang Tang, Yueting Zhuang
Multimodal Large Language Models (MLLMs) have recently sparked significant interest, which demonstrates emergent capabilities to serve as a general-purpose model for various vision-language tasks. However, existing methods mainly focus on limited types of instructions with a single image as visual context, which hinders the widespread availability of MLLMs. In this paper, we introduce the I4 benchmark to comprehensively evaluate the instruction following ability on complicated interleaved vision-language instructions, which involve intricate image-text sequential context, covering a diverse range of scenarios (e.g., visually-rich webpages/textbooks, lecture slides, embodied dialogue). Systematic evaluation on our I4 benchmark reveals a common defect of existing methods: the Visual Prompt Generator (VPG) trained on image-captioning alignment objective tends to attend to common foreground information for captioning but struggles to extract specific information required by particular tasks. To address this issue, we propose a generic and lightweight controllable knowledge re-injection module, which utilizes the sophisticated reasoning ability of LLMs to control the VPG to conditionally extract instruction-specific visual information and re-inject it into the LLM. Further, we introduce an annotation-free cross-attention guided counterfactual image training strategy to methodically learn the proposed module by collaborating a cascade of foundation models. Enhanced by the proposed module and training strategy, we present Cheetor, a Transformer-based MLLM that can effectively handle a wide variety of interleaved vision-language instructions and achieves state-of-the-art zero-shot performance across all tasks of I4, without high-quality multimodal instruction tuning data. Cheetor also exhibits competitive performance compared with state-of-the-art instruction tuned models on MME benchmark.
PDF
点此查看论文截图
Which Tokens to Use? Investigating Token Reduction in Vision Transformers
Authors:Joakim Bruslund Haurum, Sergio Escalera, Graham W. Taylor, Thomas B. Moeslund
Since the introduction of the Vision Transformer (ViT), researchers have sought to make ViTs more efficient by removing redundant information in the processed tokens. While different methods have been explored to achieve this goal, we still lack understanding of the resulting reduction patterns and how those patterns differ across token reduction methods and datasets. To close this gap, we set out to understand the reduction patterns of 10 different token reduction methods using four image classification datasets. By systematically comparing these methods on the different classification tasks, we find that the Top-K pruning method is a surprisingly strong baseline. Through in-depth analysis of the different methods, we determine that: the reduction patterns are generally not consistent when varying the capacity of the backbone model, the reduction patterns of pruning-based methods significantly differ from fixed radial patterns, and the reduction patterns of pruning-based methods are correlated across classification datasets. Finally we report that the similarity of reduction patterns is a moderate-to-strong proxy for model performance. Project page at https://vap.aau.dk/tokens.
PDF ICCV 2023 NIVT Workshop. Project webpage https://vap.aau.dk/tokens
点此查看论文截图
Spatial Gated Multi-Layer Perceptron for Land Use and Land Cover Mapping
Authors:Ali Jamali, Swalpa Kumar Roy, Danfeng Hong, Peter M Atkinson, Pedram Ghamisi
Convolutional Neural Networks (CNNs) are models that are utilized extensively for the hierarchical extraction of features. Vision transformers (ViTs), through the use of a self-attention mechanism, have recently achieved superior modeling of global contextual information compared to CNNs. However, to realize their image classification strength, ViTs require substantial training datasets. Where the available training data are limited, current advanced multi-layer perceptrons (MLPs) can provide viable alternatives to both deep CNNs and ViTs. In this paper, we developed the SGU-MLP, a learning algorithm that effectively uses both MLPs and spatial gating units (SGUs) for precise land use land cover (LULC) mapping. Results illustrated the superiority of the developed SGU-MLP classification algorithm over several CNN and CNN-ViT-based models, including HybridSN, ResNet, iFormer, EfficientFormer and CoAtNet. The proposed SGU-MLP algorithm was tested through three experiments in Houston, USA, Berlin, Germany and Augsburg, Germany. The SGU-MLP classification model was found to consistently outperform the benchmark CNN and CNN-ViT-based algorithms. For example, for the Houston experiment, SGU-MLP significantly outperformed HybridSN, CoAtNet, Efficientformer, iFormer and ResNet by approximately 15%, 19%, 20%, 21%, and 25%, respectively, in terms of average accuracy. The code will be made publicly available at https://github.com/aj1365/SGUMLP
