Anti-Adversarially Manipulated Attributions for Weakly Supervised Semantic Segmentation and Object Localization

被引:10
|
作者
Lee, Jungbeom [1 ]
Kim, Eunji [1 ]
Mok, Jisoo [1 ]
Yoon, Sungroh [1 ,2 ,3 ]
机构
[1] Seoul Natl Univ, Dept Elect & Comp Engn, Seoul 08826, South Korea
[2] Seoul Natl Univ, Interdisciplinary Program AI, AIIS, ASRI,INMC, Seoul 08826, South Korea
[3] Seoul Natl Univ, ISRC, Seoul 08826, South Korea
关键词
Semantics; Location awareness; Image segmentation; Annotations; Training; Perturbation methods; Artificial neural networks; Weakly supervised learning; semi-supervised learning; semantic segmentation; object localization;
D O I
10.1109/TPAMI.2022.3166916
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Obtaining accurate pixel-level localization from class labels is a crucial process in weakly supervised semantic segmentation and object localization. Attribution maps from a trained classifier are widely used to provide pixel-level localization, but their focus tends to be restricted to a small discriminative region of the target object. An AdvCAM is an attribution map of an image that is manipulated to increase the classification score produced by a classifier before the final softmax or sigmoid layer. This manipulation is realized in an anti-adversarial manner, so that the original image is perturbed along pixel gradients in directions opposite to those used in an adversarial attack. This process enhances non-discriminative yet class-relevant features, which make an insufficient contribution to previous attribution maps, so that the resulting AdvCAM identifies more regions of the target object. In addition, we introduce a new regularization procedure that inhibits the incorrect attribution of regions unrelated to the target object and the excessive concentration of attributions on a small region of the target object. Our method achieves a new state-of-the-art performance in weakly and semi-supervised semantic segmentation, on both the PASCAL VOC 2012 and MS COCO 2014 datasets. In weakly supervised object localization, it achieves a new state-of-the-art performance on the CUB-200-2011 and ImageNet-1K datasets.
引用
收藏
页码:1618 / 1634
页数:17
相关论文
共 50 条
  • [41] Semantic-Constraint Matching for transformer-based weakly supervised object localization
    Cao, Yiwen
    Su, Yukun
    Wang, Wenjun
    Liu, Yanxia
    Wu, Qingyao
    PATTERN RECOGNITION, 2025, 158
  • [42] Regional Semantic Contrast and Aggregation for Weakly Supervised Semantic Segmentation
    Zhou, Tianfei
    Zhang, Meijie
    Zhao, Fang
    Li, Jianwu
    2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022), 2022, : 4289 - 4299
  • [43] Weakly Supervised Object Detection With Segmentation Collaboration
    Li, Xiaoyan
    Kan, Meina
    Shan, Shiguang
    Chen, Xilin
    2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019), 2019, : 9734 - 9743
  • [44] Weakly Supervised Object Localization Using Long-Range Semantic Foreground Activation
    Wang, Lianxing
    Li, Huaxiong
    2022 26TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2022, : 4580 - 4586
  • [45] Manipulated Face Detection and Localization Based on Semantic Segmentation
    Li, Gen
    Zhao, Xianfeng
    Cao, Yun
    Hu, Chengqiao
    DIGITAL FORENSICS AND WATERMARKING, IWDW 2022, 2023, 13825 : 98 - 113
  • [46] Weakly Supervised Object Localization with Stable Segmentations
    Galleguillos, Carolina
    Babenko, Boris
    Rabinovich, Andrew
    Belongie, Serge
    COMPUTER VISION - ECCV 2008, PT I, PROCEEDINGS, 2008, 5302 : 193 - 207
  • [47] Weakly Supervised Object Localization as Domain Adaption
    Zhu, Lei
    She, Qi
    Chen, Qian
    You, Yunfei
    Wang, Boyu
    Lu, Yanye
    2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022), 2022, : 14617 - 14626
  • [48] Adversarial Transformers for Weakly Supervised Object Localization
    Meng, Meng
    Zhang, Tianzhu
    Zhang, Zhe
    Zhang, Yongdong
    Wu, Feng
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2022, 31 : 7130 - 7143
  • [49] Adversarial Transformers for Weakly Supervised Object Localization
    Meng, Meng
    Zhang, Tianzhu
    Zhang, Zhe
    Zhang, Yongdong
    Wu, Feng
    IEEE Transactions on Image Processing, 2022, 31 : 7130 - 7143
  • [50] Weakly Supervised Object Localization and Detection: A Survey
    Zhang, Dingwen
    Han, Junwei
    Cheng, Gong
    Yang, Ming-Hsuan
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2022, 44 (09) : 5866 - 5885