Vision transformer (ViT) has achieved competitive accuracy on a variety of computer vision applications, but its computational cost impedes the deployment on resource-limited mobile devices.
We explore the sparsity in ViT and observe that informative patches and heads are sufficient for accurate image recognition.
In this paper, we propose a cascade pruning framework named CP-ViT by predicting sparsity in ViT models progressively and dynamically to reduce computational redundancy while minimizing the accuracy loss. Specifically, we define the cumulative score to reserve the informative patches and heads across the ViT model for better accuracy. We also propose the dynamic pruning ratio adjustment technique based on layer-aware attention range. CP-ViT has great general applicability for practical deployment, which can be applied to a wide range of ViT models and can achieve superior accuracy with or without fine-tuning.
Extensive experiments on ImageNet, CIFAR-10, and CIFAR-100 with various pre-trained models have demonstrated the effectiveness and efficiency of CP-ViT. By progressively pruning 50\% patches, our CP-ViT method reduces over 40\% FLOPs while maintaining accuracy loss within 1\%.
The recently proposed Vision transformers (ViTs) have shown very impressive empirical performance in various computer vision tasks, and they are viewed as an important type of foundation model. However, ViTs are typically constructed with large-scale sizes, which then severely hinder their potential deployment in many practical resources-constrained applications. To mitigate this challenging problem, structured pruning is a promising solution to compress model size and enable practical efficiency. However, unlike its current popularity for CNNs and RNNs, structured pruning for ViT models is li…
The Chinese University of Hong Kong（香港中文大学）；SenseTime Research（商汤科技研究院）；École Polytechnique Fédérale de Lausanne (EPFL)（洛桑联邦理工学院）；Qing Yuan Research Institute, Shanghai Jiao Tong University（上海交通大学清源研究院）
Correspondence selection aims to correctly select the consistent matches (inliers) from an initial set of putative correspondences. The selection is challenging since putative matches are typically extremely unbalanced, largely dominated by outliers, and the random distribution of such outliers further complicates the learning process for learning-based methods. To address this issue, we propose to progressively prune the correspondences via a local-to-global consensus learning procedure. We introduce a ``pruning'' block that lets us identify reliable candidates among the initial matches accor…
TAP-ViTs: Task-Adaptive Pruning for On-Device Deployment of Vision Transformers
State Key Laboratory of Blockchain and Data Security（区块链与数据安全国家重点实验室）；College of Computer Science and Technology（计算机科学与技术学院）；College of Computer Science and Electronic Engineering（计算机科学与电子工程学院）
This paper describes a channel-selection approach for simplifying deep neural networks. Specifically, we propose a new type of generic network layer, called pruning layer, to seamlessly augment a given pre-trained model for compression. Each pruning layer, comprising $1 \times 1$ depth-wise kernels, is represented with a dual format: one is real-valued and the other is binary. The former enables a two-phase optimization process of network pruning to operate with an end-to-end differentiable network, and the latter yields the mask information for channel selection. Our method progressively perf…
While vision transformers (ViTs) have continuously achieved new milestones in the field of computer vision, their sophisticated network architectures with high computation and memory costs have impeded their deployment on resource-limited edge devices. In this paper, we propose a hardware-efficient image-adaptive token pruning framework called HeatViT for efficient yet accurate ViT acceleration on embedded FPGAs. By analyzing the inherent computational patterns in ViTs, we first design an effective attention-based multi-head token selector, which can be progressively inserted before transforme…
Block-based Symmetric Pruning and Fusion for Efficient Vision Transformers
College of Artificial Intelligence and Green Energy National Yang Ming Chiao Tung University（人工智能与绿色能源学院，阳明交通大学）；Computer Science Department University at Albany, SUNY（计算机科学系，阿尔巴尼大学）；Computer Science Information Engineering Department University at Albany, SUNY（计算机科学与信息工程系，阿尔巴尼大学）