PDF Submitted in IEEE
点此查看论文截图
ICPC: Instance-Conditioned Prompting with Contrastive Learning for Semantic Segmentation
Authors:Chaohui Yu, Qiang Zhou, Zhibin Wang, Fan Wang
Modern supervised semantic segmentation methods are usually finetuned based on the supervised or self-supervised models pre-trained on ImageNet. Recent work shows that transferring the knowledge from CLIP to semantic segmentation via prompt learning can achieve promising performance. The performance boost comes from the feature enhancement with multimodal alignment, i.e., the dot product between vision and text embeddings. However, how to improve the multimodal alignment for better transfer performance in dense tasks remains underexplored. In this work, we focus on improving the quality of vision-text alignment from two aspects of prompting design and loss function, and present an instance-conditioned prompting with contrastive learning (ICPC) framework. First, compared with the static prompt designs, we reveal that dynamic prompting conditioned on image content can more efficiently utilize the text encoder for complex dense tasks. Second, we propose an align-guided contrastive loss to refine the alignment of vision and text embeddings. We further propose lightweight multi-scale alignment for better performance. Extensive experiments on three large-scale datasets (ADE20K, COCO-Stuff10k, and ADE20K-Full) demonstrate that ICPC brings consistent improvements across diverse backbones. Taking ResNet-50 as an example, ICPC outperforms the state-of-the-art counterpart by 1.71%, 1.05%, and 1.41% mIoU on the three datasets, respectively.
PDF
点此查看论文截图
SEDA: Self-Ensembling ViT with Defensive Distillation and Adversarial Training for robust Chest X-rays Classification
Authors:Raza Imam, Ibrahim Almakky, Salma Alrashdi, Baketah Alrashdi, Mohammad Yaqub
Deep Learning methods have recently seen increased adoption in medical imaging applications. However, elevated vulnerabilities have been explored in recent Deep Learning solutions, which can hinder future adoption. Particularly, the vulnerability of Vision Transformer (ViT) to adversarial, privacy, and confidentiality attacks raise serious concerns about their reliability in medical settings. This work aims to enhance the robustness of self-ensembling ViTs for the tuberculosis chest x-ray classification task. We propose Self-Ensembling ViT with defensive Distillation and Adversarial training (SEDA). SEDA utilizes efficient CNN blocks to learn spatial features with various levels of abstraction from feature representations extracted from intermediate ViT blocks, that are largely unaffected by adversarial perturbations. Furthermore, SEDA leverages adversarial training in combination with defensive distillation for improved robustness against adversaries. Training using adversarial examples leads to better model generalizability and improves its ability to handle perturbations. Distillation using soft probabilities introduces uncertainty and variation into the output probabilities, making it more difficult for adversarial and privacy attacks. Extensive experiments performed with the proposed architecture and training paradigm on publicly available Tuberculosis x-ray dataset shows SOTA efficacy of SEDA compared to SEViT in terms of computational efficiency with 70x times lighter framework and enhanced robustness of +9%.
PDF Accepted at DART (Domain Adaptation and Representation Transfer) Workshop, MICCAI, 2023. Code: https://github.com/Razaimam45/SEDA
点此查看论文截图
Painter: Teaching Auto-regressive Language Models to Draw Sketches
Authors:Reza Pourreza, Apratim Bhattacharyya, Sunny Panchal, Mingu Lee, Pulkit Madan, Roland Memisevic
Large language models (LLMs) have made tremendous progress in natural language understanding and they have also been successfully adopted in other domains such as computer vision, robotics, reinforcement learning, etc. In this work, we apply LLMs to image generation tasks by directly generating the virtual brush strokes to paint an image. We present Painter, an LLM that can convert user prompts in text description format to sketches by generating the corresponding brush strokes in an auto-regressive way. We construct Painter based on off-the-shelf LLM that is pre-trained on a large text corpus, by fine-tuning it on the new task while preserving language understanding capabilities. We create a dataset of diverse multi-object sketches paired with textual prompts that covers several object types and tasks. Painter can generate sketches from text descriptions, remove objects from canvas, and detect and classify objects in sketches. Although this is an unprecedented pioneering work in using LLMs for auto-regressive image generation, the results are very encouraging.
