CC-Loss: Channel Correlation Loss For Image Classification

by   Zeyu Song, et al.

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, 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.


page 1

page 2

page 3

page 4


A New Loss Function for CNN Classifier Based on Pre-defined Evenly-Distributed Class Centroids

With the development of convolutional neural networks (CNNs) in recent y...

On the Separability of Classes with the Cross-Entropy Loss Function

In this paper, we focus on the separability of classes with the cross-en...

σ^2R Loss: a Weighted Loss by Multiplicative Factors using Sigmoidal Functions

In neural networks, the loss function represents the core of the learnin...

Intra-Class Uncertainty Loss Function for Classification

Most classification models can be considered as the process of matching ...

Redesigning the classification layer by randomizing the class representation vectors

Neural image classification models typically consist of two components. ...

Steganalysis of Image with Adaptively Parametric Activation

Steganalysis as a method to detect whether image contains se-cret messag...

Anchor-based Nearest Class Mean Loss for Convolutional Neural Networks

Discriminative features are critical for machine learning applications. ...

Please sign up or login with your details

Forgot password? Click here to reset