Autor: |
Zhu, Lei, She, Qi, Chen, Qian, Meng, Xiangxi, Geng, Mufeng, Jin, Lujia, Jiang, Zhe, Qiu, Bin, You, Yunfei, Zhang, Yibao, Ren, Qiushi, Lu, Yanye |
Rok vydání: |
2021 |
Předmět: |
|
Druh dokumentu: |
Working Paper |
Popis: |
Weakly supervised object localization (WSOL) relaxes the requirement of dense annotations for object localization by using image-level classification masks to supervise its learning process. However, current WSOL methods suffer from excessive activation of background locations and need post-processing to obtain the localization mask. This paper attributes these issues to the unawareness of background cues, and propose the background-aware classification activation map (B-CAM) to simultaneously learn localization scores of both object and background with only image-level labels. In our B-CAM, two image-level features, aggregated by pixel-level features of potential background and object locations, are used to purify the object feature from the object-related background and to represent the feature of the pure-background sample, respectively. Then based on these two features, both the object classifier and the background classifier are learned to determine the binary object localization mask. Our B-CAM can be trained in end-to-end manner based on a proposed stagger classification loss, which not only improves the objects localization but also suppresses the background activation. Experiments show that our B-CAM outperforms one-stage WSOL methods on the CUB-200, OpenImages and VOC2012 datasets. |
Databáze: |
arXiv |
Externí odkaz: |
|