Open access
2026
Boosting Lightweight CNN-Based Networks Via Selective Residual Attentive Patterns for Image Recognition
A simple fusion of two novel components of residual attentive information forms a robust volume of selective residual attentive patterns (named SRAP), which boosted the performance of lightweight CNN-based networks by up to ~7% on ImageNet-100 without increasing the computational complexity.
Thanh Tuan Nguyen, H. Pham, Thinh Le Vinh et al.
· IEEE Access · 0 citations