A Progressive Gated Attention Model for Fine-Grained Visual Classification

Fine-grained image classification has been a hot research topic in computer vision, pattern recognition, and other fields in recent years. Most existing fine-grained methods use a single attention mechanism or multiple sub-networks to zoom in and find distinguishable local feature regions. These models seldom explore the intrinsic connections between cross-layer features with similar semantic features. This tends to show erratic performance in images with complex backgrounds. To this end, we propose a method focusing on cross-layer feature-context relations. In our method, propose a learning method based on feature channel weights and pyramid patterns, which can increase the diversity of global feature information. Second, we employ cross-layer attention, which can find key target regions. Finally, we propose a cross-gated attention mechanism that can find rich discriminative features from key regions of images. Experiments show that the proposed model performs well on three datasets: CUB-200-2011, Stanford Cars, and FGVC Aircraft.