paper-with-me

홈 › Papers

Understanding Label Bias in Single Positive Multi-Label Learning

2023-05-24 · Julio Arroyo, Pietro Perona, Elijah Cole

Annotating data for multi-label classification is prohibitively expensive because every category of interest must be confirmed to be present or absent. Recent work on single positive multi-label (SPML) learning shows that it is possible to train effective multi-label classifiers using only one positive label per image. However, the standard benchmarks for SPML are derived from traditional multi-label classification datasets by retaining one positive label for each training example (chosen uniformly at random) and discarding all other labels. In realistic settings it is not likely that positive labels are chosen uniformly at random. This work introduces protocols for studying label bias in SPML and provides new empirical results.

📄 PDF Abstract BibTeX arXiv:2305.15584

Code (0)

등록된 구현이 없습니다.

Tasks

ClassificationMulti-Label ClassificationMUlTI-LABEL-ClASSIFICATIONMulti-Label Learning

Similar Papers 제목 키워드 기반

One Positive Label is Sufficient: Single-Positive Multi-Label Learning with Label Enhancement

2022-06-01 · Ning Xu, Congyu Qiao, Jiaqi Lv, Xin Geng 외

Multi-label learning (MLL) learns from the examples each associated with multiple labels simultaneously, where the high cost of annotating all relevant labels for each training example is challenging for real-world appli…

Multi-Label Learning

Overview of GeoLifeCLEF 2023: Species Composition Prediction with High Spatial Resolution at Continental Scale Using Remote Sensing

2025-09-30 · Christophe Botella, Benjamin Deneu, Diego Marcos, Maximilien Servajean 외 arxiv

Understanding the spatio-temporal distribution of species is a cornerstone of ecology and conservation. By pairing species observations with geographic and environmental predictors, researchers can model the relationship…

Multi-Label Classification

Can Class-Priors Help Single-Positive Multi-Label Learning?

2023-09-25 · Biao Liu, Ning Xu, Jie Wang, Xin Geng

Single-positive multi-label learning (SPMLL) is a typical weakly supervised multi-label learning problem, where each training example is annotated with only one positive label. Existing SPMLL methods typically assign pse…

Multi-Label Learning

Adapting Vision-Language Models from Iconic to Inclusive for Multi-Label Recognition Without Labels

2026-06-10 · Cheng Chen, Jingyu Zhou, Yifan Zhao, Jia Li arxiv

Understanding multi-label images remains a challenging task in computer vision. With the rapid progress of vision-language multimodal learning, vision-language models (VLMs) enable zero-shot recognition without labeled d…

Multi-Label Learning

Better Protein Function Prediction by Modeling Survivorship Bias

2026-05-07 · Zhongmou Chao, Poompol Buathong, Ekaterina Selivanovitch, Susan Daniel 외 arxiv

Protein sequence data from nature exhibits survivorship bias: we only observe data from those organisms that survive and reproduce, while non-functional protein mutations are eliminated by natural selection. Thus, predic…

Protein Function Prediction