CFBoost: Capacity-Boosting Feature Augmentation via Spatial-Geometrical Coordination

Fine-grained image classification constitutes a long-standing challenge, with its performance bottlenecks stemming primarily from high inter-class similarity and insufficient discriminative feature. Feature augmentation alleviates this constraint through cross-image feature fusion, and as an online augmentation approach, integrates seamlessly into network architectures without requiring independent training phases. However, existing methods typically exhibit either random region selection mechanisms or constrained spatial awareness. Such inherent shortcomings critically constrain their ability to generate adequately capacity discriminative feature necessary for fine-grained classification. To this end, we propose CFBoost, a feature augmentation method that incorporates spatial-geometrical coordination to generate diverse features with sufficient capacity. It adaptively modulates spatial-geometric properties within fusion regions while simultaneously constructing feature-capacity-aware semantic labels. CFBoost integrates three core strategies: precisely locating fusion regions and positions to prevent occlusion of essential features, independently smoothing edges in all orientations of the fusion region to mitigate strong edge effects, and generating soft labels from a semantic weight matrix to improve the representational capacity of sample labels. Experiments across four benchmark datasets demonstrate CFBoost's superiority, achieving an average improvement of 2.48% relative to the optimal baseline, with particularly pronounced performance gains on images containing dispersed high-capacity regions.