CAM: compound attention module for improved vision models

Houhong Liu; Fei Tan; Zhengmiao Du

doi:10.1117/12.3050534

24 October 2024 CAM: compound attention module for improved vision models

Houhong Liu, Fei Tan, Zhengmiao Du

Proceedings Volume 13396, Third International Conference on Image Processing, Object Detection, and Tracking (IPODT 2024); 1339608 (2024) https://doi.org/10.1117/12.3050534
Event: 3rd International Conference on Image Processing, Object Detection and Tracking (IPODT24), 2024, Nanjing, China

Abstract

In recent years, the attention mechanism has played a significant role in enhancing algorithm performance in deep learning-based visual tasks. Most methods focus on developing more complex attention mechanisms to improve network performance, which inevitably increases the computational complexity of the model. To balance performance and computational complexity, this paper proposes the CAM (Compound Attention Module) attention mechanism, which delivers substantial performance improvements with only a slight increase in parameters. The CAM module operates in two dimensions: space and channel. It is a lightweight, plug-and-play module with minimal computational overhead. We validate our CAM module through extensive experiments on image classification and object detection tasks using the CIFAR-100 and VisDrone2019 datasets. Experimental results demonstrate that the model consistently improves image classification and object detection performance, outperforming similar modules.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Houhong Liu, Fei Tan, and Zhengmiao Du "CAM: compound attention module for improved vision models", Proc. SPIE 13396, Third International Conference on Image Processing, Object Detection, and Tracking (IPODT 2024), 1339608 (24 October 2024); https://doi.org/10.1117/12.3050534

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