PDF
点此查看论文截图
SimFIR: A Simple Framework for Fisheye Image Rectification with Self-supervised Representation Learning
Authors:Hao Feng, Wendi Wang, Jiajun Deng, Wengang Zhou, Li Li, Houqiang Li
In fisheye images, rich distinct distortion patterns are regularly distributed in the image plane. These distortion patterns are independent of the visual content and provide informative cues for rectification. To make the best of such rectification cues, we introduce SimFIR, a simple framework for fisheye image rectification based on self-supervised representation learning. Technically, we first split a fisheye image into multiple patches and extract their representations with a Vision Transformer (ViT). To learn fine-grained distortion representations, we then associate different image patches with their specific distortion patterns based on the fisheye model, and further subtly design an innovative unified distortion-aware pretext task for their learning. The transfer performance on the downstream rectification task is remarkably boosted, which verifies the effectiveness of the learned representations. Extensive experiments are conducted, and the quantitative and qualitative results demonstrate the superiority of our method over the state-of-the-art algorithms as well as its strong generalization ability on real-world fisheye images.
PDF Accepted to ICCV 2023
点此查看论文截图
Which Transformer to Favor: A Comparative Analysis of Efficiency in Vision Transformers
Authors:Tobias Christian Nauen, Sebastian Palacio, Andreas Dengel
The growing popularity of Vision Transformers as the go-to models for image classification has led to an explosion of architectural modifications claiming to be more efficient than the original ViT. However, a wide diversity of experimental conditions prevents a fair comparison between all of them, based solely on their reported results. To address this gap in comparability, we conduct a comprehensive analysis of more than 30 models to evaluate the efficiency of vision transformers and related architectures, considering various performance metrics. Our benchmark provides a comparable baseline across the landscape of efficiency-oriented transformers, unveiling a plethora of surprising insights. For example, we discover that ViT is still Pareto optimal across multiple efficiency metrics, despite the existence of several alternative approaches claiming to be more efficient. Results also indicate that hybrid attention-CNN models fare particularly well when it comes to low inference memory and number of parameters, and also that it is better to scale the model size, than the image size. Furthermore, we uncover a strong positive correlation between the number of FLOPS and the training memory, which enables the estimation of required VRAM from theoretical measurements alone. Thanks to our holistic evaluation, this study offers valuable insights for practitioners and researchers, facilitating informed decisions when selecting models for specific applications. We publicly release our code and data at https://github.com/tobna/WhatTransformerToFavor
PDF
点此查看论文截图
BLIVA: A Simple Multimodal LLM for Better Handling of Text-Rich Visual Questions
Authors:Wenbo Hu, Yifan Xu, Yi Li, Weiyue Li, Zeyuan Chen, Zhuowen Tu
Vision Language Models (VLMs), which extend Large Language Models (LLM) by incorporating visual understanding capability, have demonstrated significant advancements in addressing open-ended visual question-answering (VQA) tasks. However, these models cannot accurately interpret images infused with text, a common occurrence in real-world scenarios. Standard procedures for extracting information from images often involve learning a fixed set of query embeddings. These embeddings are designed to encapsulate image contexts and are later used as soft prompt inputs in LLMs. Yet, this process is limited to the token count, potentially curtailing the recognition of scenes with text-rich context. To improve upon them, the present study introduces BLIVA: an augmented version of InstructBLIP with Visual Assistant. BLIVA incorporates the query embeddings from InstructBLIP and also directly projects encoded patch embeddings into the LLM, a technique inspired by LLaVA. This approach assists the model to capture intricate details potentially missed