RAUM-Net: Regional Attention and Uncertainty-aware Mamba Network
This work addresses the problem of fine-grained visual categorization for computer vision applications, particularly in scenarios with scarce labeled data, representing an incremental improvement over existing methods.
The paper tackles the challenge of Fine Grained Visual Categorization (FGVC) with limited labeled data by proposing a semi-supervised method that combines Mamba-based feature modeling, region attention, and Bayesian uncertainty, resulting in strong performance on benchmarks with occlusions.
Fine Grained Visual Categorization (FGVC) remains a challenging task in computer vision due to subtle inter class differences and fragile feature representations. Existing methods struggle in fine grained scenarios, especially when labeled data is scarce. We propose a semi supervised method combining Mamba based feature modeling, region attention, and Bayesian uncertainty. Our approach enhances local to global feature modeling while focusing on key areas during learning. Bayesian inference selects high quality pseudo labels for stability. Experiments show strong performance on FGVC benchmarks with occlusions, demonstrating robustness when labeled data is limited. Code is available at https://github.com/wxqnl/RAUM Net.