2023-03-29 更新
Sector Patch Embedding: An Embedding Module Conforming to The Distortion Pattern of Fisheye Image
Authors:Dianyi Yang, Jiadong Tang, Yu Gao, Yi Yang, Mengyin Fu
Fisheye cameras suffer from image distortion while having a large field of view(LFOV). And this fact leads to poor performance on some fisheye vision tasks. One of the solutions is to optimize the current vision algorithm for fisheye images. However, most of the CNN-based methods and the Transformer-based methods lack the capability of leveraging distortion information efficiently. In this work, we propose a novel patch embedding method called Sector Patch Embedding(SPE), conforming to the distortion pattern of the fisheye image. Furthermore, we put forward a synthetic fisheye dataset based on the ImageNet-1K and explore the performance of several Transformer models on the dataset. The classification top-1 accuracy of ViT and PVT is improved by 0.75% and 2.8% with SPE respectively. The experiments show that the proposed sector patch embedding method can better perceive distortion and extract features on the fisheye images. Our method can be easily adopted to other Transformer-based models. Source code is at https://github.com/IN2-ViAUn/Sector-Patch-Embedding.
PDF
点此查看论文截图
Universal Few-shot Learning of Dense Prediction Tasks with Visual Token Matching
Authors:Donggyun Kim, Jinwoo Kim, Seongwoong Cho, Chong Luo, Seunghoon Hong
Dense prediction tasks are a fundamental class of problems in computer vision. As supervised methods suffer from high pixel-wise labeling cost, a few-shot learning solution that can learn any dense task from a few labeled images is desired. Yet, current few-shot learning methods target a restricted set of tasks such as semantic segmentation, presumably due to challenges in designing a general and unified model that is able to flexibly and efficiently adapt to arbitrary tasks of unseen semantics. We propose Visual Token Matching (VTM), a universal few-shot learner for arbitrary dense prediction tasks. It employs non-parametric matching on patch-level embedded tokens of images and labels that encapsulates all tasks. Also, VTM flexibly adapts to any task with a tiny amount of task-specific parameters that modulate the matching algorithm. We implement VTM as a powerful hierarchical encoder-decoder architecture involving ViT backbones where token matching is performed at multiple feature hierarchies. We experiment VTM on a challenging variant of Taskonomy dataset and observe that it robustly few-shot learns various unseen dense prediction tasks. Surprisingly, it is competitive with fully supervised baselines using only 10 labeled examples of novel tasks (0.004% of full supervision) and sometimes outperforms using 0.1% of full supervision. Codes are available at https://github.com/GitGyun/visual_token_matching.
PDF
点此查看论文截图
What Can Human Sketches Do for Object Detection?
Authors:Pinaki Nath Chowdhury, Ayan Kumar Bhunia, Aneeshan Sain, Subhadeep Koley, Tao Xiang, Yi-Zhe Song
Sketches are highly expressive, inherently capturing subjective and fine-grained visual cues. The exploration of such innate properties of human sketches has, however, been limited to that of image retrieval. In this paper, for the first time, we cultivate the expressiveness of sketches but for the fundamental vision task of object detection. The end result is a sketch-enabled object detection framework that detects based on what \textit{you} sketch — \textit{that} zebra'' (e.g., one that is eating the grass) in a herd of zebras (instance-aware detection), and only the \textit{part} (e.g.,head” of a ``zebra”) that you desire (part-aware detection). We further dictate that our model works without (i) knowing which category to expect at testing (zero-shot) and (ii) not requiring additional bounding boxes (as per fully supervised) and class labels (as per weakly supervised). Instead of devising a model from the ground up, we show an intuitive synergy between foundation models (e.g., CLIP) and existing sketch models build for sketch-based image retrieval (SBIR), which can already elegantly solve the task — CLIP to provide model generalisation, and SBIR to bridge the (sketch$\rightarrow$photo) gap. In particular, we first perform independent prompting on both sketch and photo branches of an SBIR model to build highly generalisable sketch and photo encoders on the back of the generalisation ability of CLIP. We then devise a training paradigm to adapt the learned encoders for object detection, such that the region embeddings of detected boxes are aligned with the sketch and photo embeddings from SBIR. Evaluating our framework on standard object detection datasets like PASCAL-VOC and MS-COCO outperforms both supervised (SOD) and weakly-supervised object detectors (WSOD) on zero-shot setups. Project Page: \url{https://pinakinathc.github.io/sketch-detect}
PDF Accepted as Top 12 Best Papers. Will be presented in special single-track plenary sessions to all attendees in Computer Vision and Pattern Recognition (CVPR), 2023. Project Page: www.pinakinathc.me/sketch-detect
点此查看论文截图
Supervised Masked Knowledge Distillation for Few-Shot Transformers
Authors:Han Lin, Guangxing Han, Jiawei Ma, Shiyuan Huang, Xudong Lin, Shih-Fu Chang
Vision Transformers (ViTs) emerge to achieve impressive performance on many data-abundant computer vision tasks by capturing long-range dependencies among local features. However, under few-shot learning (FSL) settings on small datasets with only a few labeled data, ViT tends to overfit and suffers from severe performance degradation due to its absence of CNN-alike inductive bias. Previous works in FSL avoid such problem either through the help of self-supervised auxiliary losses, or through the dextile uses of label information under supervised settings. But the gap between self-supervised and supervised few-shot Transformers is still unfilled. Inspired by recent advances in self-supervised knowledge distillation and masked image modeling (MIM), we propose a novel Supervised Masked Knowledge Distillation model (SMKD) for few-shot Transformers which incorporates label information into self-distillation frameworks. Compared with previous self-supervised methods, we allow intra-class knowledge distillation on both class and patch tokens, and introduce the challenging task of masked patch tokens reconstruction across intra-class images. Experimental results on four few-shot classification benchmark datasets show that our method with simple design outperforms previous methods by a large margin and achieves a new start-of-the-art. Detailed ablation studies confirm the effectiveness of each component of our model. Code for this paper is available here: https://github.com/HL-hanlin/SMKD.
