VALSE 论文速览 第80期：全监督对比学习：语义分割新训练范式 ...

论文题目：Exploring Cross-Image Pixel Contrast for Semantic Segmentation

作者列表：Wenguan Wang (ETH Zurich，共同一作)，Tianfei Zhou (ETH Zurich，共同一作)，Fisher Yu (ETH Zurich)，Jifeng Dai (Sensetime Research)，Ender Konukoglu (ETH Zurich), Luc Van Gool (ETH Zurich)

B站观看网址：

https://www.bilibili.com/video/BV1V34y1W7Wc/

论文摘要：

Current semantic segmentation methods focus only on mining "local"context, i.e., dependencies between pixels within individual images, by context-aggregation modules (e.g., dilated convolution, neural attention)or structure-aware optimization criteria (e.g., IoU-like loss). However, they ignore "global"context of the training data, i.e., rich semantic relations between pixels across different images. Inspired by the recent advance in unsupervised contrastive representation learning, we propose a pixel-wise contrastive framework for semantic segmentation in the fully supervised setting. The core idea is to enforce pixel embeddings belonging to a same semantic class to be more similar than embeddings from different classes. It raises a pixel-wise metric learning paradigm for semantic segmentation, by explicitly exploring the structures of labeled pixels, which were rarely explored before. Our method can be effortlessly incorporated into existing segmentation frameworks without extra overhead during testing. We experimentally show that, with famous segmentation models (i.e., DeepLabV3, HRNet, OCR)and backbones (i.e., ResNet, HR-Net), our method brings consistent performance improvements across diverse datasets (i.e., Cityscapes, PASCAL-Context, COCO-Stuff, CamVid). We expect this work will encourage our community to rethink the current de facto training paradigm in fully supervised semantic segmentation.

论文信息：

[1] Wenguan Wang*, Tianfei Zhou*, Fisher Yu, Jifeng Dai, Ender Konukoglu and Luc Van Gool. Exploring Cross-Image Pixel Contrast for Semantic Segmentation. ICCV 2021 (Oral)

论文链接：

[https://arxiv.org/pdf/2101.11939.pdf]

代码链接：

[https://github.com/tfzhou/ContrastiveSeg]

视频讲者简介：

周天飞，苏黎世联邦理工学院CVL博后研究员，主要研究方向是计算机视觉和深度学习。

特别鸣谢本次论文速览主要组织者：

月度轮值AC：赵文达 (大连理工大学)、任文琦 (中山大学)

季度责任AC：魏秀参 (南京理工大学)