Blending Anti-Aliasing into Vision Transformer

• URL: http://arxiv.org/abs/2110.15156v1
• Date: Thu, 28 Oct 2021 14:30:02 GMT
• Title: Blending Anti-Aliasing into Vision Transformer
• Authors: Shengju Qian, Hao Shao, Yi Zhu, Mu Li, Jiaya Jia
• Abstract summary: discontinuous patch-wise tokenization process implicitly introduces jagged artifacts into attention maps. Aliasing effect occurs when discrete patterns are used to produce high frequency or continuous information, resulting in the indistinguishable distortions. We propose a plug-and-play Aliasing-Reduction Module(ARM) to alleviate the aforementioned issue.
• Score: 57.88274087198552
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The transformer architectures, based on self-attention mechanism and convolution-free design, recently found superior performance and booming applications in computer vision. However, the discontinuous patch-wise tokenization process implicitly introduces jagged artifacts into attention maps, arising the traditional problem of aliasing for vision transformers. Aliasing effect occurs when discrete patterns are used to produce high frequency or continuous information, resulting in the indistinguishable distortions. Recent researches have found that modern convolution networks still suffer from this phenomenon. In this work, we analyze the uncharted problem of aliasing in vision transformer and explore to incorporate anti-aliasing properties. Specifically, we propose a plug-and-play Aliasing-Reduction Module(ARM) to alleviate the aforementioned issue. We investigate the effectiveness and generalization of the proposed method across multiple tasks and various vision transformer families. This lightweight design consistently attains a clear boost over several famous structures. Furthermore, our module also improves data efficiency and robustness of vision transformers.

Related papers

• Attention Deficit is Ordered! Fooling Deformable Vision Transformers with Collaborative Adversarial Patches [3.4673556247932225]
  Deformable vision transformers significantly reduce the complexity of attention modeling. Recent work has demonstrated adversarial attacks against conventional vision transformers. We develop new collaborative attacks where a source patch manipulates attention to point to a target patch, which contains the adversarial noise to fool the model.
  arXiv  Detail & Related papers  (2023-11-21T17:55:46Z)
• What Makes for Good Tokenizers in Vision Transformer? [62.44987486771936]
  transformers are capable of extracting their pairwise relationships using self-attention. What makes for a good tokenizer has not been well understood in computer vision. Modulation across Tokens (MoTo) incorporates inter-token modeling capability through normalization. Regularization objective TokenProp is embraced in the standard training regime.
  arXiv  Detail & Related papers  (2022-12-21T15:51:43Z)
• Vision Transformers for Action Recognition: A Survey [41.69370782177517]
  Vision transformers are emerging as a powerful tool to solve computer vision problems. Recent techniques have proven the efficacy of transformers beyond the image domain to solve numerous video-related tasks. Human action recognition is receiving special attention from the research community due to its widespread applications.
  arXiv  Detail & Related papers  (2022-09-13T02:57:05Z)
• Visualizing and Understanding Patch Interactions in Vision Transformer [96.70401478061076]
  Vision Transformer (ViT) has become a leading tool in various computer vision tasks. We propose a novel explainable visualization approach to analyze and interpret the crucial attention interactions among patches for vision transformer.
  arXiv  Detail & Related papers  (2022-03-11T13:48:11Z)
• 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)
• Augmented Shortcuts for Vision Transformers [49.70151144700589]
  We study the relationship between shortcuts and feature diversity in vision transformer models. We present an augmented shortcut scheme, which inserts additional paths with learnable parameters in parallel on the original shortcuts. Experiments conducted on benchmark datasets demonstrate the effectiveness of the proposed method.
  arXiv  Detail & Related papers  (2021-06-30T09:48:30Z)
• 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 Solve the Limited Receptive Field for Monocular Depth Prediction [82.90445525977904]
  We propose TransDepth, an architecture which benefits from both convolutional neural networks and transformers. This is the first paper which applies transformers into pixel-wise prediction problems involving continuous labels.
  arXiv  Detail & Related papers  (2021-03-22T18:00:13Z)

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.