End-to-End Supervised Multilabel Contrastive Learning

TL;DR

This paper introduces KMCL, an end-to-end multilabel contrastive learning framework that effectively models label dependencies and data imbalance, demonstrating consistent improvements over state-of-the-art methods in image classification.

Contribution

The paper proposes KMCL, a novel end-to-end training framework that combines kernel-based feature transformation with multiple loss functions to address multilabel learning challenges.

Findings

KMCL outperforms SOTA methods on image classification tasks.

The framework effectively models label correlations and data imbalance.

It maintains low computational complexity.

Abstract

Multilabel representation learning is recognized as a challenging problem that can be associated with either label dependencies between object categories or data-related issues such as the inherent imbalance of positive/negative samples. Recent advances address these challenges from model- and data-centric viewpoints. In model-centric, the label correlation is obtained by an external model designs (e.g., graph CNN) to incorporate an inductive bias for training. However, they fail to design an end-to-end training framework, leading to high computational complexity. On the contrary, in data-centric, the realistic nature of the dataset is considered for improving the classification while ignoring the label dependencies. In this paper, we propose a new end-to-end training framework -- dubbed KMCL (Kernel-based Mutlilabel Contrastive Learning) -- to address the shortcomings of both model- and data-centric designs. The KMCL first transforms the embedded features into a mixture of exponential kernels in Gaussian RKHS. It is then followed by encoding an objective loss that is comprised of (a) reconstruction loss to reconstruct kernel representation, (b) asymmetric classification loss to address the inherent imbalance problem, and (c) contrastive loss to capture label correlation. The KMCL models the uncertainty of the feature encoder while maintaining a low computational footprint. Extensive experiments are conducted on image classification tasks to showcase the consistent improvements of KMCL over the SOTA methods. PyTorch implementation is provided in \url{https://github.com/mahdihosseini/KMCL}.