Syracuse University（雪城大学）；Northeastern University（东北大学）；George Mason University（乔治梅森大学）；MIT-IBM Watson AI Lab, IBM Research（IBM研究院MIT-IBM沃森人工智能实验室）
Deep neural networks (DNNs) although achieving human-level performance in many domains, have very large model size that hinders their broader applications on edge computing devices. Extensive research work have been conducted on DNN model compression or pruning. However, most of the previous work took heuristic approaches. This work proposes a progressive weight pruning approach based on ADMM (Alternating Direction Method of Multipliers), a powerful technique to deal with non-convex optimization problems with potentially combinatorial constraints. Motivated by dynamic programming, the proposed…
Mila - Quebec AI Institute（米拉-魁北克人工智能研究所）；Landskape AI（Landskape人工智能）；UdeM（蒙特利尔大学）；IIT-Delhi（印度理工学院德里分校）；UT-Austin（德克萨斯大学奥斯汀分校）
With the latest advances in deep learning, there has been a lot of focus on the online learning paradigm due to its relevance in practical settings. Although many methods have been investigated for optimal learning settings in scenarios where the data stream is continuous over time, sparse networks training in such settings have often been overlooked. In this paper, we explore the problem of training a neural network with a target sparsity in a particular case of online learning: the anytime learning at macroscale paradigm (ALMA). We propose a novel way of progressive pruning, referred to as \…
Back to Fundamentals: Low-Level Visual Features Guided Progressive Token Pruning
Xidian University（西安电子科技大学）；University of Michigan – Shanghai Jiao Tong University Joint Institute（密歇根大学-上海交通大学联合学院）；Shanghai Jiao Tong University（上海交通大学）；Norwegian University of Science and Technology（挪威科技大学）；Xi’an Jiaotong-Liverpool University（西交利物浦大学）
Cut-ViT: Task-Specific Model Pruning via Gram Anchoring Subspace Consistency
Nanjing University of Science and Technology（南京理工大学）；State Key Laboratory of Intelligent Manufacturing of Advanced Construction Machinery（先进工程机械智能制造国家重点实验室）；Zhejiang University（浙江大学）；Nanjing Normal University（南京师范大学）
NVIDIA（英伟达）；University of California, Berkeley（加州大学伯克利分校）；Duke University（杜克大学）
Transformers yield state-of-the-art results across many tasks. However, their heuristically designed architecture impose huge computational costs during inference. This work aims on challenging the common design philosophy of the Vision Transformer (ViT) model with uniform dimension across all the stacked blocks in a model stage, where we redistribute the parameters both across transformer blocks and between different structures within the block via the first systematic attempt on global structural pruning. Dealing with diverse ViT structural components, we derive a novel Hessian-based structu…
Finding Sparse Subnetworks in One Training Cycle via Progressive Magnitude-Based Pruning
King Abdullah University of Science and Technology（阿卜杜拉国王科技大学）；University of Jeddah（吉达大学）；King Fahd University of Petroleum and Minerals（法赫德国王石油矿产大学）；King Saud University（沙特国王大学）
Sensetime Research（商汤科技研究院）；Tsinghua University（清华大学）；Syracuse University（雪城大学）；Northeastern University（东北大学）；Florida International University（佛罗里达国际大学）；MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）；IBM Research（IBM研究院）
Weight pruning and weight quantization are two important categories of DNN model compression. Prior work on these techniques are mainly based on heuristics. A recent work developed a systematic frame-work of DNN weight pruning using the advanced optimization technique ADMM (Alternating Direction Methods of Multipliers), achieving one of state-of-art in weight pruning results. In this work, we first extend such one-shot ADMM-based framework to guarantee solution feasibility and provide fast convergence rate, and generalize to weight quantization as well. We have further developed a multi-step, …
Northeastern University（东北大学）；Clemson University（克莱姆森大学）；Peking University（北京大学）；College of William and Mary（威廉与玛丽学院）；ETH Zürich（苏黎世联邦理工学院）
Recently, Vision Transformer (ViT) has continuously established new milestones in the computer vision field, while the high computation and memory cost makes its propagation in industrial production difficult. Pruning, a traditional model compression paradigm for hardware efficiency, has been widely applied in various DNN structures. Nevertheless, it stays ambiguous on how to perform exclusive pruning on the ViT structure. Considering three key points: the structural characteristics, the internal data pattern of ViTs, and the related edge device deployment, we leverage the input token sparsity…
