ProPML: Probability Partial Multi-label Learning
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 12 of its 33 references that are in the map. First posted on arXiv 12 Mar 2024.
Builds on
12 of 33 references.
References · 12
- 2014Microsoft COCO: Common Objects in Contextcited by 17,608
- 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,269
- 2018BOHB: Robust and Efficient Hyperparameter Optimization at Scalecited by 470
- 2020Asymmetric Loss For Multi-Label Classificationcited by 381
- 2019Multi-Label Image Recognition with Graph Convolutional Networkscited by 322
- 2021Query2Label: A Simple Transformer Way to Multi-Label Classificationcited by 128
- 2020TResNet: High Performance GPU-Dedicated Architecturecited by 119
- 2020Progressive Identification of True Labels for Partial-Label Learningcited by 102
- 2020The Emerging Trends of Multi-Label Learningcited by 100
- 2019Adversarial Partial Multi-Label Learningcited by 5
- 2022A Deep Model for Partial Multi-Label Image Classification with Curriculum Based Disambiguationcited by 5
- 2022ProPaLL: Probabilistic Partial Label Learningcited by 1
Built on by
Citing papers per year: 2024: 1.
1 paper.