Concentration Distribution Learning from Label Distributions

TL;DR

This paper introduces a new concept called background concentration to enhance label distribution learning by capturing absolute label intensities, leading to more accurate predictions and better handling of hidden labels.

Contribution

It proposes a novel concentration distribution learning paradigm and a neural network-based model to learn background concentrations, improving upon existing LDL methods.

Findings

The approach effectively extracts background concentrations from label distributions.

The method achieves more accurate predictions than state-of-the-art LDL techniques.

Experiments demonstrate the model's ability to handle hidden labels better.

Abstract

Label distribution learning (LDL) is an effective method to predict the relative label description degree (a.k.a. label distribution) of a sample. However, the label distribution is not a complete representation of an instance because it overlooks the absolute intensity of each label. Specifically, it's impossible to obtain the total description degree of hidden labels that not in the label space, which leads to the loss of information and confusion in instances. To solve the above problem, we come up with a new concept named background concentration to serve as the absolute description degree term of the label distribution and introduce it into the LDL process, forming the improved paradigm of concentration distribution learning. Moreover, we propose a novel model by probabilistic methods and neural networks to learn label distributions and background concentrations from existing LDL datasets. Extensive experiments prove that the proposed approach is able to extract background concentrations from label distributions while producing more accurate prediction results than the state-of-the-art LDL methods. The code is available in https://github.com/seutjw/CDL-LD.