Angular joint loss for image classification

Hao Ai; Qingmin Liao

doi:10.1117/12.2601016

30 June 2021 Angular joint loss for image classification

Hao Ai, Qingmin Liao

Proceedings Volume 11878, Thirteenth International Conference on Digital Image Processing (ICDIP 2021); 118780X (2021) https://doi.org/10.1117/12.2601016
Event: Thirteenth International Conference on Digital Image Processing, 2021, Singapore, Singapore

Abstract

Current CNN-based deep feature learning methods for image classification are mainly focused on learning with two types of loss functions: the softmax loss and its variants with class-level labels, or the metric-learning losses with pairwise labels. The former regards the weight vectors of the last fully connected layer of CNNs as representations of the class centres and focuses on the similarity between a single feature and each weight vector. The latter aims at seeking appropriate distance metrics between features pairs to boost the CNNs by learning a discriminative embedding space. In this work, we propose a simple yet effective new loss function called angular joint loss (AJL) to exploit the best of both worlds. By integrating feature-weight angles with feature-feature angles, AJL inherits the simplicity of softmax loss and the power of pair-wise metric learning and enhances both the intra-class compactness and the inter-class separability. The proposed AJL is simple to implement and has no time-consuming mining of pair or triple samples. On some popular image classification datasets (CIFAR-10, CIFAR-100 and ImageNet), extensive experimental results show that the proposed AJL can achieve the state-of-the-art performance.

Citation Download Citation

Hao Ai and Qingmin Liao "Angular joint loss for image classification", Proc. SPIE 11878, Thirteenth International Conference on Digital Image Processing (ICDIP 2021), 118780X (30 June 2021); https://doi.org/10.1117/12.2601016

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available