CC-Loss: Channel Correlation Loss For Image Classification

TL;DR

This paper introduces CC-Loss, a novel loss function that leverages channel correlation and attention mechanisms to improve feature discriminability in image classification, outperforming existing loss functions across multiple datasets.

Contribution

The paper proposes CC-Loss, which incorporates channel correlation constraints and attention modules to enhance intra-class compactness and inter-class separability in deep learning models.

Findings

CC-Loss improves classification accuracy over state-of-the-art loss functions.

The method enhances intra-class compactness and inter-class separability.

Experimental results on three datasets validate the effectiveness of CC-Loss.

Abstract

The loss function is a key component in deep learning models. A commonly used loss function for classification is the cross entropy loss, which is a simple yet effective application of information theory for classification problems. Based on this loss, many other loss functions have been proposed,~\emph{e.g.}, by adding intra-class and inter-class constraints to enhance the discriminative ability of the learned features. However, these loss functions fail to consider the connections between the feature distribution and the model structure. Aiming at addressing this problem, we propose a channel correlation loss (CC-Loss) that is able to constrain the specific relations between classes and channels as well as maintain the intra-class and the inter-class separability. CC-Loss uses a channel attention module to generate channel attention of features for each sample in the training stage. Next, an Euclidean distance matrix is calculated to make the channel attention vectors associated with the same class become identical and to increase the difference between different classes. Finally, we obtain a feature embedding with good intra-class compactness and inter-class separability.Experimental results show that two different backbone models trained with the proposed CC-Loss outperform the state-of-the-art loss functions on three image classification datasets.