paper-with-me

홈 › Papers

ProPML: Probability Partial Multi-label Learning

2024-03-12 · Łukasz Struski, Adam Pardyl, Jacek Tabor, Bartosz Zieliński

Partial Multi-label Learning (PML) is a type of weakly supervised learning where each training instance corresponds to a set of candidate labels, among which only some are true. In this paper, we introduce \our{}, a novel probabilistic approach to this problem that extends the binary cross entropy to the PML setup. In contrast to existing methods, it does not require suboptimal disambiguation and, as such, can be applied to any deep architecture. Furthermore, experiments conducted on artificial and real-world datasets indicate that \our{} outperforms existing approaches, especially for high noise in a candidate set.

📄 PDF Abstract BibTeX arXiv:2403.07603

Code (1)

gmum/propml 공식 구현 pytorch

Tasks

Multi-Label LearningWeakly-supervised Learning

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Marginal loss and exclusion loss for partially supervised multi-organ segmentation

2020-07-08 · Gonglei Shi, Li Xiao, Yang Chen, S. Kevin Zhou

Annotating multiple organs in medical images is both costly and time-consuming; therefore, existing multi-organ datasets with labels are often low in sample size and mostly partially labeled, that is, a dataset has a few…

Organ SegmentationSegmentation

Proper losses for learning from partial labels

2012-12-01 · NeurIPS 2012 12 · Jesús Cid-Sueiro

This paper discusses the problem of calibrating posterior class probabilities from partially labelled data. Each instance is assumed to be labelled as belonging to one of several candidate categories, at most one of them…

Multi-Instance Partial-Label Learning with Margin Adjustment

2025-01-22 · Wei Tang, Yin-Fang Yang, Zhaofei Wang, Weijia Zhang 외

Multi-instance partial-label learning (MIPL) is an emerging learning framework where each training sample is represented as a multi-instance bag associated with a candidate label set. Existing MIPL algorithms often overl…

Partial Label Learning

Multi-label Classification with Partial Annotations using Class-aware Selective Loss

2021-10-21 · CVPR 2022 1 · Emanuel Ben-Baruch, Tal Ridnik, Itamar Friedman, Avi Ben-Cohen 외

Large-scale multi-label classification datasets are commonly, and perhaps inevitably, partially annotated. That is, only a small subset of labels are annotated per sample. Different methods for handling the missing label…

Missing LabelsMulti-Label ClassificationMUlTI-LABEL-ClASSIFICATION

Beyond Novelty Detection: Incongruent Events, when General and Specific Classifiers Disagree

2008-12-01 · NeurIPS 2008 12 · Daphna Weinshall, Hynek Hermansky, Alon Zweig, Jie Luo 외

Unexpected stimuli are a challenge to any machine learning algorithm. Here we identify distinct types of unexpected events, focusing on 'incongruent events' - when 'general level' and 'specific level' classifiers give co…

Novelty DetectionObject Recognitionspeech-recognitionSpeech Recognition