Wild animal recognition based on effective-class-balanced softmax loss

Wen Chen; Qianzhou Cai; Jin Hou; Jindong Zhang; Bochuan Zheng

doi:10.1117/12.2667361

28 March 2023 Wild animal recognition based on effective-class-balanced softmax loss

Wen Chen, Qianzhou Cai, Jin Hou, Jindong Zhang, Bochuan Zheng

Proceedings Volume 12566, Fifth International Conference on Computer Information Science and Artificial Intelligence (CISAI 2022); 125662I (2023) https://doi.org/10.1117/12.2667361
Event: Fifth International Conference on Computer Information Science and Artificial Intelligence (CISAI 2022), 2022, Chongqing, China

Abstract

Wild animal recognition is important for wild animal protection. Because the number of different wild animals is different in the wild. The wild animal image dataset collected in field by using camera trap is a typical long tail dataset. This paper proposes an Effective-Class-Balanced Softmax Loss (ECBSL) to solve the long tail problem of self-built wild animal dataset. Firstly, a new cross entropy loss function is obtained by using pointwise mutual information instead of conditional probability for modeling. Then the improved effective number of samples calculation method is used to approximately calculate the prior probability distribution of different animal species. Finally, the effectiveness of ECBSL is proved by experiments. Experiments on the self-built wild animal dataset show that the proposed method improves the recognition accuracy of the tail classes and the whole dataset. The comparison experiments with other methods show that the proposed method is superior to other methods.

Citation Download Citation

Wen Chen, Qianzhou Cai, Jin Hou, Jindong Zhang, and Bochuan Zheng "Wild animal recognition based on effective-class-balanced softmax loss", Proc. SPIE 12566, Fifth International Conference on Computer Information Science and Artificial Intelligence (CISAI 2022), 125662I (28 March 2023); https://doi.org/10.1117/12.2667361

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

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
8 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Animals

Head

Cameras

Deep convolutional neural networks

Infrared cameras

Detection and tracking algorithms

Neural networks

Keywords/Phrases

Search In:

Publication Years