Sun Fayou

Work place: Faculty of Information and Communication Technology, Universiti Teknikal Malaysia Melaka, Melaka, Malaysia



Research Interests: Information-Theoretic Security, Network Security, Network Architecture, Information Security, Computer Networks, Computer Vision, Computer systems and computational processes


SUN FAYOU is currently pursuing Ph.D. degree in the Faculty of Information and Communication Technology, Universiti Teknikal Malaysia Melaka. His research interests include computer vision, generative adversarial networks and Information network security.

Author Articles
Combining Multi-Feature Regions for Fine-Grained Image Recognition

By Sun Fayou Hea Choon Ngo Yong Wee Sek

DOI:, Pub. Date: 8 Feb. 2022

Fine-grained visual classification(FGVC) is challenging task duo to the subtle discriminative features.Recently, RA-CNN selects a single feature region of the image, and recursively learns the discriminative features. However, RA-CNN abandons most of feature regions, which is not only the inefficient but aslo ineffective.To address above issues,we design a noval fine-grained visual recognition model MRA-CNN,which associates multi-feature regions.To improve the feature representation,attention blocks are integrated into the backbone to reinforce significant features;To improve the classification accuracy, we design the feature scale dependent(FSD) algorithm to select the optimal outputs as the classifier inputs;To avoid missing features, we adopt the k-means algorithm to select multiple feature regions.We demonstrate the value of MRA-CNN by expensive experiments on three popular fine-grained benchmarks:CUB-200-2011,Cars196 and Aircrafts100 where we achieve state-of-the-art performance.Our codes can be found at

[...] Read more.
Other Articles