Learning to Merge Tokens in Vision Transformers

• URL: http://arxiv.org/abs/2202.12015v1
• Date: Thu, 24 Feb 2022 10:56:17 GMT
• Title: Learning to Merge Tokens in Vision Transformers
• Authors: Cedric Renggli, Andr\'e Susano Pinto, Neil Houlsby, Basil Mustafa, Joan Puigcerver, Carlos Riquelme
• Abstract summary: We present the PatchMerger, a module that reduces the number of patches or tokens the network has to process by merging them between two consecutive intermediate layers. We show that the PatchMerger achieves a significant speedup across various model sizes while matching the original performance both upstream and downstream after fine-tuning.
• Score: 22.029357721814044
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Transformers are widely applied to solve natural language understanding and computer vision tasks. While scaling up these architectures leads to improved performance, it often comes at the expense of much higher computational costs. In order for large-scale models to remain practical in real-world systems, there is a need for reducing their computational overhead. In this work, we present the PatchMerger, a simple module that reduces the number of patches or tokens the network has to process by merging them between two consecutive intermediate layers. We show that the PatchMerger achieves a significant speedup across various model sizes while matching the original performance both upstream and downstream after fine-tuning.

Related papers

• Learned Thresholds Token Merging and Pruning for Vision Transformers [5.141687309207561]
  This paper introduces Learned Thresholds token Merging and Pruning (LTMP), a novel approach that leverages the strengths of both token merging and token pruning. We demonstrate our approach with extensive experiments on vision transformers on the ImageNet classification task.
  arXiv  Detail & Related papers  (2023-07-20T11:30:12Z)
• ClusTR: Exploring Efficient Self-attention via Clustering for Vision Transformers [70.76313507550684]
  We propose a content-based sparse attention method, as an alternative to dense self-attention. Specifically, we cluster and then aggregate key and value tokens, as a content-based method of reducing the total token count. The resulting clustered-token sequence retains the semantic diversity of the original signal, but can be processed at a lower computational cost.
  arXiv  Detail & Related papers  (2022-08-28T04:18:27Z)
• Dynamic Spatial Sparsification for Efficient Vision Transformers and Convolutional Neural Networks [88.77951448313486]
  We present a new approach for model acceleration by exploiting spatial sparsity in visual data. We propose a dynamic token sparsification framework to prune redundant tokens. We extend our method to hierarchical models including CNNs and hierarchical vision Transformers.
  arXiv  Detail & Related papers  (2022-07-04T17:00:51Z)
• Learned Queries for Efficient Local Attention [11.123272845092611]
  Self-attention mechanism in vision transformers suffers from high latency and inefficient memory utilization. We propose a new shift-invariant local attention layer, called query and attend (QnA), that aggregates the input locally in an overlapping manner. We show improvements in speed and memory complexity while achieving comparable accuracy with state-of-the-art models.
  arXiv  Detail & Related papers  (2021-12-21T18:52:33Z)
• Local-to-Global Self-Attention in Vision Transformers [130.0369761612812]
  Transformers have demonstrated great potential in computer vision tasks. Some recent Transformer models adopt a hierarchical design, where self-attentions are only computed within local windows. This design significantly improves the efficiency but lacks global feature reasoning in early stages. In this work, we design a multi-path structure of the Transformer, which enables local-to-global reasoning at multiple granularities in each stage.
  arXiv  Detail & Related papers  (2021-07-10T02:34:55Z)
• IA-RED$^2$: Interpretability-Aware Redundancy Reduction for Vision Transformers [81.31885548824926]
  Self-attention-based model, transformer, is recently becoming the leading backbone in the field of computer vision. We present an Interpretability-Aware REDundancy REDuction framework (IA-RED$2$) We include extensive experiments on both image and video tasks, where our method could deliver up to 1.4X speed-up.
  arXiv  Detail & Related papers  (2021-06-23T18:29:23Z)
• Less is More: Pay Less Attention in Vision Transformers [61.05787583247392]
  Less attention vIsion Transformer builds upon the fact that convolutions, fully-connected layers, and self-attentions have almost equivalent mathematical expressions for processing image patch sequences. The proposed LIT achieves promising performance on image recognition tasks, including image classification, object detection and instance segmentation.
  arXiv  Detail & Related papers  (2021-05-29T05:26:07Z)
• CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification [17.709880544501758]
  We propose a dual-branch transformer to combine image patches of different sizes to produce stronger image features. Our approach processes small-patch and large-patch tokens with two separate branches of different computational complexity. Our proposed cross-attention only requires linear time for both computational and memory complexity instead of quadratic time otherwise.
  arXiv  Detail & Related papers  (2021-03-27T13:03:17Z)
• Addressing Some Limitations of Transformers with Feedback Memory [51.94640029417114]
  Transformers have been successfully applied to sequential, auto-regressive tasks despite being feedforward networks. We propose the Feedback Transformer architecture that exposes all previous representations to all future representations. We demonstrate on a variety of benchmarks in language modeling, machine translation, and reinforcement learning that the increased representation capacity can create small, shallow models with much stronger performance than comparable Transformers.
  arXiv  Detail & Related papers  (2020-02-21T16:37:57Z)

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.