Three things everyone should know about Vision Transformers

• URL: http://arxiv.org/abs/2203.09795v1
• Date: Fri, 18 Mar 2022 08:23:03 GMT
• Title: Three things everyone should know about Vision Transformers
• Authors: Hugo Touvron, Matthieu Cord, Alaaeldin El-Nouby, Jakob Verbeek, Herv\'e J\'egou
• Abstract summary: transformer architectures have rapidly gained traction in computer vision. We offer three insights based on simple and easy to implement variants of vision transformers. We evaluate the impact of these design choices using the ImageNet-1k dataset, and confirm our findings on the ImageNet-v2 test set.
• Score: 67.30250766591405
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: After their initial success in natural language processing, transformer architectures have rapidly gained traction in computer vision, providing state-of-the-art results for tasks such as image classification, detection, segmentation, and video analysis. We offer three insights based on simple and easy to implement variants of vision transformers. (1) The residual layers of vision transformers, which are usually processed sequentially, can to some extent be processed efficiently in parallel without noticeably affecting the accuracy. (2) Fine-tuning the weights of the attention layers is sufficient to adapt vision transformers to a higher resolution and to other classification tasks. This saves compute, reduces the peak memory consumption at fine-tuning time, and allows sharing the majority of weights across tasks. (3) Adding MLP-based patch pre-processing layers improves Bert-like self-supervised training based on patch masking. We evaluate the impact of these design choices using the ImageNet-1k dataset, and confirm our findings on the ImageNet-v2 test set. Transfer performance is measured across six smaller datasets.

Related papers

• 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)
• Vicinity Vision Transformer [53.43198716947792]
  We present a Vicinity Attention that introduces a locality bias to vision transformers with linear complexity. Our approach achieves state-of-the-art image classification accuracy with 50% fewer parameters than previous methods.
  arXiv  Detail & Related papers  (2022-06-21T17:33:53Z)
• AdaViT: Adaptive Vision Transformers for Efficient Image Recognition [78.07924262215181]
  We introduce AdaViT, an adaptive framework that learns to derive usage policies on which patches, self-attention heads and transformer blocks to use. Our method obtains more than 2x improvement on efficiency compared to state-of-the-art vision transformers with only 0.8% drop of accuracy.
  arXiv  Detail & Related papers  (2021-11-30T18:57:02Z)
• Patch Slimming for Efficient Vision Transformers [107.21146699082819]
  We study the efficiency problem for visual transformers by excavating redundant calculation in given networks. We present a novel patch slimming approach that discards useless patches in a top-down paradigm. Experimental results on benchmark datasets demonstrate that the proposed method can significantly reduce the computational costs of vision transformers.
  arXiv  Detail & Related papers  (2021-06-05T09:46:00Z)
• Improve Vision Transformers Training by Suppressing Over-smoothing [28.171262066145612]
  Introducing the transformer structure into computer vision tasks holds the promise of yielding a better speed-accuracy trade-off than traditional convolution networks. However, directly training vanilla transformers on vision tasks has been shown to yield unstable and sub-optimal results. Recent works propose to modify transformer structures by incorporating convolutional layers to improve the performance on vision tasks.
  arXiv  Detail & Related papers  (2021-04-26T17:43:04Z)
• Transformers in Vision: A Survey [101.07348618962111]
  Transformers enable modeling long dependencies between input sequence elements and support parallel processing of sequence. Transformers require minimal inductive biases for their design and are naturally suited as set-functions. This survey aims to provide a comprehensive overview of the Transformer models in the computer vision discipline.
  arXiv  Detail & Related papers  (2021-01-04T18:57:24Z)
• Toward Transformer-Based Object Detection [12.704056181392415]
  Vision Transformers can be used as a backbone by a common detection task head to produce competitive COCO results. ViT-FRCNN demonstrates several known properties associated with transformers, including large pretraining capacity and fast fine-tuning performance. We view ViT-FRCNN as an important stepping stone toward a pure-transformer solution of complex vision tasks such as object detection.
  arXiv  Detail & Related papers  (2020-12-17T22:33:14Z)

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.