paper-with-me

Weakly-Supervised Semantic Segmentation

10개 벤치마크 · 논문 299편 · 이 태스크의 논문 보기 →

Benchmarks

PASCAL VOC 2012 val

결과 146개

PASCAL VOC 2012 test

결과 120개

COCO 2014 val

결과 78개

PASCAL VOC 2012 train

결과 8개

ADE20K val

결과 2개

COCO-Stuff val

결과 2개

Cityscapes test

결과 2개

Cityscapes val

결과 2개

PASCAL Context val

결과 2개

^(#$!@#$)(()))******

결과 2개

Most implemented

Papers

Rewis3d: Reconstruction Improves Weakly-Supervised Semantic Segmentation

2026-03-06 · Jonas Ernst, Wolfgang Boettcher, Lukas Hoyer, Jan Eric Lenssen 외 arxiv

We present Rewis3d, a framework that leverages recent advances in feed-forward 3D reconstruction to significantly improve weakly supervised semantic segmentation on 2D images. Obtaining dense, pixel-level annotations rem…

Weakly-Supervised Semantic Segmentation3D ReconstructionPoint Clouds

TWLR: Text-Guided Weakly-Supervised Lesion Localization and Severity Regression for Explainable Diabetic Retinopathy Grading

2025-12-15 · Xi Luo, Shixin Xu, Ying Xie, JianZhong Hu 외 arxiv

Accurate medical image analysis can greatly assist clinical diagnosis, but its effectiveness relies on high-quality expert annotations Obtaining pixel-level labels for medical images, particularly fundus images, remains …

Weakly-Supervised Semantic SegmentationDiabetic Retinopathy GradingLesion Segmentation

Diffusion-Guided Knowledge Distillation for Weakly-Supervised Low-Light Semantic Segmentation

2025-07-10 · Chunyan Wang, Dong Zhang, Jinhui Tang arxiv

Weakly-supervised semantic segmentation aims to assign category labels to each pixel using weak annotations, significantly reducing manual annotation costs. Although existing methods have achieved remarkable progress in …

Weakly-Supervised Semantic SegmentationKnowledge Distillation

SPARS: Self-Play Adversarial Reinforcement Learning for Segmentation of Liver Tumours

2025-05-25 · Catalina Tan, Yipeng Hu, Shaheer U. Saeed

Accurate tumour segmentation is vital for various targeted diagnostic and therapeutic procedures for cancer, e.g., planning biopsies or tumour ablations. Manual delineation is extremely labour-intensive, requiring substa…

DiagnosticSemantic SegmentationWeakly supervised Semantic SegmentationWeakly-Supervised Semantic Segmentation

Exploring CLIP's Dense Knowledge for Weakly Supervised Semantic Segmentation

2025-03-26 · CVPR 2025 1 · Zhiwei Yang, Yucong Meng, Kexue Fu, Feilong Tang 외

Weakly Supervised Semantic Segmentation (WSSS) with image-level labels aims to achieve pixel-level predictions using Class Activation Maps (CAMs). Recently, Contrastive Language-Image Pre-training (CLIP) has been introdu…

AttributeSemantic SegmentationWeakly supervised Semantic SegmentationWeakly-Supervised Semantic Segmentation

Exploiting Inherent Class Label: Towards Robust Scribble Supervised Semantic Segmentation

2025-03-18 · Xinliang Zhang, Lei Zhu, Shuang Zeng, Hangzhou He 외

Scribble-based weakly supervised semantic segmentation leverages only a few annotated pixels as labels to train a segmentation model, presenting significant potential for reducing the human labor involved in the annotati…

SegmentationSemantic SegmentationWeakly supervised Semantic SegmentationWeakly-Supervised Semantic Segmentation

전체 299편 보기 →