Adaptive Token Sampling For Efficient Vision Transformers
Technische Universität Berlin（柏林工业大学）；Berlin Institute for the Foundations of Learning and Data（柏林学习与数据基础研究所）；University of Bonn（波恩大学）；Microsoft（微软）；University of California, Davis（加州大学戴维斯分校）；Meta Reality Labs（Meta现实实验室）
Mohsen Fayyaz, Soroush Abbasi Koohpayegani, Farnoush Rezaei Jafari, Sunando Sengupta, Hamid Reza Vaezi Joze, Eric Sommerlade, Hamed Pirsiavash, Juergen Gall
While state-of-the-art vision transformer models achieve promising results in image classification, they are computationally expensive and require many GFLOPs. Although the GFLOPs of a vision transformer can be decreased by reducing the number of tokens in the network, there is no setting that is optimal for all input images. In this work, we therefore introduce a differentiable parameter-free Adaptive Token Sampler (ATS) module, which can be plugged into any existing vision transformer architecture. ATS empowers vision transformers by scoring and adaptively sampling significant tokens. As a result, the number of tokens is not constant anymore and varies for each input image. By integrating ATS as an additional layer within the current transformer blocks, we can convert them into much more efficient vision transformers with an adaptive number of tokens. Since ATS is a parameter-free module, it can be added to the off-the-shelf pre-trained vision transformers as a plug and play module, thus reducing their GFLOPs without any additional training. Moreover, due to its differentiable design, one can also train a vision transformer equipped with ATS. We evaluate the efficiency of our module in both image and video classification tasks by adding it to multiple SOTA vision transformers. Our proposed module improves the SOTA by reducing their computational costs (GFLOPs) by 2X, while preserving their accuracy on the ImageNet, Kinetics-400, and Kinetics-600 datasets.
Compared with the vanilla transformer, the window-based transformer offers a better trade-off between accuracy and efficiency. Although the window-based transformer has made great progress, its long-range modeling capabilities are limited due to the size of the local window and the window connection scheme. To address this problem, we propose a novel Token Transformer (TT). The core mechanism of TT is the addition of a Class (CLS) token for summarizing window information in each local window. We refer to this type of token interaction as CLS Attention. These CLS tokens will interact spatially …
The Chinese University of Hong Kong（香港中文大学）；Amazon AI（亚马逊人工智能部门）
The architecture of transformers, which recently witness booming applications in vision tasks, has pivoted against the widespread convolutional paradigm. Relying on the tokenization process that splits inputs into multiple tokens, transformers are capable of extracting their pairwise relationships using self-attention. While being the stemming building block of transformers, what makes for a good tokenizer has not been well understood in computer vision. In this work, we investigate this uncharted problem from an information trade-off perspective. In addition to unifying and understanding exis…
Mixup is a commonly adopted data augmentation technique for image classification. Recent advances in mixup methods primarily focus on mixing based on saliency. However, many saliency detectors require intense computation and are especially burdensome for parameter-heavy transformer models. To this end, we propose TokenMixup, an efficient attention-guided token-level data augmentation method that aims to maximize the saliency of a mixed set of tokens. TokenMixup provides x15 faster saliency-aware data augmentation compared to gradient-based methods. Moreover, we introduce a variant of TokenMixu…
The University of Western Australia（西澳大学）；The University of Sydney（悉尼大学）；Hong Kong University of Science and Technology（香港科技大学）
This paper proposes a new transformer-based framework to learn class-specific object localization maps as pseudo labels for weakly supervised semantic segmentation (WSSS). Inspired by the fact that the attended regions of the one-class token in the standard vision transformer can be leveraged to form a class-agnostic localization map, we investigate if the transformer model can also effectively capture class-specific attention for more discriminative object localization by learning multiple class tokens within the transformer. To this end, we propose a Multi-class Token Transformer, termed as …
While vision transformers have achieved impressive results, effectively and efficiently accelerating these models can further boost performances. In this work, we propose a dense/sparse training framework to obtain a unified model, enabling weight sharing across various token densities. Thus one model offers a range of accuracy and throughput tradeoffs for different applications. Besides, we introduce adaptive token pruning to optimize the patch token sparsity based on the input image. In addition, we investigate knowledge distillation to enhance token selection capability in early transformer…