during the query decoding process. Empirical evidence demonstrates that our model, BLIVA, significantly enhances performance in processing text-rich VQA benchmarks (up to 17.76\% in OCR-VQA benchmark) and in undertaking typical VQA benchmarks (up to 7.9\% in Visual Spatial Reasoning benchmark), comparing to our baseline InstructBLIP. BLIVA demonstrates significant capability in decoding real-world images, irrespective of text presence. To demonstrate the broad industry applications enabled by BLIVA, we evaluate the model using a new dataset comprising YouTube thumbnails paired with question-answer sets across 13 diverse categories. For researchers interested in further exploration, our code and models are freely accessible at https://github.com/mlpc-ucsd/BLIVA.git
PDF
点此查看论文截图
DPL: Decoupled Prompt Learning for Vision-Language Models
Authors:Chen Xu, Yuhan Zhu, Guozhen Zhang, Haocheng Shen, Yixuan Liao, Xiaoxin Chen, Gangshan Wu, Limin Wang
Prompt learning has emerged as an efficient and effective approach for transferring foundational Vision-Language Models (e.g., CLIP) to downstream tasks. However, current methods tend to overfit to seen categories, thereby limiting their generalization ability for unseen classes. In this paper, we propose a new method, Decoupled Prompt Learning (DPL), which reformulates the attention in prompt learning to alleviate this problem. Specifically, we theoretically investigate the collaborative process between prompts and instances (i.e., image patches/text tokens) by reformulating the original self-attention into four separate sub-processes. Through detailed analysis, we observe that certain sub-processes can be strengthened to bolster robustness and generalizability by some approximation techniques. Furthermore, we introduce language-conditioned textual prompting based on decoupled attention to naturally preserve the generalization of text input. Our approach is flexible for both visual and textual modalities, making it easily extendable to multi-modal prompt learning. By combining the proposed techniques, our approach achieves state-of-the-art performance on three representative benchmarks encompassing 15 image recognition datasets, while maintaining parameter-efficient. Moreover, our DPL does not rely on any auxiliary regularization task or extra training data, further demonstrating its remarkable generalization ability.
PDF 11 pages, 5 figures, 8 tables
点此查看论文截图
ViT-Lens: Towards Omni-modal Representations
Authors:Weixian Lei, Yixiao Ge, Jianfeng Zhang, Dylan Sun, Kun Yi, Ying Shan, Mike Zheng Shou
Though the success of CLIP-based training recipes in vision-language models, their scalability to more modalities (e.g., 3D, audio, etc.) is limited to large-scale data, which is expensive or even inapplicable for rare modalities. In this paper, we present ViT-Lens that facilitates efficient omni-modal representation learning by perceiving novel modalities with a pretrained ViT and aligning to a pre-defined space. Specifically, the modality-specific lens is tuned to project multimodal signals to the shared embedding space, which are then processed by a strong ViT that carries pre-trained image knowledge. The encoded multimodal representations are optimized toward aligning with the modal-independent space, pre-defined by off-the-shelf foundation models. A well-trained lens with a ViT backbone has the potential to serve as one of these foundation models, supervising the learning of subsequent modalities. ViT-Lens provides a unified solution for representation learning of increasing modalities with two appealing benefits: (i) Exploiting the pretrained ViT across tasks and domains effectively with efficient data regime; (ii) Emergent downstream capabilities of novel modalities are demonstrated due to the modality alignment space. We evaluate ViT-Lens in the context of 3D as an initial verification. In zero-shot 3D classification, ViT-Lens achieves substantial improvements over previous state-of-the-art, showing 52.0% accuracy on Objaverse-LVIS, 87.4% on ModelNet40, and 60.6% on ScanObjectNN. Furthermore, we enable zero-shot 3D question-answering by simply integrating the trained 3D lens into the InstructBLIP model without any adaptation. We will release the results of ViT-Lens on more modalities in the near future.
