2023-03-04 更新
CapEnrich: Enriching Caption Semantics for Web Images via Cross-modal Pre-trained Knowledge
Authors:Linli Yao, Weijing Chen, Qin Jin
Automatically generating textual descriptions for massive unlabeled images on the web can greatly benefit realistic web applications, e.g. multimodal retrieval and recommendation. However, existing models suffer from the problem of generating ``over-generic’’ descriptions, such as their tendency to generate repetitive sentences with common concepts for different images. These generic descriptions fail to provide sufficient textual semantics for ever-changing web images. Inspired by the recent success of Vision-Language Pre-training (VLP) models that learn diverse image-text concept alignment during pretraining, we explore leveraging their cross-modal pre-trained knowledge to automatically enrich the textual semantics of image descriptions. With no need for additional human annotations, we propose a plug-and-play framework, i.e CapEnrich, to complement the generic image descriptions with more semantic details. Specifically, we first propose an automatic data-building strategy to get desired training sentences, based on which we then adopt prompting strategies, i.e. learnable and template prompts, to incentivize VLP models to generate more textual details. For learnable templates, we fix the whole VLP model and only tune the prompt vectors, which leads to two advantages: 1) the pre-training knowledge of VLP models can be reserved as much as possible to describe diverse visual concepts; 2) only lightweight trainable parameters are required, so it is friendly to low data resources. Extensive experiments show that our method significantly improves the descriptiveness and diversity of generated sentences for web images. The code is available at https://github.com/yaolinli/CapEnrich.
PDF Accepted to WWW2023
点此查看论文截图
TFormer: A Transmission-Friendly ViT Model for IoT Devices
Authors:Zhichao Lu, Chuntao Ding, Felix Juefei-Xu, Vishnu Naresh Boddeti, Shangguang Wang, Yun Yang
Deploying high-performance vision transformer (ViT) models on ubiquitous Internet of Things (IoT) devices to provide high-quality vision services will revolutionize the way we live, work, and interact with the world. Due to the contradiction between the limited resources of IoT devices and resource-intensive ViT models, the use of cloud servers to assist ViT model training has become mainstream. However, due to the larger number of parameters and floating-point operations (FLOPs) of the existing ViT models, the model parameters transmitted by cloud servers are large and difficult to run on resource-constrained IoT devices. To this end, this paper proposes a transmission-friendly ViT model, TFormer, for deployment on resource-constrained IoT devices with the assistance of a cloud server. The high performance and small number of model parameters and FLOPs of TFormer are attributed to the proposed hybrid layer and the proposed partially connected feed-forward network (PCS-FFN). The hybrid layer consists of nonlearnable modules and a pointwise convolution, which can obtain multitype and multiscale features with only a few parameters and FLOPs to improve the TFormer performance. The PCS-FFN adopts group convolution to reduce the number of parameters. The key idea of this paper is to propose TFormer with few model parameters and FLOPs to facilitate applications running on resource-constrained IoT devices to benefit from the high performance of the ViT models. Experimental results on the ImageNet-1K, MS COCO, and ADE20K datasets for image classification, object detection, and semantic segmentation tasks demonstrate that the proposed model outperforms other state-of-the-art models. Specifically, TFormer-S achieves 5% higher accuracy on ImageNet-1K than ResNet18 with 1.4$\times$ fewer parameters and FLOPs.
PDF IEEE Transactions on Parallel and Distributed Systems
点此查看论文截图
Towards Efficient Visual Adaption via Structural Re-parameterization
Authors:Gen Luo, Minglang Huang, Yiyi Zhou, Xiaoshuai Sun, Guannan Jiang, Zhiyu Wang, Rongrong Ji
Parameter-efficient transfer learning (PETL) is an emerging research spot aimed at inexpensively adapting large-scale pre-trained models to downstream tasks. Recent advances have achieved great success in saving storage costs for various vision tasks by updating or injecting a small number of parameters instead of full fine-tuning. However, we notice that most existing PETL methods still incur non-negligible latency during inference. In this paper, we propose a parameter-efficient and computationally friendly adapter for giant vision models, called RepAdapter. Specifically, we prove that the adaption modules, even with a complex structure, can be seamlessly integrated into most giant vision models via structural re-parameterization. This property makes RepAdapter zero-cost during inference. In addition to computation efficiency, RepAdapter is more effective and lightweight than existing PETL methods due to its sparse structure and our careful deployment. To validate RepAdapter, we conduct extensive experiments on 27 benchmark datasets of three vision tasks, i.e., image and video classifications and semantic segmentation. Experimental results show the superior performance and efficiency of RepAdapter than the state-of-the-art PETL methods. For instance, by updating only 0.6% parameters, we can improve the performance of ViT from 38.8 to 55.1 on Sun397. Its generalizability is also well validated by a bunch of vision models, i.e., ViT, CLIP, Swin-Transformer and ConvNeXt. Our source code is released at https://github.com/luogen1996/RepAdapter.
