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.

本文提出了一种名为正例与未标注多标签分类（PU-MLC）的新方法，通过在训练时直接丢弃训练集中的负标签来减少嘈杂的标签所带来的不良影响，并通过引入自适应重平衡因子和自适应温度系数来缓解标签分布中的灾难性不平衡和概率平滑问题。大量的实验证明了 PU-MLC 方法在 MS-COCO 和 PASCAL VOC 数据集上取得了显着的改进。