PDF
点此查看论文截图
MoViT: Memorizing Vision Transformers for Medical Image Analysis
Authors:Yiqing Shen, Pengfei Guo, Jinpu Wu, Qianqi Huang, Jinyuan Zhou, Shanshan Jiang, Mathias Unberath
The synergy of long-range dependencies from transformers and local representations of image content from convolutional neural networks (CNNs) has led to advanced architectures and increased performance for various medical image analysis tasks due to their complementary benefits. However, compared with CNNs, transformers require considerably more training data, due to a larger number of parameters and an absence of inductive bias. The need for increasingly large datasets continues to be problematic, particularly in the context of medical imaging, where both annotation efforts and data protection result in limited data availability. In this work, inspired by the human decision-making process of correlating new evidence'' with previously memorizedexperience’’, we propose a Memorizing Vision Transformer (MoViT) to alleviate the need for large-scale datasets to successfully train and deploy transformer-based architectures. MoViT leverages an external memory structure to cache history attention snapshots during the training stage. To prevent overfitting, we incorporate an innovative memory update scheme, attention temporal moving average, to update the stored external memories with the historical moving average. For inference speedup, we design a prototypical attention learning method to distill the external memory into smaller representative subsets. We evaluate our method on a public histology image dataset and an in-house MRI dataset, demonstrating that MoViT applied to varied medical image analysis tasks, can outperform vanilla transformer models across varied data regimes, especially in cases where only a small amount of annotated data is available. More importantly, MoViT can reach a competitive performance of ViT with only 3.0% of the training data.
PDF
点此查看论文截图
Core-Periphery Principle Guided Redesign of Self-Attention in Transformers
Authors:Xiaowei Yu, Lu Zhang, Haixing Dai, Yanjun Lyu, Lin Zhao, Zihao Wu, David Liu, Tianming Liu, Dajiang Zhu
Designing more efficient, reliable, and explainable neural network architectures is critical to studies that are based on artificial intelligence (AI) techniques. Previous studies, by post-hoc analysis, have found that the best-performing ANNs surprisingly resemble biological neural networks (BNN), which indicates that ANNs and BNNs may share some common principles to achieve optimal performance in either machine learning or cognitive/behavior tasks. Inspired by this phenomenon, we proactively instill organizational principles of BNNs to guide the redesign of ANNs. We leverage the Core-Periphery (CP) organization, which is widely found in human brain networks, to guide the information communication mechanism in the self-attention of vision transformer (ViT) and name this novel framework as CP-ViT. In CP-ViT, the attention operation between nodes is defined by a sparse graph with a Core-Periphery structure (CP graph), where the core nodes are redesigned and reorganized to play an integrative role and serve as a center for other periphery nodes to exchange information. We evaluated the proposed CP-ViT on multiple public datasets, including medical image datasets (INbreast) and natural image datasets. Interestingly, by incorporating the BNN-derived principle (CP structure) into the redesign of ViT, our CP-ViT outperforms other state-of-the-art ANNs. In general, our work advances the state of the art in three aspects: 1) This work provides novel insights for brain-inspired AI: we can utilize the principles found in BNNs to guide and improve our ANN architecture design; 2) We show that there exist sweet spots of CP graphs that lead to CP-ViTs with significantly improved performance; and 3) The core nodes in CP-ViT correspond to task-related meaningful and important image patches, which can significantly enhance the interpretability of the trained deep model.