PDF
点此查看论文截图
MCAE: Masked Contrastive Autoencoder for Face Anti-Spoofing
Authors:Tianyi Zheng
Face anti-spoofing (FAS) method performs well under the intra-domain setups. But cross-domain performance of the model is not satisfying. Domain generalization method has been used to align the feature from different domain extracted by convolutional neural network (CNN) backbone. However, the improvement is limited. Recently, the Vision Transformer (ViT) model has performed well on various visual tasks. But ViT model relies heavily on pre-training of large-scale dataset, which cannot be satisfied by existing FAS datasets. In this paper, taking the FAS task as an example, we propose Masked Contrastive Autoencoder (MCAE) method to solve this problem using only limited data. Meanwhile in order for a feature extractor to extract common features in live samples from different domains, we combine Masked Image Model (MIM) with supervised contrastive learning to train our model.Some intriguing design principles are summarized for performing MIM pre-training for downstream tasks.We also provide insightful analysis for our method from an information theory perspective. Experimental results show our approach has good performance on extensive public datasets and outperforms the state-of-the-art methods.
PDF
点此查看论文截图
Meta Style Adversarial Training for Cross-Domain Few-Shot Learning
Authors:Yuqian Fu, Yu Xie, Yanwei Fu, Yu-Gang Jiang
Cross-Domain Few-Shot Learning (CD-FSL) is a recently emerging task that tackles few-shot learning across different domains. It aims at transferring prior knowledge learned on the source dataset to novel target datasets. The CD-FSL task is especially challenged by the huge domain gap between different datasets. Critically, such a domain gap actually comes from the changes of visual styles, and wave-SAN empirically shows that spanning the style distribution of the source data helps alleviate this issue. However, wave-SAN simply swaps styles of two images. Such a vanilla operation makes the generated styles real'' andeasy’’, which still fall into the original set of the source styles. Thus, inspired by vanilla adversarial learning, a novel model-agnostic meta Style Adversarial training (StyleAdv) method together with a novel style adversarial attack method is proposed for CD-FSL. Particularly, our style attack method synthesizes both virtual'' andhard’’ adversarial styles for model training. This is achieved by perturbing the original style with the signed style gradients. By continually attacking styles and forcing the model to recognize these challenging adversarial styles, our model is gradually robust to the visual styles, thus boosting the generalization ability for novel target datasets. Besides the typical CNN-based backbone, we also employ our StyleAdv method on large-scale pretrained vision transformer. Extensive experiments conducted on eight various target datasets show the effectiveness of our method. Whether built upon ResNet or ViT, we achieve the new state of the art for CD-FSL. Codes and models will be released.
PDF
点此查看论文截图
Time to Embrace Natural Language Processing (NLP)-based Digital Pathology: Benchmarking NLP- and Convolutional Neural Network-based Deep Learning Pipelines
Authors:Min Cen, Xingyu Li, Bangwei Guo, Jitendra Jonnagaddala, Hong Zhang, Xu Steven Xu
NLP-based computer vision models, particularly vision transformers, have been shown to outperform CNN models in many imaging tasks. However, most digital pathology artificial-intelligence models are based on CNN architectures, probably owing to a lack of data regarding NLP models for pathology images. In this study, we developed digital pathology pipelines to benchmark the five most recently proposed NLP models (vision transformer (ViT), Swin Transformer, MobileViT, CMT, and Sequencer2D) and four popular CNN models (ResNet18, ResNet50, MobileNetV2, and EfficientNet) to predict biomarkers in colorectal cancer (microsatellite instability, CpG island methylator phenotype, and BRAF mutation). Hematoxylin and eosin-stained whole-slide images from Molecular and Cellular Oncology and The Cancer Genome Atlas were used as training and external validation datasets, respectively. Cross-study external validations revealed that the NLP-based models significantly outperformed the CNN-based models in biomarker prediction tasks, improving the overall prediction and precision up to approximately 10% and 26%, respectively. Notably, compared with existing models in the current literature using large training datasets, our NLP models achieved state-of-the-art predictions for all three biomarkers using a relatively small training dataset, suggesting that large training datasets are not a prerequisite for NLP models or transformers, and NLP may be more suitable for clinical studies in which small training datasets are commonly collected. The superior performance of Sequencer2D suggests that further research and innovation on both transformer and bidirectional long short-term memory architectures are warranted in the field of digital pathology. NLP models can replace classic CNN architectures and become the new workhorse backbone in the field of digital pathology.
