paper-with-me

Papers

Bootstrapping Semantic Segmentation with Regional Contrast

2021-04-09 · ICLR 2022 4 · Shikun Liu, Shuaifeng Zhi, Edward Johns, Andrew J. Davison

We present ReCo, a contrastive learning framework designed at a regional level to assist learning in semantic segmentation. ReCo performs semi-supervised or supervised pixel-level contrastive learning on a sparse set of hard negative pixels, with minimal additional memory footprint. ReCo is easy to implement, being built on top of off-the-shelf segmentation networks, and consistently improves performance in both semi-supervised and supervised semantic segmentation methods, achieving smoother segmentation boundaries and faster convergence. The strongest effect is in semi-supervised learning with very few labels. With ReCo, we achieve high-quality semantic segmentation models, requiring only 5 examples of each semantic class. Code is available at https://github.com/lorenmt/reco.

📄 PDF Abstract BibTeX arXiv:2104.04465

Code (2)

lorenmt/reco 공식 구현 pytorch
dbash/zerowaste pytorch

Tasks

Contrastive LearningSegmentationSemantic SegmentationSemi-Supervised Semantic Segmentation

Methods 이 논문이 사용한 방법론

Contrastive Learning 설명 없음
ReCo 설명 없음

Similar Papers 제목 키워드 기반

Domain Adaptive Semantic Segmentation via Regional Contrastive Consistency Regularization

2021-10-11 · Qianyu Zhou, Chuyun Zhuang, Ran Yi, Xuequan Lu 외

Unsupervised domain adaptation (UDA) for semantic segmentation has been well-studied in recent years. However, most existing works largely neglect the local regional consistency across different domains and are less robu…

Domain AdaptationSemantic SegmentationSynthetic-to-Real TranslationUnsupervised Domain Adaptation

Regional Semantic Contrast and Aggregation for Weakly Supervised Semantic Segmentation

2022-03-17 · CVPR 2022 1 · Tianfei Zhou, Meijie Zhang, Fang Zhao, Jianwu Li

Learning semantic segmentation from weakly-labeled (e.g., image tags only) data is challenging since it is hard to infer dense object regions from sparse semantic tags. Despite being broadly studied, most current efforts…

ObjectSemantic SegmentationWeakly supervised Semantic SegmentationWeakly-Supervised Semantic Segmentation

CYBORGS: Contrastively Bootstrapping Object Representations by Grounding in Segmentation

2022-03-17 · Renhao Wang, Hang Zhao, Yang Gao

Many recent approaches in contrastive learning have worked to close the gap between pretraining on iconic images like ImageNet and pretraining on complex scenes like COCO. This gap exists largely because commonly used ra…

Contrastive LearningObjectSegmentation

RANet: Region Attention Network for Semantic Segmentation

2020-12-01 · NeurIPS 2020 12 · Dingguo Shen, Yuanfeng Ji, Ping Li, Yi Wang 외

Recent semantic segmentation methods model the relationship between pixels to construct the contextual representations. In this paper, we introduce the \emph{Region Attention Network} (RANet), a novel attention network f…

ObjectSegmentationSemantic Segmentation

PIE: Physics-inspired Low-light Enhancement

2024-04-06 · Dong Liang, Zhengyan Xu, Ling Li, Mingqiang Wei 외

In this paper, we propose a physics-inspired contrastive learning paradigm for low-light enhancement, called PIE. PIE primarily addresses three issues: (i) To resolve the problem of existing learning-based methods often …

Contrastive LearningFace DetectionSemantic Segmentation