2023-09-28 更新
LoGoPrompt: Synthetic Text Images Can Be Good Visual Prompts for Vision-Language Models
Authors:Cheng Shi, Sibei Yang
Prompt engineering is a powerful tool used to enhance the performance of pre-trained models on downstream tasks. For example, providing the prompt “Let’s think step by step” improved GPT-3’s reasoning accuracy to 63% on MutiArith while prompting “a photo of” filled with a class name enables CLIP to achieve $80$\% zero-shot accuracy on ImageNet. While previous research has explored prompt learning for the visual modality, analyzing what constitutes a good visual prompt specifically for image recognition is limited. In addition, existing visual prompt tuning methods’ generalization ability is worse than text-only prompting tuning. This paper explores our key insight: synthetic text images are good visual prompts for vision-language models! To achieve that, we propose our LoGoPrompt, which reformulates the classification objective to the visual prompt selection and addresses the chicken-and-egg challenge of first adding synthetic text images as class-wise visual prompts or predicting the class first. Without any trainable visual prompt parameters, experimental results on 16 datasets demonstrate that our method consistently outperforms state-of-the-art methods in few-shot learning, base-to-new generalization, and domain generalization.
PDF ICCV 2023; Project Page:https://chengshiest.github.io/logo
点此查看论文截图
Language Models as Black-Box Optimizers for Vision-Language Models
Authors:Shihong Liu, Samuel Yu, Zhiqiu Lin, Deepak Pathak, Deva Ramanan
Vision-language models (VLMs) pre-trained on web-scale datasets have demonstrated remarkable capabilities across a variety of vision and multimodal tasks. Currently, fine-tuning methods for VLMs mainly operate in a white-box setting, requiring access to model parameters for backpropagation. However, many VLMs rely on proprietary data and are not open-source, which restricts the use of white-box approaches for fine-tuning. Given that popular private large language models (LLMs) like ChatGPT still offer a language-based user interface, we aim to develop a novel fine-tuning approach for VLMs through natural language prompts, thereby avoiding the need to access model parameters, feature embeddings, or output logits. In this setup, we propose employing chat-based LLMs as black-box optimizers to search for the best text prompt on the illustrative task of few-shot image classification using CLIP. Specifically, we adopt an automatic “hill-climbing” procedure that converges on an effective prompt by evaluating the accuracy of current prompts and asking LLMs to refine them based on textual feedback, all within a conversational process without human-in-the-loop. In a challenging 1-shot learning setup, our simple approach surpasses the white-box continuous prompting method (CoOp) by an average of 1.5% across 11 datasets including ImageNet. Our approach also outperforms OpenAI’s manually crafted prompts. Additionally, we highlight the advantage of conversational feedback that incorporates both positive and negative prompts, suggesting that LLMs can utilize the implicit “gradient” direction in textual feedback for a more efficient search. Lastly, we find that the text prompts generated through our strategy are not only more interpretable but also transfer well across different CLIP architectures in a black-box manner.
PDF
点此查看论文截图
SAMUS: Adapting Segment Anything Model for Clinically-Friendly and Generalizable Ultrasound Image Segmentation
Authors:Xian Lin, Yangyang Xiang, Li Zhang, Xin Yang, Zengqiang Yan, Li Yu
Segment anything model (SAM), an eminent universal image segmentation model, has recently gathered considerable attention within the domain of medical image segmentation. Despite the remarkable performance of SAM on natural images, it grapples with significant performance degradation and limited generalization when confronted with medical images, particularly with those involving objects of low contrast, faint boundaries, intricate shapes, and diminutive sizes. In this paper, we propose SAMUS, a universal model tailored for ultrasound image segmentation. In contrast to previous SAM-based universal models, SAMUS pursues not only better generalization but also lower deployment cost, rendering it more suitable for clinical applications. Specifically, based on SAM, a parallel CNN branch is introduced to inject local features into the ViT encoder through cross-branch attention for better medical image segmentation. Then, a position adapter and a feature adapter are developed to adapt SAM from natural to medical domains and from requiring large-size inputs (1024x1024) to small-size inputs (256x256) for more clinical-friendly deployment. A comprehensive ultrasound dataset, comprising about 30k images and 69k masks and covering six object categories, is collected for verification. Extensive comparison experiments demonstrate SAMUS’s superiority against the state-of-the-art task-specific models and universal foundation models under both task-specific evaluation and generalization evaluation. Moreover, SAMUS is deployable on entry-level GPUs, as it has been liberated from the constraints of long sequence encoding. The code, data, and models will be released at https://github.com/xianlin7/SAMUS.
