Vicinity Vision Transformer

• URL: http://arxiv.org/abs/2206.10552v2
• Date: Thu, 20 Jul 2023 08:57:20 GMT
• Title: Vicinity Vision Transformer
• Authors: Weixuan Sun, Zhen Qin, Hui Deng, Jianyuan Wang, Yi Zhang, Kaihao Zhang, Nick Barnes, Stan Birchfield, Lingpeng Kong, Yiran Zhong
• Abstract summary: 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.
• Score: 53.43198716947792
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Vision transformers have shown great success on numerous computer vision tasks. However, its central component, softmax attention, prohibits vision transformers from scaling up to high-resolution images, due to both the computational complexity and memory footprint being quadratic. Although linear attention was introduced in natural language processing (NLP) tasks to mitigate a similar issue, directly applying existing linear attention to vision transformers may not lead to satisfactory results. We investigate this problem and find that computer vision tasks focus more on local information compared with NLP tasks. Based on this observation, we present a Vicinity Attention that introduces a locality bias to vision transformers with linear complexity. Specifically, for each image patch, we adjust its attention weight based on its 2D Manhattan distance measured by its neighbouring patches. In this case, the neighbouring patches will receive stronger attention than far-away patches. Moreover, since our Vicinity Attention requires the token length to be much larger than the feature dimension to show its efficiency advantages, we further propose a new Vicinity Vision Transformer (VVT) structure to reduce the feature dimension without degenerating the accuracy. We perform extensive experiments on the CIFAR100, ImageNet1K, and ADE20K datasets to validate the effectiveness of our method. Our method has a slower growth rate of GFlops than previous transformer-based and convolution-based networks when the input resolution increases. In particular, our approach achieves state-of-the-art image classification accuracy with 50% fewer parameters than previous methods.

Related papers

• DAT++: Spatially Dynamic Vision Transformer with Deformable Attention [87.41016963608067]
  We present Deformable Attention Transformer ( DAT++), a vision backbone efficient and effective for visual recognition. DAT++ achieves state-of-the-art results on various visual recognition benchmarks, with 85.9% ImageNet accuracy, 54.5 and 47.0 MS-COCO instance segmentation mAP, and 51.5 ADE20K semantic segmentation mIoU.
  arXiv  Detail & Related papers  (2023-09-04T08:26:47Z)
• FLatten Transformer: Vision Transformer using Focused Linear Attention [80.61335173752146]
  Linear attention offers a much more efficient alternative with its linear complexity. Current linear attention approaches either suffer from significant performance degradation or introduce additional computation overhead. We propose a novel Focused Linear Attention module to achieve both high efficiency and expressiveness.
  arXiv  Detail & Related papers  (2023-08-01T10:37:12Z)
• Explicitly Increasing Input Information Density for Vision Transformers on Small Datasets [26.257612622358614]
  Vision Transformers have attracted a lot of attention recently since the successful implementation of Vision Transformer (ViT) on vision tasks. This paper proposes to explicitly increase the input information density in the frequency domain. Experiments demonstrate the effectiveness of the proposed approach on five small-scale datasets.
  arXiv  Detail & Related papers  (2022-10-25T20:24:53Z)
• 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)
• 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)
• HRFormer: High-Resolution Transformer for Dense Prediction [99.6060997466614]
  We present a High-Resolution Transformer (HRFormer) that learns high-resolution representations for dense prediction tasks. We take advantage of the multi-resolution parallel design introduced in high-resolution convolutional networks (HRNet) We demonstrate the effectiveness of the High-Resolution Transformer on both human pose estimation and semantic segmentation tasks.
  arXiv  Detail & Related papers  (2021-10-18T15:37:58Z)
• Focal Self-attention for Local-Global Interactions in Vision Transformers [90.9169644436091]
  We present focal self-attention, a new mechanism that incorporates both fine-grained local and coarse-grained global interactions. With focal self-attention, we propose a new variant of Vision Transformer models, called Focal Transformer, which achieves superior performance over the state-of-the-art vision Transformers.
  arXiv  Detail & Related papers  (2021-07-01T17:56:09Z)
• 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)
• 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.