PDF
点此查看论文截图
Human MotionFormer: Transferring Human Motions with Vision Transformers
Authors:Hongyu Liu, Xintong Han, Chengbin Jin, Lihui Qian, Huawei Wei, Zhe Lin, Faqiang Wang, Haoye Dong, Yibing Song, Jia Xu, Qifeng Chen
Human motion transfer aims to transfer motions from a target dynamic person to a source static one for motion synthesis. An accurate matching between the source person and the target motion in both large and subtle motion changes is vital for improving the transferred motion quality. In this paper, we propose Human MotionFormer, a hierarchical ViT framework that leverages global and local perceptions to capture large and subtle motion matching, respectively. It consists of two ViT encoders to extract input features (i.e., a target motion image and a source human image) and a ViT decoder with several cascaded blocks for feature matching and motion transfer. In each block, we set the target motion feature as Query and the source person as Key and Value, calculating the cross-attention maps to conduct a global feature matching. Further, we introduce a convolutional layer to improve the local perception after the global cross-attention computations. This matching process is implemented in both warping and generation branches to guide the motion transfer. During training, we propose a mutual learning loss to enable the co-supervision between warping and generation branches for better motion representations. Experiments show that our Human MotionFormer sets the new state-of-the-art performance both qualitatively and quantitatively. Project page: \url{https://github.com/KumapowerLIU/Human-MotionFormer}
PDF Accepted by ICLR2023
点此查看论文截图
VLSP2022-EVJVQA Challenge: Multilingual Visual Question Answering
Authors:Ngan Luu-Thuy Nguyen, Nghia Hieu Nguyen, Duong T. D Vo, Khanh Quoc Tran, Kiet Van Nguyen
Visual Question Answering (VQA) is a challenging task of natural language processing (NLP) and computer vision (CV), attracting significant attention from researchers. English is a resource-rich language that has witnessed various developments in datasets and models for visual question answering. Visual question answering in other languages also would be developed for resources and models. In addition, there is no multilingual dataset targeting the visual content of a particular country with its own objects and cultural characteristics. To address the weakness, we provide the research community with a benchmark dataset named EVJVQA, including 33,000+ pairs of question-answer over three languages: Vietnamese, English, and Japanese, on approximately 5,000 images taken from Vietnam for evaluating multilingual VQA systems or models. EVJVQA is used as a benchmark dataset for the challenge of multilingual visual question answering at the 9th Workshop on Vietnamese Language and Speech Processing (VLSP 2022). This task attracted 62 participant teams from various universities and organizations. In this article, we present details of the organization of the challenge, an overview of the methods employed by shared-task participants, and the results. The highest performances are 0.4392 in F1-score and 0.4009 in BLUE on the private test set. The multilingual QA systems proposed by the top 2 teams use ViT for the pre-trained vision model and mT5 for the pre-trained language model, a powerful pre-trained language model based on the transformer architecture. EVJVQA is a challenging dataset that motivates NLP and CV researchers to further explore the multilingual models or systems for visual question answering systems.
PDF VLSP2022 EVJVQA challenge
点此查看论文截图
A framework for benchmarking class-out-of-distribution detection and its application to ImageNet
Authors:Ido Galil, Mohammed Dabbah, Ran El-Yaniv
When deployed for risk-sensitive tasks, deep neural networks must be able to detect instances with labels from outside the distribution for which they were trained. In this paper we present a novel framework to benchmark the ability of image classifiers to detect class-out-of-distribution instances (i.e., instances whose true labels do not appear in the training distribution) at various levels of detection difficulty. We apply this technique to ImageNet, and benchmark 525 pretrained, publicly available, ImageNet-1k classifiers. The code for generating a benchmark for any ImageNet-1k classifier, along with the benchmarks prepared for the above-mentioned 525 models is available at https://github.com/mdabbah/COOD_benchmarking. The usefulness of the proposed framework and its advantage over alternative existing benchmarks is demonstrated by analyzing the results obtained for these models, which reveals numerous novel observations including: (1) knowledge distillation consistently improves class-out-of-distribution (C-OOD) detection performance; (2) a subset of ViTs performs better C-OOD detection than any other model; (3) the language—vision CLIP model achieves good zero-shot detection performance, with its best instance outperforming 96% of all other models evaluated; (4) accuracy and in-distribution ranking are positively correlated to C-OOD detection; and (5) we compare various confidence functions for C-OOD detection. Our companion paper, also published in ICLR 2023 (What Can We Learn From The Selective Prediction And Uncertainty Estimation Performance Of 523 Imagenet Classifiers), examines the uncertainty estimation performance (ranking, calibration, and selective prediction performance) of these classifiers in an in-distribution setting.