Jilin University（吉林大学）；Baidu VIS（百度视觉技术部）；University of Sydney（悉尼大学）
Vision transformers have achieved significant improvements on various vision tasks but their quadratic interactions between tokens significantly reduce computational efficiency. Many pruning methods have been proposed to remove redundant tokens for efficient vision transformers recently. However, existing studies mainly focus on the token importance to preserve local attentive tokens but completely ignore the global token diversity. In this paper, we emphasize the cruciality of diverse global semantics and propose an efficient token decoupling and merging method that can jointly consider the t…
Tsinghua University（清华大学）；Beijing National Research Center for Information Science and Technology（北京信息科学与技术国家研究中心）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）；Institute for AI Industry Research (AIR), Tsinghua University（清华大学智能产业研究院（AIR））
Many adaptations of transformers have emerged to address the single-modal vision tasks, where self-attention modules are stacked to handle input sources like images. Intuitively, feeding multiple modalities of data to vision transformers could improve the performance, yet the inner-modal attentive weights may also be diluted, which could thus undermine the final performance. In this paper, we propose a multimodal token fusion method (TokenFusion), tailored for transformer-based vision tasks. To effectively fuse multiple modalities, TokenFusion dynamically detects uninformative tokens and subst…
The Chinese University of Hong Kong（香港中文大学）；The University of Hong Kong（香港大学）；SenseTime Research（商汤科技研究院）；The University of Sydney（悉尼大学）
Vision transformers have achieved great successes in many computer vision tasks. Most methods generate vision tokens by splitting an image into a regular and fixed grid and treating each cell as a token. However, not all regions are equally important in human-centric vision tasks, e.g., the human body needs a fine representation with many tokens, while the image background can be modeled by a few tokens. To address this problem, we propose a novel Vision Transformer, called Token Clustering Transformer (TCFormer), which merges tokens by progressive clustering, where the tokens can be merged fr…
University of Electronic Science and Technology of China（电子科技大学）
Detection transformers like DETR have recently shown promising performance on many object detection tasks, but the generalization ability of those methods is still quite challenging for cross-domain adaptation scenarios. To address the cross-domain issue, a straightforward way is to perform token alignment with adversarial training in transformers. However, its performance is often unsatisfactory as the tokens in detection transformers are quite diverse and represent different spatial and semantic information. In this paper, we propose a new method called Spatial-aware and Semantic-aware Token…
Yitu Tech（依图科技）；National University of Singapore（新加坡国立大学）；YITU Technology Institute of Data Science（依图科技数据科学研究所）
Transformers, which are popular for language modeling, have been explored for solving vision tasks recently, e.g., the Vision Transformer (ViT) for image classification. The ViT model splits each image into a sequence of tokens with fixed length and then applies multiple Transformer layers to model their global relation for classification. However, ViT achieves inferior performance to CNNs when trained from scratch on a midsize dataset like ImageNet. We find it is because: 1) the simple tokenization of input images fails to model the important local structure such as edges and lines among neig…
With the popularity of Transformer architectures in computer vision, the research focus has shifted towards developing computationally efficient designs. Window-based local attention is one of the major techniques being adopted in recent works. These methods begin with very small patch size and small embedding dimensions and then perform strided convolution (patch merging) in order to reduce the feature map size and increase embedding dimensions, hence, forming a pyramidal Convolutional Neural Network (CNN) like design. In this work, we investigate local and global information modelling in tra…
Seoul National University（首尔国立大学）；NAVER WEBTOON AI（NAVER WEBTOON人工智能部门）
In this paper, we propose a transformer-based image matting model called MatteFormer, which takes full advantage of trimap information in the transformer block. Our method first introduces a prior-token which is a global representation of each trimap region (e.g. foreground, background and unknown). These prior-tokens are used as global priors and participate in the self-attention mechanism of each block. Each stage of the encoder is composed of PAST (Prior-Attentive Swin Transformer) block, which is based on the Swin Transformer block, but differs in a couple of aspects: 1) It has PA-WSA (Pri…
National University of Singapore（新加坡国立大学）；ByteDance（字节跳动）
