Designing a Lightweight Convolutional Neural Network for Camouflaged Object Detection

• Published in: 2024 IEEE 48th Annual Computers, Software, and Applications Conference (COMPSAC) pp. 179 - 187
• Main Authors: Gonzales, Mark Edward M., Ibrahim, Hans Oswald A., Ong, Elyssia Barrie H., Laguna, Ann Franchesca B.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 02-07-2024
• Subjects: Accuracy; camouflaged object detection; Computational modeling; convolutional neural network (CNN); Graphics processing units; model compression; Neural networks; Performance evaluation; Power demand; pruning; quantization; Quantization (signal)
• ISSN: 2836-3795
• DOI: 10.1109/COMPSAC61105.2024.00034

Camouflaged object detection is a challenging task due to the high visual similarity between the object of interest and its surroundings. While deep learning models have shown promising performance, the size and power requirements of most existing models make them unsuitable for deployment in resource-constrained devices. To alleviate this problem, we modified BGNet, a camouflaged object detection network, by replacing its backbone network Res2Net50 with a lighter neural network model such as EfficientNet and MobileNet. Replacing the backbone network with EfficientNetV2-Medium decreased the model size by 1.53× and GPU power consumption by 1.41×. To further reduce the memory footprint, we benchmarked different pruning and quantization algorithms on the resulting network. Our experiments show that applying l2-norm pruning followed by DoReFa quantization reduced the number of multiply-accumulate operations by 3.71×. Our proposed lightweight camouflaged object detection model performs better than the state-of-the-art BGNet, registering weighted F-measure scores of 0.777, 0.739, and 0.808 on CAMO, COD10K, and NC4K, respectively, compared to BGNet with scores of 0.749, 0.722, and 0.788, while also being lighter and requiring lower power.