Category-wise Fine-Tuning: Resisting Incorrect Pseudo-Labels in Multi-Label Image Classification with Partial Labels. (arXiv:2401.16991v1 [cs.CV])

Large-scale image datasets are often partially labeled, where only a few
categories' labels are known for each image. Assigning pseudo-labels to unknown
labels to gain additional training signals has become prevalent for training
deep classification models. However, some pseudo-labels are inevitably
incorrect, leading to a notable decline in the model classification
performance. In this paper, we propose a novel method called Category-wise
Fine-Tuning (CFT), aiming to reduce model inaccuracies caused by the wrong
pseudo-labels. In particular, CFT employs known labels …

arxiv become classification cs.cv datasets fine-tuning image image datasets labels scale training wise