用区域注意力与不确定性感知提升小样本细粒度图像分类
RAUM-Net: Regional Attention and Uncertainty-aware Mamba Network
- 结合Mamba架构与区域注意力，增强局部到全局特征建模
- 通过贝叶斯推断筛选高质量伪标签，提升小样本下稳定性
- 在遮挡场景下仍保持鲁棒，适合数据稀缺的细粒度识别任务
细粒度视觉分类（FGVC）因类间差异细微、特征表示脆弱而极具挑战，尤其在标注数据稀缺时现有方法表现不佳。本文提出一种半监督方法，融合基于Mamba的特征建模、区域注意力与贝叶斯不确定性机制。该方法在学习过程中聚焦关键区域，强化从局部到全局的特征表达。通过贝叶斯推理选择高质量伪标签，提升训练稳定性。实验表明，在存在遮挡的FGVC基准测试中表现优异，验证了其在标注数据有限下的强鲁棒性。代码已开源：https://github.com/wxqnl/RAUM-Net。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。