Positive Label Is All You Need for Multi-Label Classification

by   Zhixiang Yuan, et al.

Multi-label classification (MLC) suffers from the inevitable label noise in training data due to the difficulty in annotating various semantic labels in each image. To mitigate the influence of noisy labels, existing methods mainly devote to identifying and correcting the label mistakes via a trained MLC model. However, these methods still involve annoying noisy labels in training, which can result in imprecise recognition of noisy labels and weaken the performance. In this paper, considering that the negative labels are substantially more than positive labels, and most noisy labels are from the negative labels, we directly discard all the negative labels in the dataset, and propose a new method dubbed positive and unlabeled multi-label classification (PU-MLC). By extending positive-unlabeled learning into MLC task, our method trains model with only positive labels and unlabeled data, and introduces adaptive re-balance factor and adaptive temperature coefficient in the loss function to alleviate the catastrophic imbalance in label distribution and over-smoothing of probabilities in training. Our PU-MLC is simple and effective, and it is applicable to both MLC and MLC with partial labels (MLC-PL) tasks. Extensive experiments on MS-COCO and PASCAL VOC datasets demonstrate that our PU-MLC achieves significantly improvements on both MLC and MLC-PL settings with even fewer annotations. Code will be released.


page 3

page 4


Acknowledging the Unknown for Multi-label Learning with Single Positive Labels

Due to the difficulty of collecting exhaustive multi-label annotations, ...

Simple and Robust Loss Design for Multi-Label Learning with Missing Labels

Multi-label learning in the presence of missing labels (MLML) is a chall...

Exploiting Context for Robustness to Label Noise in Active Learning

Several works in computer vision have demonstrated the effectiveness of ...

Learning from Noisy Labels with Noise Modeling Network

Multi-label image classification has generated significant interest in r...

Joint Negative and Positive Learning for Noisy Labels

Training of Convolutional Neural Networks (CNNs) with data with noisy la...

G2NetPL: Generic Game-Theoretic Network for Partial-Label Image Classification

Multi-label image classification aims to predict all possible labels in ...

Category-Adaptive Label Discovery and Noise Rejection for Multi-label Image Recognition with Partial Positive Labels

As a promising solution of reducing annotation cost, training multi-labe...

Please sign up or login with your details

Forgot password? Click here to reset