PDF
点此查看论文截图
Co-Salient Object Detection with Semantic-Level Consensus Extraction and Dispersion
Authors:Peiran Xu, Yadong Mu
Given a group of images, co-salient object detection (CoSOD) aims to highlight the common salient object in each image. There are two factors closely related to the success of this task, namely consensus extraction, and the dispersion of consensus to each image. Most previous works represent the group consensus using local features, while we instead utilize a hierarchical Transformer module for extracting semantic-level consensus. Therefore, it can obtain a more comprehensive representation of the common object category, and exclude interference from other objects that share local similarities with the target object. In addition, we propose a Transformer-based dispersion module that takes into account the variation of the co-salient object in different scenes. It distributes the consensus to the image feature maps in an image-specific way while making full use of interactions within the group. These two modules are integrated with a ViT encoder and an FPN-like decoder to form an end-to-end trainable network, without additional branch and auxiliary loss. The proposed method is evaluated on three commonly used CoSOD datasets and achieves state-of-the-art performance.
PDF Accepted by ACM MM 2023
点此查看论文截图
Interpretability-Aware Vision Transformer
Authors:Yao Qiang, Chengyin Li, Prashant Khanduri, Dongxiao Zhu
Vision Transformers (ViTs) have become prominent models for solving various vision tasks. However, the interpretability of ViTs has not kept pace with their promising performance. While there has been a surge of interest in developing {\it post hoc} solutions to explain ViTs’ outputs, these methods do not generalize to different downstream tasks and various transformer architectures. Furthermore, if ViTs are not properly trained with the given data and do not prioritize the region of interest, the {\it post hoc} methods would be less effective. Instead of developing another {\it post hoc} approach, we introduce a novel training procedure that inherently enhances model interpretability. Our interpretability-aware ViT (IA-ViT) draws inspiration from a fresh insight: both the class patch and image patches consistently generate predicted distributions and attention maps. IA-ViT is composed of a feature extractor, a predictor, and an interpreter, which are trained jointly with an interpretability-aware training objective. Consequently, the interpreter simulates the behavior of the predictor and provides a faithful explanation through its single-head self-attention mechanism. Our comprehensive experimental results demonstrate the effectiveness of IA-ViT in several image classification tasks, with both qualitative and quantitative evaluations of model performance and interpretability. Source code is available from: https://github.com/qiangyao1988/IA-ViT.
PDF 10 pages, 4 figures, 5 tables
点此查看论文截图
AnyOKP: One-Shot and Instance-Aware Object Keypoint Extraction with Pretrained ViT
Authors:Fangbo Qin, Taogang Hou, Shan Lin, Kaiyuan Wang, Michael C. Yip, Shan Yu
Towards flexible object-centric visual perception, we propose a one-shot instance-aware object keypoint (OKP) extraction approach, AnyOKP, which leverages the powerful representation ability of pretrained vision transformer (ViT), and can obtain keypoints on multiple object instances of arbitrary category after learning from a support image. An off-the-shelf petrained ViT is directly deployed for generalizable and transferable feature extraction, which is followed by training-free feature enhancement. The best-prototype pairs (BPPs) are searched for in support and query images based on appearance similarity, to yield instance-unaware candidate keypoints.Then, the entire graph with all candidate keypoints as vertices are divided to sub-graphs according to the feature distributions on the graph edges. Finally, each sub-graph represents an object instance. AnyOKP is evaluated on real object images collected with the cameras of a robot arm, a mobile robot, and a surgical robot, which not only demonstrates the cross-category flexibility and instance awareness, but also show remarkable robustness to domain shift and viewpoint change.
