Double Shot: Preserve and Erase Based Class Attention Networks for Weakly Supervised Localization (Peca-Net)

Weakly supervised localization has attracted increasing attention since only image-wise labels are needed. One mainstream approach, CAM based top-down localization method, suffers from poor resolution and localizing only the most discriminative regions. Another kind, model agnostic perturbation based method, suffers from multiple iterations for each sample. In this paper, we introduce PECA-Net: Preserve and Erase Based Class Attention Networks, which adopts preserve and erase perturbed U-net as the basis, with class activation mechanism as attention to enhance localization capability. Class attention module strengthens informative features and achieves a basic localization. Preserve and erase perturbed U-net replaces the random and iterative extrinsic perturbation with meaningful erasing. In addition, this structure refines the preliminary localization. Since the target object is hit twice, therefore, entitled as double shot. Experiments validate that localization error of both CUB-200 and ILSVRC ImageNet dataset is the new state-of-the-art.