In this paper, we present token labeling -- a new training objective for training high-performance vision transformers (ViTs). Different from the standard training objective of ViTs that computes the classification loss on an additional trainable class token, our proposed one takes advantage of all the image patch tokens to compute the training loss in a dense manner. Specifically, token labeling reformulates the image classification problem into multiple token-level recognition problems and assigns each patch token with an individual location-specific supervision generated by a machine annota…
We introduce token-consistent stochastic layers in vision transformers, without causing any severe drop in performance. The added stochasticity improves network calibration, robustness and strengthens privacy. We use linear layers with token-consistent stochastic parameters inside the multilayer perceptron blocks, without altering the architecture of the transformer. The stochastic parameters are sampled from the uniform distribution, both during training and inference. The applied linear operations preserve the topological structure, formed by the set of tokens passing through the shared mult…
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Shanghai Jiao Tong University（上海交通大学）；Tencent Youtu Lab（腾讯优图实验室）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）
Vision transformers (ViTs) have recently received explosive popularity, but the huge computational cost is still a severe issue. Since the computation complexity of ViT is quadratic with respect to the input sequence length, a mainstream paradigm for computation reduction is to reduce the number of tokens. Existing designs include structured spatial compression that uses a progressive shrinking pyramid to reduce the computations of large feature maps, and unstructured token pruning that dynamically drops redundant tokens. However, the limitation of existing token pruning lies in two folds: 1) …
Fudan University（复旦大学）；University of Maryland（马里兰大学）；BirenTech Research（壁仞科技研究院）
Video transformers have achieved impressive results on major video recognition benchmarks, which however suffer from high computational cost. In this paper, we present STTS, a token selection framework that dynamically selects a few informative tokens in both temporal and spatial dimensions conditioned on input video samples. Specifically, we formulate token selection as a ranking problem, which estimates the importance of each token through a lightweight scorer network and only those with top scores will be used for downstream evaluation. In the temporal dimension, we keep the frames that are…
MCTformer+: Multi-Class Token Transformer for Weakly Supervised Semantic Segmentation
The University of Western Australia（西澳大学）；Murdoch University（莫道克大学）；Shanghai AI Laboratory（上海人工智能实验室）；The Hong Kong University of Science and Technology（香港科技大学）
Text-Video retrieval is a task of great practical value and has received increasing attention, among which learning spatial-temporal video representation is one of the research hotspots. The video encoders in the state-of-the-art video retrieval models usually directly adopt the pre-trained vision backbones with the network structure fixed, they therefore can not be further improved to produce the fine-grained spatial-temporal video representation. In this paper, we propose Token Shift and Selection Network (TS2-Net), a novel token shift and selection transformer architecture, which dynamicall…
Midea Group, AI Innovation Center（美的集团人工智能创新中心）；Tongji University（同济大学）
The vision transformer splits each image into a sequence of tokens with fixed length and processes the tokens in the same way as words in natural language processing. More tokens normally lead to better performance but considerably increased computational cost. Motivated by the proverb "A picture is worth a thousand words" we aim to accelerate the ViT model by making a long image short. To this end, we propose a novel approach to assign token length adaptively during inference. Specifically, we first train a ViT model, called Resizable-ViT (ReViT), that can process any given input with diverse…
The University of Sydney（悉尼大学）；BAIDU USA LLC（百度美国有限责任公司）；SenseTime Group Limited（商汤集团有限公司）；University of Oxford（牛津大学）
In this paper, we observe two levels of redundancies when applying vision transformers (ViT) for image recognition. First, fixing the number of tokens through the whole network produces redundant features at the spatial level. Second, the attention maps among different transformer layers are redundant. Based on the observations above, we propose a PSViT: a ViT with token Pooling and attention Sharing to reduce the redundancy, effectively enhancing the feature representation ability, and achieving a better speed-accuracy trade-off. Specifically, in our PSViT, token pooling can be defined as the…
TORE: Token Reduction for Efficient Human Mesh Recovery with Transformer
City University of Hong Kong（香港城市大学）；The University of Hong Kong（香港大学）；Texas A&M University（德克萨斯农工大学）；University of Oxford（牛津大学）；Tencent Games（腾讯游戏）；University of Cambridge（剑桥大学）
University of Chinese Academy of Sciences（中国科学院大学）；Technology and Engineering Center for Space Utilization, Chinese Academy of Sciences（中国科学院空间应用工程与技术中心）