PDF Submitted to IEEE ICRA 2024 as a contributed paper
点此查看论文截图
MMST-ViT: Climate Change-aware Crop Yield Prediction via Multi-Modal Spatial-Temporal Vision Transformer
Authors:Fudong Lin, Summer Crawford, Kaleb Guillot, Yihe Zhang, Yan Chen, Xu Yuan, Li Chen, Shelby Williams, Robert Minvielle, Xiangming Xiao, Drew Gholson, Nicolas Ashwell, Tri Setiyono, Brenda Tubana, Lu Peng, Magdy Bayoumi, Nian-Feng Tzeng
Precise crop yield prediction provides valuable information for agricultural planning and decision-making processes. However, timely predicting crop yields remains challenging as crop growth is sensitive to growing season weather variation and climate change. In this work, we develop a deep learning-based solution, namely Multi-Modal Spatial-Temporal Vision Transformer (MMST-ViT), for predicting crop yields at the county level across the United States, by considering the effects of short-term meteorological variations during the growing season and the long-term climate change on crops. Specifically, our MMST-ViT consists of a Multi-Modal Transformer, a Spatial Transformer, and a Temporal Transformer. The Multi-Modal Transformer leverages both visual remote sensing data and short-term meteorological data for modeling the effect of growing season weather variations on crop growth. The Spatial Transformer learns the high-resolution spatial dependency among counties for accurate agricultural tracking. The Temporal Transformer captures the long-range temporal dependency for learning the impact of long-term climate change on crops. Meanwhile, we also devise a novel multi-modal contrastive learning technique to pre-train our model without extensive human supervision. Hence, our MMST-ViT captures the impacts of both short-term weather variations and long-term climate change on crops by leveraging both satellite images and meteorological data. We have conducted extensive experiments on over 200 counties in the United States, with the experimental results exhibiting that our MMST-ViT outperforms its counterparts under three performance metrics of interest.
PDF
点此查看论文截图
DualToken-ViT: Position-aware Efficient Vision Transformer with Dual Token Fusion
Authors:Zhenzhen Chu, Jiayu Chen, Cen Chen, Chengyu Wang, Ziheng Wu, Jun Huang, Weining Qian
Self-attention-based vision transformers (ViTs) have emerged as a highly competitive architecture in computer vision. Unlike convolutional neural networks (CNNs), ViTs are capable of global information sharing. With the development of various structures of ViTs, ViTs are increasingly advantageous for many vision tasks. However, the quadratic complexity of self-attention renders ViTs computationally intensive, and their lack of inductive biases of locality and translation equivariance demands larger model sizes compared to CNNs to effectively learn visual features. In this paper, we propose a light-weight and efficient vision transformer model called DualToken-ViT that leverages the advantages of CNNs and ViTs. DualToken-ViT effectively fuses the token with local information obtained by convolution-based structure and the token with global information obtained by self-attention-based structure to achieve an efficient attention structure. In addition, we use position-aware global tokens throughout all stages to enrich the global information, which further strengthening the effect of DualToken-ViT. Position-aware global tokens also contain the position information of the image, which makes our model better for vision tasks. We conducted extensive experiments on image classification, object detection and semantic segmentation tasks to demonstrate the effectiveness of DualToken-ViT. On the ImageNet-1K dataset, our models of different scales achieve accuracies of 75.4% and 79.4% with only 0.5G and 1.0G FLOPs, respectively, and our model with 1.0G FLOPs outperforms LightViT-T using global tokens by 0.7%.
PDF
点此查看论文截图
Detect Every Thing with Few Examples
Authors:Xinyu Zhang, Yuting Wang, Abdeslam Boularias
Open-set object detection aims at detecting arbitrary categories beyond those seen during training. Most recent advancements have adopted the open-vocabulary paradigm, utilizing vision-language backbones to represent categories with language. In this paper, we introduce DE-ViT, an open-set object detector that employs vision-only DINOv2 backbones and learns new categories through example images instead of language. To improve general detection ability, we transform multi-classification tasks into binary classification tasks while bypassing per-class inference, and propose a novel region propagation technique for localization. We evaluate DE-ViT on open-vocabulary, few-shot, and one-shot object detection benchmark with COCO and LVIS. For COCO, DE-ViT outperforms the open-vocabulary SoTA by 6.9 AP50 and achieves 50 AP50 in novel classes. DE-ViT surpasses the few-shot SoTA by 15 mAP on 10-shot and 7.2 mAP on 30-shot and one-shot SoTA by 2.8 AP50. For LVIS, DE-ViT outperforms the open-vocabulary SoTA by 2.2 mask AP and reaches 34.3 mask APr. Code is available at https://github.com/mlzxy/devit.
