paper-with-me

홈 › Papers

CF-ViT: A General Coarse-to-Fine Method for Vision Transformer

2022-03-08 · Mengzhao Chen, Mingbao Lin, Ke Li, Yunhang Shen, Yongjian Wu, Fei Chao, Rongrong Ji

Vision Transformers (ViT) have made many breakthroughs in computer vision tasks. However, considerable redundancy arises in the spatial dimension of an input image, leading to massive computational costs. Therefore, We propose a coarse-to-fine vision transformer (CF-ViT) to relieve computational burden while retaining performance in this paper. Our proposed CF-ViT is motivated by two important observations in modern ViT models: (1) The coarse-grained patch splitting can locate informative regions of an input image. (2) Most images can be well recognized by a ViT model in a small-length token sequence. Therefore, our CF-ViT implements network inference in a two-stage manner. At coarse inference stage, an input image is split into a small-length patch sequence for a computationally economical classification. If not well recognized, the informative patches are identified and further re-split in a fine-grained granularity. Extensive experiments demonstrate the efficacy of our CF-ViT. For example, without any compromise on performance, CF-ViT reduces 53% FLOPs of LV-ViT, and also achieves 2.01x throughput.

📄 PDF Abstract BibTeX arXiv:2203.03821

Code (1)

chenmnz/cf-vit 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Residual Connection 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Vision Transformer The Vision Transformer, or ViT, is a model for image classification that employs a Transformer-like architecture over…

Similar Papers 제목 키워드 기반

Progressive Fine-to-Coarse Reconstruction for Accurate Low-Bit Post-Training Quantization in Vision Transformers

2024-12-19 · Rui Ding, Liang Yong, Sihuan Zhao, Jing Nie 외

Due to its efficiency, Post-Training Quantization (PTQ) has been widely adopted for compressing Vision Transformers (ViTs). However, when quantized into low-bit representations, there is often a significant performance d…

Instance SegmentationPOSQuantizationSemantic Segmentation

Affine Medical Image Registration with Coarse-to-Fine Vision Transformer

2022-03-29 · CVPR 2022 1 · Tony C. W. Mok, Albert C. S. Chung

Affine registration is indispensable in a comprehensive medical image registration pipeline. However, only a few studies focus on fast and robust affine registration algorithms. Most of these studies utilize convolutiona…

Image RegistrationMedical Image RegistrationTemplate Matching

Paying U-Attention to Textures: Multi-Stage Hourglass Vision Transformer for Universal Texture Synthesis

2022-02-23 · Shouchang Guo, Valentin Deschaintre, Douglas Noll, Arthur Roullier

We present a novel U-Attention vision Transformer for universal texture synthesis. We exploit the natural long-range dependencies enabled by the attention mechanism to allow our approach to synthesize diverse textures wh…

Texture Synthesis

Focal Attention for Long-Range Interactions in Vision Transformers

2021-12-01 · NeurIPS 2021 12 · Jianwei Yang, Chunyuan Li, Pengchuan Zhang, Xiyang Dai 외

Recently, Vision Transformer and its variants have shown great promise on various computer vision tasks. The ability to capture local and global visual dependencies through self-attention is the key to its success. But i…

image-classificationImage Classificationobject-detectionObject Detection+1

MAFormer: A Transformer Network with Multi-scale Attention Fusion for Visual Recognition

2022-08-31 · Yunhao Wang, Huixin Sun, Xiaodi Wang, Bin Zhang 외

Vision Transformer and its variants have demonstrated great potential in various computer vision tasks. But conventional vision transformers often focus on global dependency at a coarse level, which suffer from a learnin…

Instance Segmentationobject-detectionObject DetectionSemantic Segmentation