Image matting aims to predict alpha values of elaborate uncertainty areas of natural images, like hairs, smoke, and spider web. However, existing methods perform poorly when faced with highly transparent foreground objects due to the large area of uncertainty to predict and the small receptive field of convolutional networks. To address this issue, we propose a Transformer-based network (TransMatting) to model transparent objects with long-range features and collect a high-resolution matting dataset of transparent objects (Transparent-460) for performance evaluation. Specifically, to utilize s…
Mobile monocular 3D object detection (Mono3D) (e.g., on a vehicle, a drone, or a robot) is an important yet challenging task. Existing transformer-based offline Mono3D models adopt grid-based vision tokens, which is suboptimal when using coarse tokens due to the limited available computational power. In this paper, we propose an online Mono3D framework, called MonoATT, which leverages a novel vision transformer with heterogeneous tokens of varying shapes and sizes to facilitate mobile Mono3D. The core idea of MonoATT is to adaptively assign finer tokens to areas of more significance before uti…
TCFormer: Visual Recognition via Token Clustering Transformer
The Chinese University of Hong Kong（香港中文大学）；The University of Hong Kong（香港大学）；SenseTime Research（商汤科技研究院）；The University of Sydney（悉尼大学）；Shanghai AI Laboratory（上海人工智能实验室）；Centre for Perceptual and Interactive Intelligence Limited（感知与交互智能中心有限公司）
Non-autoregressive generative transformers recently demonstrated impressive image generation performance, and orders of magnitude faster sampling than their autoregressive counterparts. However, optimal parallel sampling from the true joint distribution of visual tokens remains an open challenge. In this paper we introduce Token-Critic, an auxiliary model to guide the sampling of a non-autoregressive generative transformer. Given a masked-and-reconstructed real image, the Token-Critic model is trained to distinguish which visual tokens belong to the original image and which were sampled by the…
University of California, Irvine（加州大学欧文分校）；Tencent Inc（腾讯公司）；Meta AI
Recently, the vision transformer and its variants have played an increasingly important role in both monocular and multi-view human pose estimation. Considering image patches as tokens, transformers can model the global dependencies within the entire image or across images from other views. However, global attention is computationally expensive. As a consequence, it is difficult to scale up these transformer-based methods to high-resolution features and many views. In this paper, we propose the token-Pruned Pose Transformer (PPT) for 2D human pose estimation, which can locate a rough human mas…
School of Computer Science and Engineering, Sun Yat-sen University（中山大学计算机科学与工程学院）；Key Laboratory of Machine Intelligence and Advanced Computing, Ministry of Education, China（中国教育部机器智能与先进计算重点实验室）；Microsoft Research Asia（微软亚洲研究院）；University of Tokyo（东京大学）
We present a new perspective of achieving image synthesis by viewing this task as a visual token generation problem. Different from existing paradigms that directly synthesize a full image from a single input (e.g., a latent code), the new formulation enables a flexible local manipulation for different image regions, which makes it possible to learn content-aware and fine-grained style control for image synthesis. Specifically, it takes as input a sequence of latent tokens to predict the visual tokens for synthesizing an image. Under this perspective, we propose a token-based generator (i.e.,T…
Capturing interaction of hands with objects is important to autonomously detect human actions from egocentric videos. In this work, we present a pyramid video transformer with a dynamic class token generator for egocentric action recognition. Different from previous video transformers, which use the same static embedding as the class token for diverse inputs, we propose a dynamic class token generator that produces a class token for each input video by analyzing the hand-object interaction and the related motion information. The dynamic class token can diffuse such information to the entire mo…
Transcending the Limit of Local Window: Advanced Super-Resolution Transformer with Adaptive Token Dictionary
University of Electronic Science and Technology of China（电子科技大学）；Computer Vision Lab, ETH Zürich（苏黎世联邦理工学院计算机视觉实验室）；Integrated Systems Laboratory, ETH Zürich（苏黎世联邦理工学院集成系统实验室）
Convolutional Neural Networks (CNNs) have dominated computer vision for years, due to its ability in capturing locality and translation invariance. Recently, many vision transformer architectures have been proposed and they show promising performance. A key component in vision transformers is the fully-connected self-attention which is more powerful than CNNs in modelling long range dependencies. However, since the current dense self-attention uses all image patches (tokens) to compute attention matrix, it may neglect locality of images patches and involve noisy tokens (e.g., clutter backgroun…
