Comprehensive Attention Self-Distillation for Weakly-Supervised Object Detection Supplementary Material

Bottom: CASD overlaid with attentions. Recall that WSOD conducts classification on object proposals (e.g., bounding boxes generated by Selective Search [ Figure 1 shows both the success and the failure cases of CASD. This could be improved by hard-sample mining in CASD training. This localization advantages of CASD benefit from its learning of comprehensive attention (see the bottom row of Figure 1). CorLoc only evaluates the localization accuracy of detectors.