paper-with-me

Papers

Pseudo-Label Generation-Evaluation Framework For Cross Domain Weakly Supervised Object Detection

2021-08-23 · IEEE International Conference on Image Processing (ICIP) 2021 8 · Shengxiong Ouyang, Xinglu Wang, Kejie Lyu, Yingming Li

Cross domain weakly supervised object detection (CDWSOD), where we can get access to instance-level annotations in the source domain while only image-level annotations are available in the target domain, adapts object detectors from label-rich to label-poor domains. It usually generates pseudo labels in the target domain and utilize them to finetune the detector pretrained in the source domain. In this paper, we propose a new pseudo-label generation-evaluation framework for CDWSOD task. In particular, an evaluator is introduced for the generated pseudo labels in the target domain and the transferring process involves two players: the detector to generate instance-level pseudo labels and the evaluator to judge the quality of pseudo labels. Only high-quality pseudo labels selected by the evaluator are utilized to finetune the detector. Experiments on three representative datasets demonstrate the effectiveness of our framework in various domains.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

object-detectionObject DetectionPseudo LabelWeakly Supervised Object Detection

Similar Papers 제목 키워드 기반

Learning Pseudo Labels for Semi-and-Weakly Supervised Semantic Segmentation

2022-08-02 · Pattern Recognition 2022 8 · Yude Wang, Jie Zhang, Meina Kan, Shiguang Shan

In this paper, we aim to tackle semi-and-weakly supervised semantic segmentation (SWSSS), where many image-level classification labels and a few pixel-level annotations are available. We believe the most crucial point fo…

Pseudo LabelSemantic SegmentationSemi-Supervised Semantic SegmentationWeakly supervised Semantic Segmentation+1

You can't handle the (dirty) truth: Data-centric insights improve pseudo-labeling

2024-06-19 · Nabeel Seedat, Nicolas Huynh, Fergus Imrie, Mihaela van der Schaar

Pseudo-labeling is a popular semi-supervised learning technique to leverage unlabeled data when labeled samples are scarce. The generation and selection of pseudo-labels heavily rely on labeled data. Existing approaches …

A Semi-Supervised Framework for Breast Ultrasound Segmentation with Training-Free Pseudo-Label Generation and Label Refinement

2026-03-06 · Ruili Li, Jiayi Ding, Ruiyu Li, Yilun Jin 외 arxiv

Semi-supervised learning (SSL) has emerged as a promising paradigm for breast ultrasound (BUS) image segmentation, but it often suffers from unstable pseudo labels under extremely limited annotations, leading to inaccura…

Semi-supervised Medical Image SegmentationContrastive Learning

Full-Stage Pseudo Label Quality Enhancement for Weakly-supervised Temporal Action Localization

2024-07-12 · Qianhan Feng, Wenshuo Li, Tong Lin, Xinghao Chen

Weakly-supervised Temporal Action Localization (WSTAL) aims to localize actions in untrimmed videos using only video-level supervision. Latest WSTAL methods introduce pseudo label learning framework to bridge the gap bet…

Action LocalizationContrastive LearningPseudo LabelTemporal Action Localization+1

Domain-Aware Hierarchical Contrastive Learning for Semi-Supervised Generalization Fault Diagnosis

2026-04-22 · Junyu Ren, Wensheng Gan, Philip S Yu arxiv

Fault diagnosis under unseen operating conditions remains highly challenging when labeled data are scarce. Semi-supervised domain generalization fault diagnosis (SSDGFD) provides a practical solution by jointly exploitin…

Representation LearningDomain GeneralizationContrastive LearningFault Diagnosis