paper-with-me

Papers

Weakly supervised clustering: Learning fine-grained signals from coarse labels

2013-10-04 · Stefan Wager, Alexander Blocker, Niall Cardin

Consider a classification problem where we do not have access to labels for individual training examples, but only have average labels over subpopulations. We give practical examples of this setup and show how such a classification task can usefully be analyzed as a weakly supervised clustering problem. We propose three approaches to solving the weakly supervised clustering problem, including a latent variables model that performs well in our experiments. We illustrate our methods on an analysis of aggregated elections data and an industry data set that was the original motivation for this research.

📄 PDF Abstract BibTeX arXiv:1310.1363

Code (0)

등록된 구현이 없습니다.

Tasks

ClassificationClusteringGeneral Classification

Similar Papers 제목 키워드 기반

Weakly-Supervised Temporal Action Detection for Fine-Grained Videos with Hierarchical Atomic Actions

2022-07-24 · Zhi Li, Lu He, Huijuan Xu

Action understanding has evolved into the era of fine granularity, as most human behaviors in real life have only minor differences. To detect these fine-grained actions accurately in a label-efficient way, we tackle the…

Action DetectionAction UnderstandingFine-Grained Action DetectionWeakly Supervised Action Localization

Contrastive Prompt Clustering for Weakly Supervised Semantic Segmentation

2025-08-23 · Wangyu Wu, Zhenhong Chen, Xiaowen Ma, Wenqiao Zhang 외 arxiv

Weakly Supervised Semantic Segmentation (WSSS) with image-level labels has gained attention for its cost-effectiveness. Most existing methods emphasize inter-class separation, often neglecting the shared semantics among …

Semantic Segmentation

Weakly-Supervised Learning of Visual Relations in Multimodal Pretraining

2023-05-23 · Emanuele Bugliarello, Aida Nematzadeh, Lisa Anne Hendricks

Recent work in vision-and-language pretraining has investigated supervised signals from object detection data to learn better, fine-grained multimodal representations. In this work, we take a step further and explore how…

object-detectionObject DetectionRelationRelation Prediction+1

Weakly Supervised Multi-Label Classification of Full-Text Scientific Papers

2023-06-24 · Yu Zhang, Bowen Jin, Xiusi Chen, Yanzhen Shen 외

Instead of relying on human-annotated training samples to build a classifier, weakly supervised scientific paper classification aims to classify papers only using category descriptions (e.g., category names, category-ind…

Multi-Label ClassificationMUlTI-LABEL-ClASSIFICATION

Distribution Guidance Network for Weakly Supervised Point Cloud Semantic Segmentation

2024-10-10 · Zhiyi Pan, Wei Gao, Shan Liu, Ge Li

Despite alleviating the dependence on dense annotations inherent to fully supervised methods, weakly supervised point cloud semantic segmentation suffers from inadequate supervision signals. In response to this challenge…

Semantic SegmentationWeakly-supervised Learning