Probability Guided Loss for Long-Tailed Multi-Label Image Classification
Proceedings of the AAAI Conference on Artificial Intelligence · 26.06.2023 · 37 (2) · 1577-1585
DOI: 10.1609/aaai.v37i2.25244 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 26.06.2023. Verfasst von Dekun Lin. Die Arbeit wurde bisher 16-mal zitiert (Crossref).
Abstract (Originalsprache)
Long-tailed learning has attracted increasing attention in very recent years. Long-tailed multi-label image classification is one subtask and remains challenging and poorly researched. In this paper, we provide a fresh perspective from probability to tackle this problem. More specifically, we find that existing cost-sensitive learning methods for long-tailed multi-label classification will affect the predicted probability of positive and negative labels in varying degrees during training, and different processes of probability will affect the final performance in turn. We thus propose a probability guided loss which contains two components to control this process. One is the probability re-balancing which can flexibly adjust the process of training probability. And the other is the adaptive probability-aware focal which can further reduce the probability gap between positive and negative labels. We conduct extensive experiments on two long-tailed multi-label image classification datasets: VOC-LT and COCO-LT. The results demonstrate the rationality and superiority of our strategy.
Zitieren
APA
Lin, D. (2023). Probability Guided Loss for Long-Tailed Multi-Label Image Classification. Proceedings of the AAAI Conference on Artificial Intelligence, 37(2), 1577-1585. https://doi.org/10.1609/aaai.v37i2.25244
Vancouver
Lin D. Probability Guided Loss for Long-Tailed Multi-Label Image Classification. Proceedings of the AAAI Conference on Artificial Intelligence. 2023;37(2):1577-1585. doi:10.1609/aaai.v37i2.25244
BibTeX
@article{Lin2023,
author = {Lin, Dekun},
title = {Probability Guided Loss for Long-Tailed Multi-Label Image Classification},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2023},
volume = {37},
number = {2},
pages = {1577--1585},
doi = {10.1609/aaai.v37i2.25244}
}
EUVIMED