Progressive Co-Attention Network for Fine-grained Visual Classification
This addresses the problem of recognizing subtle variations in sub-categories for fine-grained visual classification, but it is incremental as it builds on existing methods by incorporating image pairs.
The paper tackled fine-grained visual classification by proposing a progressive co-attention network (PCA-Net) that uses same-category image pairs to capture common and complementary discriminative features, achieving competitive results on benchmark datasets like CUB-200-2011, Stanford Cars, and FGVC Aircraft.
Fine-grained visual classification aims to recognize images belonging to multiple sub-categories within a same category. It is a challenging task due to the inherently subtle variations among highly-confused categories. Most existing methods only take an individual image as input, which may limit the ability of models to recognize contrastive clues from different images. In this paper, we propose an effective method called progressive co-attention network (PCA-Net) to tackle this problem. Specifically, we calculate the channel-wise similarity by encouraging interaction between the feature channels within same-category image pairs to capture the common discriminative features. Considering that complementary information is also crucial for recognition, we erase the prominent areas enhanced by the channel interaction to force the network to focus on other discriminative regions. The proposed model has achieved competitive results on three fine-grained visual classification benchmark datasets: CUB-200-2011, Stanford Cars, and FGVC Aircraft.