Filter pruning is a common method to achieve model compression and acceleration in deep neural networks (DNNs).Some research regarded filter pruning as a combinatorial optimization problem and thus used evolutionary algorithms (EA) to prune filters of DNNs. However, it is difficult to find a satisfactory compromise solution in a reasonable time due to the complexity of solution space searching. To solve this problem, we first formulate a multi-objective optimization problem based on a sub-network of the full model and propose a Sub-network Multiobjective Evolutionary Algorithm (SMOEA) for filt…
California Institute of Technology（加州理工学院）；Ecole des Ponts ParisTech（巴黎高科路桥学院）
We propose a general and versatile framework that significantly speeds-up graphical model optimization while maintaining an excellent solution accuracy. The proposed approach relies on a multi-scale pruning scheme that is able to progressively reduce the solution space by use of a novel strategy based on a coarse-to-fine cascade of learnt classifiers. We thoroughly experiment with classic computer vision related MRF problems, where our framework constantly yields a significant time speed-up (with respect to the most efficient inference methods) and obtains a more accurate solution than directl…
DORA: Dynamic Online Reinforcement Agent for Token Pruning in Vision Transformers
University of Science and Technology of China（中国科学技术大学）；Institute of Artificial Intelligence, Hefei Comprehensive National Science Center（合肥综合性国家科学中心人工智能研究院）
Which Layer Causes Distribution Deviation? Entropy-Guided Adaptive Pruning for Diffusion and Flow Models
Stanford University（斯坦福大学）；North China Electric Power University（华北电力大学）；University of Technology Sydney（悉尼科技大学）；Harvard University（哈佛大学）；University of Science and Technology of China（中国科学技术大学）
University of Texas at Austin（德克萨斯大学奥斯汀分校）；Texas A&M University（德州农工大学）；Kwai Inc.（快手公司）
Vision transformers (ViTs) have gained popularity recently. Even without customized image operators such as convolutions, ViTs can yield competitive performance when properly trained on massive data. However, the computational overhead of ViTs remains prohibitive, due to stacking multi-head self-attention modules and else. Compared to the vast literature and prevailing success in compressing convolutional neural networks, the study of Vision Transformer compression has also just emerged, and existing works focused on one or two aspects of compression. This paper proposes a unified ViT compress…
National Key Laboratory for Novel Software Technology（新型软件技术国家重点实验室）；Nanjing University（南京大学）；Nanjing（南京）；China（中国）
Channel pruning is an important family of methods to speed up deep model's inference. Previous filter pruning algorithms regard channel pruning and model fine-tuning as two independent steps. This paper argues that combining them into a single end-to-end trainable system will lead to better results. We propose an efficient channel selection layer, namely AutoPruner, to find less important filters automatically in a joint training manner. Our AutoPruner takes previous activation responses as an input and generates a true binary index code for pruning. Hence, all the filters corresponding to zer…
Neural Architecture Search (NAS) has attracted growing interest. To reduce the search cost, recent work has explored weight sharing across models and made major progress in One-Shot NAS. However, it has been observed that a model with higher one-shot model accuracy does not necessarily perform better when stand-alone trained. To address this issue, in this paper, we propose Progressive Automatic Design of search space, named PAD-NAS. Unlike previous approaches where the same operation search space is shared by all the layers in the supernet, we formulate a progressive search strategy based on …
Reinforcement Learning-based Token Pruning in Vision Transformers: A Markov Game Approach
School of Computer Science, Fudan University（复旦大学计算机科学学院）；Data Intelligence Institute of Paris（巴黎数据智能研究院）；Université Paris Cité（巴黎西岱大学）；Shijiazhuang Tiedao University（石家庄铁道大学）