PDF 19 pages, 4 figures and 9 tables
点此查看论文截图
Jumping through Local Minima: Quantization in the Loss Landscape of Vision Transformers
Authors:Natalia Frumkin, Dibakar Gope, Diana Marculescu
Quantization scale and bit-width are the most important parameters when considering how to quantize a neural network. Prior work focuses on optimizing quantization scales in a global manner through gradient methods (gradient descent \& Hessian analysis). Yet, when applying perturbations to quantization scales, we observe a very jagged, highly non-smooth test loss landscape. In fact, small perturbations in quantization scale can greatly affect accuracy, yielding a $0.5-0.8\%$ accuracy boost in 4-bit quantized vision transformers (ViTs). In this regime, gradient methods break down, since they cannot reliably reach local minima. In our work, dubbed Evol-Q, we use evolutionary search to effectively traverse the non-smooth landscape. Additionally, we propose using an infoNCE loss, which not only helps combat overfitting on the small calibration dataset ($1,000$ images) but also makes traversing such a highly non-smooth surface easier. Evol-Q improves the top-1 accuracy of a fully quantized ViT-Base by $10.30\%$, $0.78\%$, and $0.15\%$ for $3$-bit, $4$-bit, and $8$-bit weight quantization levels. Extensive experiments on a variety of CNN and ViT architectures further demonstrate its robustness in extreme quantization scenarios. Our code is available at https://github.com/enyac-group/evol-q
PDF arXiv admin note: text overlap with arXiv:2211.09643
点此查看论文截图
Video OWL-ViT: Temporally-consistent open-world localization in video
Authors:Georg Heigold, Matthias Minderer, Alexey Gritsenko, Alex Bewley, Daniel Keysers, Mario Lučić, Fisher Yu, Thomas Kipf
We present an architecture and a training recipe that adapts pre-trained open-world image models to localization in videos. Understanding the open visual world (without being constrained by fixed label spaces) is crucial for many real-world vision tasks. Contrastive pre-training on large image-text datasets has recently led to significant improvements for image-level tasks. For more structured tasks involving object localization applying pre-trained models is more challenging. This is particularly true for video tasks, where task-specific data is limited. We show successful transfer of open-world models by building on the OWL-ViT open-vocabulary detection model and adapting it to video by adding a transformer decoder. The decoder propagates object representations recurrently through time by using the output tokens for one frame as the object queries for the next. Our model is end-to-end trainable on video data and enjoys improved temporal consistency compared to tracking-by-detection baselines, while retaining the open-world capabilities of the backbone detector. We evaluate our model on the challenging TAO-OW benchmark and demonstrate that open-world capabilities, learned from large-scale image-text pre-training, can be transferred successfully to open-world localization across diverse videos.
PDF ICCV 2023
点此查看论文截图
Knowledge-Aware Prompt Tuning for Generalizable Vision-Language Models
Authors:Baoshuo Kan, Teng Wang, Wenpeng Lu, Xiantong Zhen, Weili Guan, Feng Zheng
Pre-trained vision-language models, e.g., CLIP, working with manually designed prompts have demonstrated great capacity of transfer learning. Recently, learnable prompts achieve state-of-the-art performance, which however are prone to overfit to seen classes, failing to generalize to unseen classes. In this paper, we propose a Knowledge-Aware Prompt Tuning (KAPT) framework for vision-language models. Our approach takes inspiration from human intelligence in which external knowledge is usually incorporated into recognizing novel categories of objects. Specifically, we design two complementary types of knowledge-aware prompts for the text encoder to leverage the distinctive characteristics of category-related external knowledge. The discrete prompt extracts the key information from descriptions of an object category, and the learned continuous prompt captures overall contexts. We further design an adaptation head for the visual encoder to aggregate salient attentive visual cues, which establishes discriminative and task-aware visual representations. We conduct extensive experiments on 11 widely-used benchmark datasets and the results verify the effectiveness in few-shot image classification, especially in generalizing to unseen categories. Compared with the state-of-the-art CoCoOp method, KAPT exhibits favorable performance and achieves an absolute gain of 3.22% on new classes and 2.57% in terms of harmonic mean.
