Sub-token ViT Embedding via Stochastic Resonance Transformers

• URL: http://arxiv.org/abs/2310.03967v2
• Date: Mon, 6 May 2024 18:39:58 GMT
• Title: Sub-token ViT Embedding via Stochastic Resonance Transformers
• Authors: Dong Lao, Yangchao Wu, Tian Yu Liu, Alex Wong, Stefano Soatto,
• Abstract summary: Vision Transformer (ViT) architectures represent images as collections of high-dimensional vectorized tokens, each corresponding to a rectangular non-overlapping patch. We propose a training-free method inspired by "stochastic resonance" The resulting "Stochastic Resonance Transformer" (SRT) retains the rich semantic information of the original representation, but grounds it on a finer-scale spatial domain, partly mitigating the coarse effect of spatial tokenization.
• Score: 51.12001699637727
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Vision Transformer (ViT) architectures represent images as collections of high-dimensional vectorized tokens, each corresponding to a rectangular non-overlapping patch. This representation trades spatial granularity for embedding dimensionality, and results in semantically rich but spatially coarsely quantized feature maps. In order to retrieve spatial details beneficial to fine-grained inference tasks we propose a training-free method inspired by "stochastic resonance". Specifically, we perform sub-token spatial transformations to the input data, and aggregate the resulting ViT features after applying the inverse transformation. The resulting "Stochastic Resonance Transformer" (SRT) retains the rich semantic information of the original representation, but grounds it on a finer-scale spatial domain, partly mitigating the coarse effect of spatial tokenization. SRT is applicable across any layer of any ViT architecture, consistently boosting performance on several tasks including segmentation, classification, depth estimation, and others by up to 14.9% without the need for any fine-tuning.

Related papers

• White-Box Transformers via Sparse Rate Reduction: Compression Is All There Is? [27.58916930770997]
  We show a family of white-box transformer-like deep network architectures, named CRATE, which are mathematically fully interpretable. Experiments show that these networks, despite their simplicity, indeed learn to compress and sparsify representations of large-scale real-world image and text datasets.
  arXiv  Detail & Related papers  (2023-11-22T02:23:32Z)
• AiluRus: A Scalable ViT Framework for Dense Prediction [95.1313839257891]
  Vision transformers (ViTs) have emerged as a prevalent architecture for vision tasks owing to their impressive performance. We propose to apply adaptive resolution for different regions in the image according to their importance. We evaluate our proposed method on three different datasets and observe promising performance.
  arXiv  Detail & Related papers  (2023-11-02T12:48:43Z)
• White-Box Transformers via Sparse Rate Reduction [25.51855431031564]
  We show a family of white-box transformer-like deep network architectures which are mathematically fully interpretable. Experiments show that these networks indeed learn to optimize the designed objective.
  arXiv  Detail & Related papers  (2023-06-01T20:28:44Z)
• Spectral Enhanced Rectangle Transformer for Hyperspectral Image Denoising [64.11157141177208]
  We propose a spectral enhanced rectangle Transformer to model the spatial and spectral correlation in hyperspectral images. For the former, we exploit the rectangle self-attention horizontally and vertically to capture the non-local similarity in the spatial domain. For the latter, we design a spectral enhancement module that is capable of extracting global underlying low-rank property of spatial-spectral cubes to suppress noise.
  arXiv  Detail & Related papers  (2023-04-03T09:42:13Z)
• Making Vision Transformers Efficient from A Token Sparsification View [26.42498120556985]
  We propose a novel Semantic Token ViT (STViT) for efficient global and local vision transformers. Our method can achieve competitive results compared to the original networks in object detection and instance segmentation, with over 30% FLOPs reduction for backbone. In addition, we design a STViT-R(ecover) network to restore the detailed spatial information based on the STViT, making it work for downstream tasks.
  arXiv  Detail & Related papers  (2023-03-15T15:12:36Z)
• SegViT: Semantic Segmentation with Plain Vision Transformers [91.50075506561598]
  We explore the capability of plain Vision Transformers (ViTs) for semantic segmentation. We propose the Attention-to-Mask (ATM) module, in which similarity maps between a set of learnable class tokens and the spatial feature maps are transferred to the segmentation masks. Experiments show that our proposed SegVit using the ATM module outperforms its counterparts using the plain ViT backbone.
  arXiv  Detail & Related papers  (2022-10-12T00:30:26Z)
• Is Attention All NeRF Needs? [103.51023982774599]
  Generalizable NeRF Transformer (GNT) is a pure, unified transformer-based architecture that efficiently reconstructs Neural Radiance Fields (NeRFs) on the fly from source views. GNT achieves generalizable neural scene representation and rendering, by encapsulating two transformer-based stages.
  arXiv  Detail & Related papers  (2022-07-27T05:09:54Z)
• PnP-DETR: Towards Efficient Visual Analysis with Transformers [146.55679348493587]
  Recently, DETR pioneered the solution vision tasks with transformers, it directly translates the image feature map into the object result. Recent transformer-based image recognition model andTT show consistent efficiency gain.
  arXiv  Detail & Related papers  (2021-09-15T01:10:30Z)

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.