PDF Published in ICLR 2023. arXiv admin note: text overlap with arXiv:2206.02152
点此查看论文截图
Boosting Adversarial Transferability using Dynamic Cues
Authors:Muzammal Naseer, Ahmad Mahmood, Salman Khan, Fahad Khan
The transferability of adversarial perturbations between image models has been extensively studied. In this case, an attack is generated from a known surrogate \eg, the ImageNet trained model, and transferred to change the decision of an unknown (black-box) model trained on an image dataset. However, attacks generated from image models do not capture the dynamic nature of a moving object or a changing scene due to a lack of temporal cues within image models. This leads to reduced transferability of adversarial attacks from representation-enriched \emph{image} models such as Supervised Vision Transformers (ViTs), Self-supervised ViTs (\eg, DINO), and Vision-language models (\eg, CLIP) to black-box \emph{video} models. In this work, we induce dynamic cues within the image models without sacrificing their original performance on images. To this end, we optimize \emph{temporal prompts} through frozen image models to capture motion dynamics. Our temporal prompts are the result of a learnable transformation that allows optimizing for temporal gradients during an adversarial attack to fool the motion dynamics. Specifically, we introduce spatial (image) and temporal (video) cues within the same source model through task-specific prompts. Attacking such prompts maximizes the adversarial transferability from image-to-video and image-to-image models using the attacks designed for image models. Our attack results indicate that the attacker does not need specialized architectures, \eg, divided space-time attention, 3D convolutions, or multi-view convolution networks for different data modalities. Image models are effective surrogates to optimize an adversarial attack to fool black-box models in a changing environment over time. Code is available at https://bit.ly/3Xd9gRQ
PDF International Conference on Learning Representations (ICLR’23), Code:https://bit.ly/3Xd9gRQ
点此查看论文截图
A Convolutional Vision Transformer for Semantic Segmentation of Side-Scan Sonar Data
Authors:Hayat Rajani, Nuno Gracias, Rafael Garcia
Distinguishing among different marine benthic habitat characteristics is of key importance in a wide set of seabed operations ranging from installations of oil rigs to laying networks of cables and monitoring the impact of humans on marine ecosystems. The Side-Scan Sonar (SSS) is a widely used imaging sensor in this regard. It produces high-resolution seafloor maps by logging the intensities of sound waves reflected back from the seafloor. In this work, we leverage these acoustic intensity maps to produce pixel-wise categorization of different seafloor types. We propose a novel architecture adapted from the Vision Transformer (ViT) in an encoder-decoder framework. Further, in doing so, the applicability of ViTs is evaluated on smaller datasets. To overcome the lack of CNN-like inductive biases, thereby making ViTs more conducive to applications in low data regimes, we propose a novel feature extraction module to replace the Multi-layer Perceptron (MLP) block within transformer layers and a novel module to extract multiscale patch embeddings. A lightweight decoder is also proposed to complement this design in order to further boost multiscale feature extraction. With the modified architecture, we achieve state-of-the-art results and also meet real-time computational requirements. We make our code available at ~\url{https://github.com/hayatrajani/s3seg-vit
PDF Submitted to Ocean Engineering special issue “Autonomous Marine Robotics Operations”
点此查看论文截图
Spatially-Adaptive Feature Modulation for Efficient Image Super-Resolution
Authors:Long Sun, Jiangxin Dong, Jinhui Tang, Jinshan Pan
Although numerous solutions have been proposed for image super-resolution, they are usually incompatible with low-power devices with many computational and memory constraints. In this paper, we address this problem by proposing a simple yet effective deep network to solve image super-resolution efficiently. In detail, we develop a spatially-adaptive feature modulation (SAFM) mechanism upon a vision transformer (ViT)-like block. Within it, we first apply the SAFM block over input features to dynamically select representative feature representations. As the SAFM block processes the input features from a long-range perspective, we further introduce a convolutional channel mixer (CCM) to simultaneously extract local contextual information and perform channel mixing. Extensive experimental results show that the proposed method is $3\times$ smaller than state-of-the-art efficient SR methods, e.g., IMDN, in terms of the network parameters and requires less computational cost while achieving comparable performance. The code is available at https://github.com/sunny2109/SAFMN.
