paper-with-me

Papers

Robust Trust Region for Weakly Supervised Segmentation

2021-04-05 · ICCV 2021 10 · Dmitrii Marin, Yuri Boykov

Acquisition of training data for the standard semantic segmentation is expensive if requiring that each pixel is labeled. Yet, current methods significantly deteriorate in weakly supervised settings, e.g. where a fraction of pixels is labeled or when only image-level tags are available. It has been shown that regularized losses - originally developed for unsupervised low-level segmentation and representing geometric priors on pixel labels - can considerably improve the quality of weakly supervised training. However, many common priors require optimization stronger than gradient descent. Thus, such regularizers have limited applicability in deep learning. We propose a new robust trust region approach for regularized losses improving the state-of-the-art results. Our approach can be seen as a higher-order generalization of the classic chain rule. It allows neural network optimization to use strong low-level solvers for the corresponding regularizers, including discrete ones.

📄 PDF Abstract BibTeX arXiv:2104.01948

Code (1)

dmitrii-marin/robust_trust_region 공식 구현 pytorch

Tasks

SegmentationSemantic SegmentationWeakly supervised segmentation

Similar Papers 제목 키워드 기반

Learning a Weakly-Supervised Video Actor-Action Segmentation Model with a Wise Selection

2020-03-29 · CVPR 2020 6 · Jie Chen, Zhiheng Li, Jiebo Luo, Chenliang Xu

We address weakly-supervised video actor-action segmentation (VAAS), which extends general video object segmentation (VOS) to additionally consider action labels of the actors. The most successful methods on VOS synthesi…

Action SegmentationSegmentationSemantic SegmentationVideo Object Segmentation+1

Weakly-supervised segmentation using inherently-explainable classification models and their application to brain tumour classification

2022-06-10 · Soumick Chatterjee, Hadya Yassin, Florian Dubost, Andreas Nürnberger 외

Deep learning models have shown their potential for several applications. However, most of the models are opaque and difficult to trust due to their complex reasoning - commonly known as the black-box problem. Some field…

ClassificationDecision MakingSegmentationTumour Classification+1

Weakly-Supervised Semantic Segmentation Network With Deep Seeded Region Growing

2018-06-01 · CVPR 2018 6 · Zilong Huang, Xinggang Wang, Jiasi Wang, Wenyu Liu 외

This paper studies the problem of learning image semantic segmentation networks only using image-level labels as supervision, which is important since it can significantly reduce human annotation efforts. Recent state-of…

Image SegmentationSegmentationSemantic SegmentationWeakly supervised Semantic Segmentation+1

DuPL: Dual Student with Trustworthy Progressive Learning for Robust Weakly Supervised Semantic Segmentation

2024-03-17 · CVPR 2024 1 · Yuanchen Wu, Xichen Ye, Kequan Yang, Jide Li 외

Recently, One-stage Weakly Supervised Semantic Segmentation (WSSS) with image-level labels has gained increasing interest due to simplification over its cumbersome multi-stage counterpart. Limited by the inherent ambigui…

Semantic SegmentationWeakly supervised Semantic SegmentationWeakly-Supervised Semantic Segmentation

Multi-Miner: Object-Adaptive Region Mining for Weakly-Supervised Semantic Segmentation

2020-06-14 · Kuangqi Zhou, Qibin Hou, Zun Li, Jiashi Feng

Object region mining is a critical step for weakly-supervised semantic segmentation. Most recent methods mine the object regions by expanding the seed regions localized by class activation maps. They generally do not con…

ObjectSegmentationSemantic SegmentationWeakly supervised Semantic Segmentation+1