PDF Accepted by ICCV 2023
点此查看论文截图
Local Distortion Aware Efficient Transformer Adaptation for Image Quality Assessment
Authors:Kangmin Xu, Liang Liao, Jing Xiao, Chaofeng Chen, Haoning Wu, Qiong Yan, Weisi Lin
Image Quality Assessment (IQA) constitutes a fundamental task within the field of computer vision, yet it remains an unresolved challenge, owing to the intricate distortion conditions, diverse image contents, and limited availability of data. Recently, the community has witnessed the emergence of numerous large-scale pretrained foundation models, which greatly benefit from dramatically increased data and parameter capacities. However, it remains an open problem whether the scaling law in high-level tasks is also applicable to IQA task which is closely related to low-level clues. In this paper, we demonstrate that with proper injection of local distortion features, a larger pretrained and fixed foundation model performs better in IQA tasks. Specifically, for the lack of local distortion structure and inductive bias of vision transformer (ViT), alongside the large-scale pretrained ViT, we use another pretrained convolution neural network (CNN), which is well known for capturing the local structure, to extract multi-scale image features. Further, we propose a local distortion extractor to obtain local distortion features from the pretrained CNN and a local distortion injector to inject the local distortion features into ViT. By only training the extractor and injector, our method can benefit from the rich knowledge in the powerful foundation models and achieve state-of-the-art performance on popular IQA datasets, indicating that IQA is not only a low-level problem but also benefits from stronger high-level features drawn from large-scale pretrained models.
PDF
点此查看论文截图
Masking Strategies for Background Bias Removal in Computer Vision Models
Authors:Ananthu Aniraj, Cassio F. Dantas, Dino Ienco, Diego Marcos
Models for fine-grained image classification tasks, where the difference between some classes can be extremely subtle and the number of samples per class tends to be low, are particularly prone to picking up background-related biases and demand robust methods to handle potential examples with out-of-distribution (OOD) backgrounds. To gain deeper insights into this critical problem, our research investigates the impact of background-induced bias on fine-grained image classification, evaluating standard backbone models such as Convolutional Neural Network (CNN) and Vision Transformers (ViT). We explore two masking strategies to mitigate background-induced bias: Early masking, which removes background information at the (input) image level, and late masking, which selectively masks high-level spatial features corresponding to the background. Extensive experiments assess the behavior of CNN and ViT models under different masking strategies, with a focus on their generalization to OOD backgrounds. The obtained findings demonstrate that both proposed strategies enhance OOD performance compared to the baseline models, with early masking consistently exhibiting the best OOD performance. Notably, a ViT variant employing GAP-Pooled Patch token-based classification combined with early masking achieves the highest OOD robustness.
PDF Accepted at the 2023 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW) on Out Of Distribution Generalization in Computer Vision (OOD-CV)
点此查看论文截图
Towards Realistic Zero-Shot Classification via Self Structural Semantic Alignment
Authors:Sheng Zhang, Muzammal Naseer, Guangyi Chen, Zhiqiang Shen, Salman Khan, Kun Zhang, Fahad Khan
Large-scale pre-trained Vision Language Models (VLMs) have proven effective for zero-shot classification. Despite the success, most traditional VLMs-based methods are restricted by the assumption of partial source supervision or ideal vocabularies, which rarely satisfy the open-world scenario. In this paper, we aim at a more challenging setting, Realistic Zero-Shot Classification, which assumes no annotation but instead a broad vocabulary. To address this challenge, we propose the Self Structural Semantic Alignment (S^3A) framework, which extracts the structural semantic information from unlabeled data while simultaneously self-learning. Our S^3A framework adopts a unique Cluster-Vote-Prompt-Realign (CVPR) algorithm, which iteratively groups unlabeled data to derive structural semantics for pseudo-supervision. Our CVPR process includes iterative clustering on images, voting within each cluster to identify initial class candidates from the vocabulary, generating discriminative prompts with large language models to discern confusing candidates, and realigning images and the vocabulary as structural semantic alignment. Finally, we propose to self-learn the CLIP image encoder with both individual and structural semantic alignment through a teacher-student learning strategy. Our comprehensive experiments across various generic and fine-grained benchmarks demonstrate that the S^3A method offers substantial improvements over existing VLMs-based approaches, achieving a more than 15% accuracy improvement over CLIP on average. Our codes, models, and prompts are publicly released at https://github.com/sheng-eatamath/S3A.
PDF submission at 24 Aug
点此查看论文截图