PDF The code is available at https://github.com/sunny2109/SAFMN
点此查看论文截图
Efficient Masked Autoencoders with Self-Consistency
Authors:Zhaowen Li, Yousong Zhu, Zhiyang Chen, Wei Li, Chaoyang Zhao, Liwei Wu, Rui Zhao, Ming Tang, Jinqiao Wang
Inspired by masked language modeling (MLM) in natural language processing, masked image modeling (MIM) has been recognized as a strong and popular self-supervised pre-training method in computer vision. However, its high random mask ratio would result in two serious problems: 1) the data are not efficiently exploited, which brings inefficient pre-training (\eg, 1600 epochs for MAE $vs.$ 300 epochs for the supervised), and 2) the high uncertainty and inconsistency of the pre-trained model, \ie, the prediction of the same patch may be inconsistent under different mask rounds. To tackle these problems, we propose efficient masked autoencoders with self-consistency (EMAE), to improve the pre-training efficiency and increase the consistency of MIM. In particular, we progressively divide the image into K non-overlapping parts, each of which is generated by a random mask and has the same mask ratio. Then the MIM task is conducted parallelly on all parts in an iteration and generates predictions. Besides, we design a self-consistency module to further maintain the consistency of predictions of overlapping masked patches among parts. Overall, the proposed method is able to exploit the data more efficiently and obtains reliable representations. Experiments on ImageNet show that EMAE achieves even higher results with only 300 pre-training epochs under ViT-Base than MAE (1600 epochs). EMAE also consistently obtains state-of-the-art transfer performance on various downstream tasks, like object detection, and semantic segmentation.
PDF
点此查看论文截图
Mask3D: Pre-training 2D Vision Transformers by Learning Masked 3D Priors
Authors:Ji Hou, Xiaoliang Dai, Zijian He, Angela Dai, Matthias Nießner
Current popular backbones in computer vision, such as Vision Transformers (ViT) and ResNets are trained to perceive the world from 2D images. However, to more effectively understand 3D structural priors in 2D backbones, we propose Mask3D to leverage existing large-scale RGB-D data in a self-supervised pre-training to embed these 3D priors into 2D learned feature representations. In contrast to traditional 3D contrastive learning paradigms requiring 3D reconstructions or multi-view correspondences, our approach is simple: we formulate a pre-text reconstruction task by masking RGB and depth patches in individual RGB-D frames. We demonstrate the Mask3D is particularly effective in embedding 3D priors into the powerful 2D ViT backbone, enabling improved representation learning for various scene understanding tasks, such as semantic segmentation, instance segmentation and object detection. Experiments show that Mask3D notably outperforms existing self-supervised 3D pre-training approaches on ScanNet, NYUv2, and Cityscapes image understanding tasks, with an improvement of +6.5% mIoU against the state-of-the-art Pri3D on ScanNet image semantic segmentation.
PDF accepted to CVPR2023
点此查看论文截图
Generic-to-Specific Distillation of Masked Autoencoders
Authors:Wei Huang, Zhiliang Peng, Li Dong, Furu Wei, Jianbin Jiao, Qixiang Ye
Large vision Transformers (ViTs) driven by self-supervised pre-training mechanisms achieved unprecedented progress. Lightweight ViT models limited by the model capacity, however, benefit little from those pre-training mechanisms. Knowledge distillation defines a paradigm to transfer representations from large (teacher) models to small (student) ones. However, the conventional single-stage distillation easily gets stuck on task-specific transfer, failing to retain the task-agnostic knowledge crucial for model generalization. In this study, we propose generic-to-specific distillation (G2SD), to tap the potential of small ViT models under the supervision of large models pre-trained by masked autoencoders. In generic distillation, decoder of the small model is encouraged to align feature predictions with hidden representations of the large model, so that task-agnostic knowledge can be transferred. In specific distillation, predictions of the small model are constrained to be consistent with those of the large model, to transfer task-specific features which guarantee task performance. With G2SD, the vanilla ViT-Small model respectively achieves 98.7%, 98.1% and 99.3% the performance of its teacher (ViT-Base) for image classification, object detection, and semantic segmentation, setting a solid baseline for two-stage vision distillation. Code will be available at https://github.com/pengzhiliang/G2SD.
