Positive Label Is All You Need for Multi-Label Classification

TL;DR

This paper introduces PU-MLC, a novel multi-label classification method that effectively handles label noise by focusing on positive and unlabeled data, improving performance on standard datasets with fewer annotations.

Contribution

The paper proposes a positive-unlabeled learning approach for multi-label classification that discards negative labels and incorporates adaptive loss components to mitigate label noise.

Findings

PU-MLC outperforms existing methods on MS-COCO and PASCAL VOC datasets.

The method achieves higher accuracy with fewer annotations.

It effectively reduces the impact of noisy labels during training.

Abstract

Multi-label classification (MLC) faces challenges from label noise in training data due to annotating diverse semantic labels for each image. Current methods mainly target identifying and correcting label mistakes using trained MLC models, but still struggle with persistent noisy labels during training, resulting in imprecise recognition and reduced performance. Our paper addresses label noise in MLC by introducing a positive and unlabeled multi-label classification (PU-MLC) method. To counteract noisy labels, we directly discard negative labels, focusing on the abundance of negative labels and the origin of most noisy labels. PU-MLC employs positive-unlabeled learning, training the model with only positive labels and unlabeled data. The method incorporates adaptive re-balance factors and temperature coefficients in the loss function to address label distribution imbalance and prevent over-smoothing of probabilities during training. Additionally, we introduce a local-global convolution module to capture both local and global dependencies in the image without requiring backbone retraining. PU-MLC proves effective on MLC and MLC with partial labels (MLC-PL) tasks, demonstrating significant improvements on MS-COCO and PASCAL VOC datasets with fewer annotations. Code is available at: https://github.com/TAKELAMAG/PU-MLC.