Hierarchical complementary learning for weakly supervised object localization

Sabrina Narimene Benassou, Wuzhen Shi, Feng Jiang, Abdallah Benzine

Abstract: Highlights•Weakly supervised object localization aims to localize objects using image labels.•HCLNet hierarchically generates different class activation maps, and fuses them.•The addition strategy and the l1<math><msub is="true"><mrow is="true"><mi is="true">l</mi></mrow><mrow is="true"><mn is="true">1</mn></mrow></msub></math>-norm strategy have been introduced to fuse the CAMs.•Extensive experiments show that HCLNet achieves a new state-of-the-art performance.