PDF Accepted by CVPR2023
点此查看论文截图
AMIGO: Sparse Multi-Modal Graph Transformer with Shared-Context Processing for Representation Learning of Giga-pixel Images
Authors:Ramin Nakhli, Puria Azadi Moghadam, Haoyang Mi, Hossein Farahani, Alexander Baras, Blake Gilks, Ali Bashashati
Processing giga-pixel whole slide histopathology images (WSI) is a computationally expensive task. Multiple instance learning (MIL) has become the conventional approach to process WSIs, in which these images are split into smaller patches for further processing. However, MIL-based techniques ignore explicit information about the individual cells within a patch. In this paper, by defining the novel concept of shared-context processing, we designed a multi-modal Graph Transformer (AMIGO) that uses the celluar graph within the tissue to provide a single representation for a patient while taking advantage of the hierarchical structure of the tissue, enabling a dynamic focus between cell-level and tissue-level information. We benchmarked the performance of our model against multiple state-of-the-art methods in survival prediction and showed that ours can significantly outperform all of them including hierarchical Vision Transformer (ViT). More importantly, we show that our model is strongly robust to missing information to an extent that it can achieve the same performance with as low as 20% of the data. Finally, in two different cancer datasets, we demonstrated that our model was able to stratify the patients into low-risk and high-risk groups while other state-of-the-art methods failed to achieve this goal. We also publish a large dataset of immunohistochemistry images (InUIT) containing 1,600 tissue microarray (TMA) cores from 188 patients along with their survival information, making it one of the largest publicly available datasets in this context.
PDF Accepted at CVPR 2023
点此查看论文截图
Token Contrast for Weakly-Supervised Semantic Segmentation
Authors:Lixiang Ru, Heliang Zheng, Yibing Zhan, Bo Du
Weakly-Supervised Semantic Segmentation (WSSS) using image-level labels typically utilizes Class Activation Map (CAM) to generate the pseudo labels. Limited by the local structure perception of CNN, CAM usually cannot identify the integral object regions. Though the recent Vision Transformer (ViT) can remedy this flaw, we observe it also brings the over-smoothing issue, \ie, the final patch tokens incline to be uniform. In this work, we propose Token Contrast (ToCo) to address this issue and further explore the virtue of ViT for WSSS. Firstly, motivated by the observation that intermediate layers in ViT can still retain semantic diversity, we designed a Patch Token Contrast module (PTC). PTC supervises the final patch tokens with the pseudo token relations derived from intermediate layers, allowing them to align the semantic regions and thus yield more accurate CAM. Secondly, to further differentiate the low-confidence regions in CAM, we devised a Class Token Contrast module (CTC) inspired by the fact that class tokens in ViT can capture high-level semantics. CTC facilitates the representation consistency between uncertain local regions and global objects by contrasting their class tokens. Experiments on the PASCAL VOC and MS COCO datasets show the proposed ToCo can remarkably surpass other single-stage competitors and achieve comparable performance with state-of-the-art multi-stage methods. Code is available at https://github.com/rulixiang/ToCo.
PDF Accepted to CVPR 2023
点此查看论文截图
Image as Set of Points
Authors:Xu Ma, Yuqian Zhou, Huan Wang, Can Qin, Bin Sun, Chang Liu, Yun Fu
What is an image and how to extract latent features? Convolutional Networks (ConvNets) consider an image as organized pixels in a rectangular shape and extract features via convolutional operation in local region; Vision Transformers (ViTs) treat an image as a sequence of patches and extract features via attention mechanism in a global range. In this work, we introduce a straightforward and promising paradigm for visual representation, which is called Context Clusters. Context clusters (CoCs) view an image as a set of unorganized points and extract features via simplified clustering algorithm. In detail, each point includes the raw feature (e.g., color) and positional information (e.g., coordinates), and a simplified clustering algorithm is employed to group and extract deep features hierarchically. Our CoCs are convolution- and attention-free, and only rely on clustering algorithm for spatial interaction. Owing to the simple design, we show CoCs endow gratifying interpretability via the visualization of clustering process. Our CoCs aim at providing a new perspective on image and visual representation, which may enjoy broad applications in different domains and exhibit profound insights. Even though we are not targeting SOTA performance, COCs still achieve comparable or even better results than ConvNets or ViTs on several benchmarks. Codes are available at: https://github.com/ma-xu/Context-Cluster.
PDF ICLR’23 Oral (top 5%); Codes: https://github.com/ma-xu/Context-Cluster
点此查看论文截图