Log In Sign Up

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

by   Qiuyu Zhu, et al.

With the development of convolutional neural networks (CNNs) in recent years, the network structure has become more and more complex and varied, and has achieved very good results in pattern recognition, image classification, object detection and tracking. For CNNs used for image classification, in addition to the network structure, more and more research is now focusing on the improvement of the loss function, so as to enlarge the inter-class feature differences, and reduce the intra-class feature variations as soon as possible. Besides the traditional Softmax, typical loss functions include L-Softmax, AM-Softmax, ArcFace, and Center loss, etc. Based on the concept of predefined evenly-distributed class centroids (PEDCC) in CSAE network, this paper proposes a PEDCC-based loss function called PEDCC-Loss, which can make the inter-class distance maximal and intra-class distance small enough in hidden feature space. Multiple experiments on image classification and face recognition have proved that our method achieve the best recognition accuracy, and network training is stable and easy to converge.


page 1

page 2

page 3

page 4


Git Loss for Deep Face Recognition

Convolutional Neural Networks (CNNs) have been widely used in computer v...

CC-Loss: Channel Correlation Loss For Image Classification

The loss function is a key component in deep learning models. A commonly...

Vehicle Re-identification Based on Dual Distance Center Loss

Recently, deep learning has been widely used in the field of vehicle re-...

Mixture separability loss in a deep convolutional network for image classification

In machine learning, the cost function is crucial because it measures ho...

Boosting Network Weight Separability via Feed-Backward Reconstruction

This paper proposes a new evaluation metric and boosting method for weig...

Robust Classification with Convolutional Prototype Learning

Convolutional neural networks (CNNs) have been widely used for image cla...

Contraction Mapping of Feature Norms for Classifier Learning on the Data with Different Quality

The popular softmax loss and its recent extensions have achieved great s...