PDF
点此查看论文截图
Randomize to Generalize: Domain Randomization for Runway FOD Detection
Authors:Javaria Farooq, Nayyer Aafaq, M Khizer Ali Khan, Ammar Saleem, M Ibraheem Siddiqui
Tiny Object Detection is challenging due to small size, low resolution, occlusion, background clutter, lighting conditions and small object-to-image ratio. Further, object detection methodologies often make underlying assumption that both training and testing data remain congruent. However, this presumption often leads to decline in performance when model is applied to out-of-domain(unseen) data. Techniques like synthetic image generation are employed to improve model performance by leveraging variations in input data. Such an approach typically presumes access to 3D-rendered datasets. In contrast, we propose a novel two-stage methodology Synthetic Randomized Image Augmentation (SRIA), carefully devised to enhance generalization capabilities of models encountering 2D datasets, particularly with lower resolution which is more practical in real-world scenarios. The first stage employs a weakly supervised technique to generate pixel-level segmentation masks. Subsequently, the second stage generates a batch-wise synthesis of artificial images, carefully designed with an array of diverse augmentations. The efficacy of proposed technique is illustrated on challenging foreign object debris (FOD) detection. We compare our results with several SOTA models including CenterNet, SSD, YOLOv3, YOLOv4, YOLOv5, and Outer Vit on a publicly available FOD-A dataset. We also construct an out-of-distribution test set encompassing 800 annotated images featuring a corpus of ten common categories. Notably, by harnessing merely 1.81% of objects from source training data and amalgamating with 29 runway background images, we generate 2227 synthetic images. Subsequent model retraining via transfer learning, utilizing enriched dataset generated by domain randomization, demonstrates significant improvement in detection accuracy. We report that detection accuracy improved from an initial 41% to 92% for OOD test set.
PDF 29 pages, 9 figures
点此查看论文截图
Improving Facade Parsing with Vision Transformers and Line Integration
Authors:Bowen Wang, Jiaxing Zhang, Ran Zhang, Yunqin Li, Liangzhi Li, Yuta Nakashima
Facade parsing stands as a pivotal computer vision task with far-reaching applications in areas like architecture, urban planning, and energy efficiency. Despite the recent success of deep learning-based methods in yielding impressive results on certain open-source datasets, their viability for real-world applications remains uncertain. Real-world scenarios are considerably more intricate, demanding greater computational efficiency. Existing datasets often fall short in representing these settings, and previous methods frequently rely on extra models to enhance accuracy, which requires much computation cost. In this paper, we introduce Comprehensive Facade Parsing (CFP), a dataset meticulously designed to encompass the intricacies of real-world facade parsing tasks. Comprising a total of 602 high-resolution street-view images, this dataset captures a diverse array of challenging scenarios, including sloping angles and densely clustered buildings, with painstakingly curated annotations for each image. We introduce a new pipeline known as Revision-based Transformer Facade Parsing (RTFP). This marks the pioneering utilization of Vision Transformers (ViT) in facade parsing, and our experimental results definitively substantiate its merit. We also design Line Acquisition, Filtering, and Revision (LAFR), an efficient yet accurate revision algorithm that can improve the segment result solely from simple line detection using prior knowledge of the facade. In ECP 2011, RueMonge 2014, and our CFP, we evaluate the superiority of our method. The dataset and code are available at https://github.com/wbw520/RTFP.
PDF 13 pages, 7 figures, 9 tables
点此查看论文截图
CAIT: Triple-Win Compression towards High Accuracy, Fast Inference, and Favorable Transferability For ViTs
Authors:Ao Wang, Hui Chen, Zijia Lin, Sicheng Zhao, Jungong Han, Guiguang Ding
Vision Transformers (ViTs) have emerged as state-of-the-art models for various vision tasks recently. However, their heavy computation costs remain daunting for resource-limited devices. Consequently, researchers have dedicated themselves to compressing redundant information in ViTs for acceleration. However, they generally sparsely drop redundant image tokens by token pruning or brutally remove channels by channel pruning, leading to a sub-optimal balance between model performance and inference speed. They are also disadvantageous in transferring compressed models to downstream vision tasks that require the spatial structure of images, such as semantic segmentation. To tackle these issues, we propose a joint compression method for ViTs that offers both high accuracy and fast inference speed, while also maintaining favorable transferability to downstream tasks (CAIT). Specifically, we introduce an asymmetric token merging (ATME) strategy to effectively integrate neighboring tokens. It can successfully compress redundant token information while preserving the spatial structure of images. We further employ a consistent dynamic channel pruning (CDCP) strategy to dynamically prune unimportant channels in ViTs. Thanks to CDCP, insignificant channels in multi-head self-attention modules of ViTs can be pruned uniformly, greatly enhancing the model compression. Extensive experiments on benchmark datasets demonstrate that our proposed method can achieve state-of-the-art performance across various ViTs. For example, our pruned DeiT-Tiny and DeiT-Small achieve speedups of 1.7$\times$ and 1.9$\times$, respectively, without accuracy drops on ImageNet. On the ADE20k segmentation dataset, our method can enjoy up to 1.31$\times$ speedups with comparable mIoU. Our code will be publicly available.
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
点此查看论文截图