Multi-criteria Token Fusion with One-step-ahead Attention for Efficient Vision Transformers

• URL: http://arxiv.org/abs/2403.10030v3
• Date: Mon, 1 Apr 2024 05:22:52 GMT
• Title: Multi-criteria Token Fusion with One-step-ahead Attention for Efficient Vision Transformers
• Authors: Sanghyeok Lee, Joonmyung Choi, Hyunwoo J. Kim,
• Abstract summary: Vision Transformer (ViT) has emerged as a prominent backbone for computer vision. Recent works lessen the quadratic cost of the self-attention layer by pruning or fusing the redundant tokens. Here, we argue that token fusion needs to consider diverse relations between tokens to minimize information loss.
• Score: 16.576495786546612
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Vision Transformer (ViT) has emerged as a prominent backbone for computer vision. For more efficient ViTs, recent works lessen the quadratic cost of the self-attention layer by pruning or fusing the redundant tokens. However, these works faced the speed-accuracy trade-off caused by the loss of information. Here, we argue that token fusion needs to consider diverse relations between tokens to minimize information loss. In this paper, we propose a Multi-criteria Token Fusion (MCTF), that gradually fuses the tokens based on multi-criteria (e.g., similarity, informativeness, and size of fused tokens). Further, we utilize the one-step-ahead attention, which is the improved approach to capture the informativeness of the tokens. By training the model equipped with MCTF using a token reduction consistency, we achieve the best speed-accuracy trade-off in the image classification (ImageNet1K). Experimental results prove that MCTF consistently surpasses the previous reduction methods with and without training. Specifically, DeiT-T and DeiT-S with MCTF reduce FLOPs by about 44% while improving the performance (+0.5%, and +0.3%) over the base model, respectively. We also demonstrate the applicability of MCTF in various Vision Transformers (e.g., T2T-ViT, LV-ViT), achieving at least 31% speedup without performance degradation. Code is available at https://github.com/mlvlab/MCTF.

Related papers

• LeMeViT: Efficient Vision Transformer with Learnable Meta Tokens for Remote Sensing Image Interpretation [37.72775203647514]
  This paper proposes to use learnable meta tokens to formulate sparse tokens, which effectively learn key information and improve inference speed. By employing Dual Cross-Attention (DCA) in the early stages with dense visual tokens, we obtain the hierarchical architecture LeMeViT with various sizes. Experimental results in classification and dense prediction tasks show that LeMeViT has a significant $1.7 times$ speedup, fewer parameters, and competitive performance compared to the baseline models.
  arXiv  Detail & Related papers  (2024-05-16T03:26:06Z)
• SkipViT: Speeding Up Vision Transformers with a Token-Level Skip Connection [3.960622297616708]
  We propose a method to optimize the amount of unnecessary interactions between unimportant tokens by separating and sending them through a different low-cost computational path. Our experimental results on training ViT-small from scratch show that SkipViT is capable of effectively dropping 55% of the tokens while gaining more than 13% training throughput.
  arXiv  Detail & Related papers  (2024-01-27T04:24:49Z)
• Hourglass Tokenizer for Efficient Transformer-Based 3D Human Pose Estimation [73.31524865643709]
  We present a plug-and-play pruning-and-recovering framework, called Hourglass Tokenizer (HoT), for efficient transformer-based 3D pose estimation from videos. Our HoDT begins with pruning pose tokens of redundant frames and ends with recovering full-length tokens, resulting in a few pose tokens in the intermediate transformer blocks. Our method can achieve both high efficiency and estimation accuracy compared to the original VPT models.
  arXiv  Detail & Related papers  (2023-11-20T18:59:51Z)
• No Token Left Behind: Efficient Vision Transformer via Dynamic Token Idling [55.203866875294516]
  Vision Transformers (ViTs) have demonstrated outstanding performance in computer vision tasks. Various token pruning techniques have been introduced to alleviate the high computational burden of ViTs. We propose IdleViT, a dynamic token-idle-based method that achieves an excellent trade-off between performance and efficiency.
  arXiv  Detail & Related papers  (2023-10-09T12:10:41Z)
• PPT: Token Pruning and Pooling for Efficient Vision Transformers [7.792045532428676]
  We propose a novel acceleration framework, namely token Pruning & Pooling Transformers (PPT) PPT integrates both token pruning and token pooling techniques in ViTs without additional trainable parameters. It reduces over 37% FLOPs and improves the throughput by over 45% for DeiT-S without any accuracy drop on the ImageNet dataset.
  arXiv  Detail & Related papers  (2023-10-03T05:55:11Z)
• Multi-Scale And Token Mergence: Make Your ViT More Efficient [3.087140219508349]
  Vision Transformer (ViT) has emerged as a prevalent model in the computer vision domain. We propose a novel token pruning method that retains information from non-crucial tokens by merging them with more crucial tokens. Our method achieves a remarkable 33% reduction in computational costs while only incurring a 0.1% decrease in accuracy on DeiT-S.
  arXiv  Detail & Related papers  (2023-06-08T02:58:15Z)
• CageViT: Convolutional Activation Guided Efficient Vision Transformer [90.69578999760206]
  This paper presents an efficient vision Transformer, called CageViT, that is guided by convolutional activation to reduce computation. Our CageViT, unlike current Transformers, utilizes a new encoder to handle the rearranged tokens. Experimental results demonstrate that the proposed CageViT outperforms the most recent state-of-the-art backbones by a large margin in terms of efficiency.
  arXiv  Detail & Related papers  (2023-05-17T03:19:18Z)
• Robustifying Token Attention for Vision Transformers [72.07710236246285]
  Vision transformers (ViTs) still suffer from significant drops in accuracy in the presence of common corruptions. We propose two techniques to make attention more stable through two general techniques. First, our Token-aware Average Pooling (TAP) module encourages the local neighborhood of each token to take part in the attention mechanism. Second, we force the output tokens to aggregate information from a diverse set of input tokens rather than focusing on just a few.
  arXiv  Detail & Related papers  (2023-03-20T14:04:40Z)
• Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations [37.11387992603467]
  Vision Transformers (ViTs) take all the image patches as tokens and construct multi-head self-attention (MHSA) among them. Examples include tokens containing semantically meaningless or distractive image backgrounds. We propose to reorganize image tokens during the feed-forward process of ViT models, which is integrated into ViT during training.
  arXiv  Detail & Related papers  (2022-02-16T00:19:42Z)
• Self-slimmed Vision Transformer [52.67243496139175]
  Vision transformers (ViTs) have become the popular structures and outperformed convolutional neural networks (CNNs) on various vision tasks. We propose a generic self-slimmed learning approach for vanilla ViTs, namely SiT. Specifically, we first design a novel Token Slimming Module (TSM), which can boost the inference efficiency of ViTs.
  arXiv  Detail & Related papers  (2021-11-24T16:48:57Z)
• DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification [134.9393799043401]
  We propose a dynamic token sparsification framework to prune redundant tokens based on the input. By hierarchically pruning 66% of the input tokens, our method greatly reduces 31%37% FLOPs and improves the throughput by over 40%. DynamicViT models can achieve very competitive complexity/accuracy trade-offs compared to state-of-the-art CNNs and vision transformers on ImageNet.
  arXiv  Detail & Related papers  (2021-06-03T17:57:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.