paper-with-me

홈 › Papers

Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers

2020-12-31 · CVPR 2021 1 · Sixiao Zheng, Jiachen Lu, Hengshuang Zhao, Xiatian Zhu, Zekun Luo, Yabiao Wang, Yanwei Fu, Jianfeng Feng, Tao Xiang, Philip H. S. Torr, Li Zhang

Most recent semantic segmentation methods adopt a fully-convolutional network (FCN) with an encoder-decoder architecture. The encoder progressively reduces the spatial resolution and learns more abstract/semantic visual concepts with larger receptive fields. Since context modeling is critical for segmentation, the latest efforts have been focused on increasing the receptive field, through either dilated/atrous convolutions or inserting attention modules. However, the encoder-decoder based FCN architecture remains unchanged. In this paper, we aim to provide an alternative perspective by treating semantic segmentation as a sequence-to-sequence prediction task. Specifically, we deploy a pure transformer (ie, without convolution and resolution reduction) to encode an image as a sequence of patches. With the global context modeled in every layer of the transformer, this encoder can be combined with a simple decoder to provide a powerful segmentation model, termed SEgmentation TRansformer (SETR). Extensive experiments show that SETR achieves new state of the art on ADE20K (50.28% mIoU), Pascal Context (55.83% mIoU) and competitive results on Cityscapes. Particularly, we achieve the first position in the highly competitive ADE20K test server leaderboard on the day of submission.

📄 PDF Abstract BibTeX arXiv:2012.15840

Code (5)

fudan-zvg/SETR 공식 구현 pytorch
920232796/setr-pytorch pytorch
BR-IDL/PaddleViT/tree/main/semantic_segmentation paddle
PaddlePaddle/PaddleSeg paddle
gupta-abhay/setr-pytorch pytorch

Tasks

DecoderMedical Image SegmentationSegmentationSemantic Segmentation

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
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…
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 $x$…
Residual Connection 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Multi-Head Attention 설명 없음
Position-Wise Feed-Forward Layer 설명 없음

Similar Papers 제목 키워드 기반

Rethinking Vector Field Learning for Generative Segmentation

2026-03-19 · Chaoyang Wang, Yaobo Liang, Boci Peng, Fan Duan 외 arxiv

Taming diffusion models for generative segmentation has attracted increasing attention. While existing approaches primarily focus on architectural tweaks or training heuristics, there remains a limited understanding of t…

TEA: Temporal Adaptive Satellite Image Semantic Segmentation

2026-01-08 · Juyuan Kang, Hao Zhu, Yan Zhu, Wei Zhang 외 arxiv

Crop mapping based on satellite images time-series (SITS) holds substantial economic value in agricultural production settings, in which parcel segmentation is an essential step. Existing approaches have achieved notable…

Semantic Segmentation

Rethinking the protein folding problem from a new perspective

2022-10-10 · Jorge A. Vila

One of the main concerns of Anfinsen was to reveal the connection between the amino acid sequence and their biologically active conformation. This search gave rise to two crucial questions in structural biology, namely, …

Protein Folding

DFormer: Rethinking RGBD Representation Learning for Semantic Segmentation

2023-09-18 · Bowen Yin, Xuying Zhang, Zhongyu Li, Li Liu 외

We present DFormer, a novel RGB-D pretraining framework to learn transferable representations for RGB-D segmentation tasks. DFormer has two new key innovations: 1) Unlike previous works that encode RGB-D information with…

3D geometryDecoderobject-detectionObject Detection+6

Timestamp-Supervised Action Segmentation from the Perspective of Clustering

2022-12-22 · Dazhao Du, Enhan Li, Lingyu Si, Fanjiang Xu 외

Video action segmentation under timestamp supervision has recently received much attention due to lower annotation costs. Most existing methods generate pseudo-labels for all frames in each video to train the segmentatio…

Action SegmentationClusteringPseudo LabelSegmentation