Label Distribution Learning with Biased Annotations by Learning Multi-Label Representation

TL;DR

This paper proposes a novel approach for Label Distribution Learning with biased annotations, transforming soft labels into hard multi-hot labels to improve robustness and accuracy in recovering true label distributions.

Contribution

It introduces a new method that degenerates soft label distributions into hard labels before recovery, addressing bias and noise issues more effectively than low-rank approximation methods.

Findings

Method improves label distribution recovery accuracy.

Demonstrates robustness against annotation bias and noise.

Validated on real-world datasets with positive results.

Abstract

Multi-label learning (MLL) has gained attention for its ability to represent real-world data. Label Distribution Learning (LDL), an extension of MLL to learning from label distributions, faces challenges in collecting accurate label distributions. To address the issue of biased annotations, based on the low-rank assumption, existing works recover true distributions from biased observations by exploring the label correlations. However, recent evidence shows that the label distribution tends to be full-rank, and naive apply of low-rank approximation on biased observation leads to inaccurate recovery and performance degradation. In this paper, we address the LDL with biased annotations problem from a novel perspective, where we first degenerate the soft label distribution into a hard multi-hot label and then recover the true label information for each instance. This idea stems from an insight that assigning hard multi-hot labels is often easier than assigning a soft label distribution, and it shows stronger immunity to noise disturbances, leading to smaller label bias. Moreover, assuming that the multi-label space for predicting label distributions is low-rank offers a more reasonable approach to capturing label correlations. Theoretical analysis and experiments confirm the effectiveness and robustness of our method on real-world datasets.