提升弱监督学习中物体区域定位精度，让激活图更完整贴合物体边界。
Region-CAM: Towards Accurate Object Regions in Class Activation Maps for Weakly Supervised Learning Tasks
- 通过语义信息传播机制，融合多阶段梯度与特征生成激活图。
- 在PASCAL VOC上达到60.12%和58.43%的mIoU，较原始CAM提升13.61%以上。
- 适合需要精确物体边界定位的弱监督分割与目标定位任务。
类激活映射（CAM）方法因能突出目标物体区域，在弱监督学习中广泛应用。然而传统CAM仅聚焦最显著区域，常无法覆盖完整物体且与边界错位，制约了下游任务性能，尤其在弱监督语义分割（WSSS）中表现受限。为此，本文提出新方法Region-CAM。不同于仅依赖网络特征权重的思路，Region-CAM通过提取语义信息图（SIMs），并结合各阶段模型的梯度与特征进行语义信息传播（SIP），实现更完整、边界更精确的激活图。在PASCAL VOC训练与验证集上，Region-CAM分别取得60.12%与58.43%的均交并比（mIoU），相比原始CAM（46.51%、45.30%）提升13.61%与13.13%；在MS COCO验证集上达36.38%，较原始CAM（20.15%）提升16.23%。此外，在ILSVRC2012验证集上，其Top-1定位准确率达51.7%，优于LayerCAM的4.5%。
原文摘要 · Abstract (English)
Class Activation Mapping (CAM) methods are widely applied in weakly supervised learning tasks due to their ability to highlight object regions. However, conventional CAM methods highlight only the most discriminative regions of the target. These highlighted regions often fail to cover the entire object and are frequently misaligned with object boundaries, thereby limiting the performance of downstream weakly supervised learning tasks, particularly Weakly Supervised Semantic Segmentation (WSSS), which demands pixel-wise accurate activation maps to get the best results. To alleviate the above problems, we propose a novel activation method, Region-CAM. Distinct from network feature weighting approaches, Region-CAM generates activation maps by extracting semantic information maps (SIMs) and performing semantic information propagation (SIP) by considering both gradients and features in each of the stages of the baseline classification model. Our approach highlights a greater proportion of object regions while ensuring activation maps to have precise boundaries that align closely with object edges. Region-CAM achieves 60.12% and 58.43% mean intersection over union (mIoU) using the baseline model on the PASCAL VOC training and validation datasets, respectively, which are improvements of 13.61% and 13.13% over the original CAM (46.51% and 45.30%). On the MS COCO validation set, Region-CAM achieves 36.38%, a 16.23% improvement over the original CAM (20.15%). We also demonstrate the superiority of Region-CAM in object localization tasks, using the ILSVRC2012 validation set. Region-CAM achieves 51.7% in Top-1 Localization accuracy Loc1. Compared with LayerCAM, an activation method designed for weakly supervised object localization, Region-CAM achieves 4.5% better performance in Loc1.
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。