PDF Core-periphery, functional brain networks, ViT
点此查看论文截图
Learning Expressive Prompting With Residuals for Vision Transformers
Authors:Rajshekhar Das, Yonatan Dukler, Avinash Ravichandran, Ashwin Swaminathan
Prompt learning is an efficient approach to adapt transformers by inserting learnable set of parameters into the input and intermediate representations of a pre-trained model. In this work, we present Expressive Prompts with Residuals (EXPRES) which modifies the prompt learning paradigm specifically for effective adaptation of vision transformers (ViT). Out method constructs downstream representations via learnable ``output’’ tokens, that are akin to the learned class tokens of the ViT. Further for better steering of the downstream representation processed by the frozen transformer, we introduce residual learnable tokens that are added to the output of various computations. We apply EXPRES for image classification, few shot learning, and semantic segmentation, and show our method is capable of achieving state of the art prompt tuning on 3/3 categories of the VTAB benchmark. In addition to strong performance, we observe that our approach is an order of magnitude more prompt efficient than existing visual prompting baselines. We analytically show the computational benefits of our approach over weight space adaptation techniques like finetuning. Lastly we systematically corroborate the architectural design of our method via a series of ablation experiments.
PDF Accepted at CVPR (2023)
点此查看论文截图
TFS-ViT: Token-Level Feature Stylization for Domain Generalization
Authors:Mehrdad Noori, Milad Cheraghalikhani, Ali Bahri, Gustavo A. Vargas Hakim, David Osowiechi, Ismail Ben Ayed, Christian Desrosiers
Standard deep learning models such as convolutional neural networks (CNNs) lack the ability of generalizing to domains which have not been seen during training. This problem is mainly due to the common but often wrong assumption of such models that the source and target data come from the same i.i.d. distribution. Recently, Vision Transformers (ViTs) have shown outstanding performance for a broad range of computer vision tasks. However, very few studies have investigated their ability to generalize to new domains. This paper presents a first Token-level Feature Stylization (TFS-ViT) approach for domain generalization, which improves the performance of ViTs to unseen data by synthesizing new domains. Our approach transforms token features by mixing the normalization statistics of images from different domains. We further improve this approach with a novel strategy for attention-aware stylization, which uses the attention maps of class (CLS) tokens to compute and mix normalization statistics of tokens corresponding to different image regions. The proposed method is flexible to the choice of backbone model and can be easily applied to any ViT-based architecture with a negligible increase in computational complexity. Comprehensive experiments show that our approach is able to achieve state-of-the-art performance on five challenging benchmarks for domain generalization, and demonstrate its ability to deal with different types of domain shifts. The implementation is available at: {https://github.com/Mehrdad-Noori/TFS-ViT_Token-level_Feature_Stylization}.
PDF
点此查看论文截图
Unmasked Teacher: Towards Training-Efficient Video Foundation Models
Authors:Kunchang Li, Yali Wang, Yizhuo Li, Yi Wang, Yinan He, Limin Wang, Yu Qiao
Video Foundation Models (VFMs) have received limited exploration due to high computational costs and data scarcity. Previous VFMs rely on Image Foundation Models (IFMs), which face challenges in transferring to the video domain. Although VideoMAE has trained a robust ViT from limited data, its low-level reconstruction poses convergence difficulties and conflicts with high-level cross-modal alignment. This paper proposes a training-efficient method for temporal-sensitive VFMs that integrates the benefits of existing methods. To increase data efficiency, we mask out most of the low-semantics video tokens, but selectively align the unmasked tokens with IFM, which serves as the UnMasked Teacher (UMT). By providing semantic guidance, our method enables faster convergence and multimodal friendliness. With a progressive pre-training framework, our model can handle various tasks including scene-related, temporal-related, and complex video-language understanding. Using only public sources for pre-training in 6 days on 32 A100 GPUs, our scratch-built ViT-L/16 achieves state-of-the-art performances on various video tasks. The code and models will be released at https://github.com/OpenGVLab/unmasked_teacher.
PDF 16 pages, 5 figures, 28 tables
点此查看论文截图
ASIC: Aligning Sparse in-the-wild Image Collections
Authors:Kamal Gupta, Varun Jampani, Carlos Esteves, Abhinav Shrivastava, Ameesh Makadia, Noah Snavely, Abhishek Kar
We present a method for joint alignment of sparse in-the-wild image collections of an object category. Most prior works assume either ground-truth keypoint annotations or a large dataset of images of a single object category. However, neither of the above assumptions hold true for the long-tail of the objects present in the world. We present a self-supervised technique that directly optimizes on a sparse collection of images of a particular object/object category to obtain consistent dense correspondences across the collection. We use pairwise nearest neighbors obtained from deep features of a pre-trained vision transformer (ViT) model as noisy and sparse keypoint matches and make them dense and accurate matches by optimizing a neural network that jointly maps the image collection into a learned canonical grid. Experiments on CUB and SPair-71k benchmarks demonstrate that our method can produce globally consistent and higher quality correspondences across the image collection when compared to existing self-supervised methods. Code and other material will be made available at \url{https://kampta.github.io/asic}.
PDF Web: https://kampta.github.io/asic
点此查看论文截图