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] Entropy regularization for weakly supervised object localization
    Hwang, Dongjun
    Ha, Jung-Woo
    Shim, Hyunjung
    Choe, Junsuk
    PATTERN RECOGNITION LETTERS, 2023, 169 : 1 - 7
  • [42] Pseudo-Label-Free Weakly Supervised Semantic Segmentation Using Image Masking
    Kim, Sangtae
    Luong Trung Nguyen
    Shim, Kyuhong
    Kim, Junhan
    Shim, Byonghyo
    IEEE ACCESS, 2022, 10 : 19401 - 19411
  • [43] Discovering an inference recipe for weakly-supervised object localization
    Lee, Sanghuk
    Mun, Cheolhyun
    Uh, Youngjung
    Choe, Junsuk
    Byun, Hyeran
    PATTERN RECOGNITION, 2024, 156
  • [44] Competing for Pixels: A Self-Play Algorithm for Weakly-Supervised Semantic Segmentation
    Saeed, Shaheer U.
    Huang, Shiqi
    Ramalhinho, Joao
    Gayo, Iani J. M. B.
    Montana-Brown, Nina
    Bonmati, Ester
    Pereira, Stephen P.
    Davidson, Brian
    Barratt, Dean C.
    Clarkson, Matthew J.
    Hu, Yipeng
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2025, 47 (02) : 825 - 839
  • [45] Boat in the Sky: Background Decoupling and Object-aware Pooling for Weakly Supervised Semantic Segmentation
    Xu, Jianjun
    Xie, Hongtao
    Xu, Hai
    Wang, Yuxin
    Liu, Sun-ao
    Zhang, Yongdong
    PROCEEDINGS OF THE 30TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA, MM 2022, 2022, : 5783 - 5792
  • [46] Dense Supervised Dual-Aware Contrastive Learning for Airborne Laser Scanning Weakly Supervised Semantic Segmentation
    Luo, Ziwei
    Zeng, Tao
    Jiang, Xinyi
    Peng, Qingyu
    Ma, Ying
    Xie, Zhong
    Pan, Xiong
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2025, 63
  • [47] Enhanced Pseudo-Label Generation With Self-Supervised Training for Weakly- Supervised Semantic Segmentation
    Qin, Zhen
    Chen, Yujie
    Zhu, Guosong
    Zhou, Erqiang
    Zhou, Yingjie
    Zhou, Yicong
    Zhu, Ce
    IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2024, 34 (08) : 7017 - 7028
  • [48] A Survey of Weakly -supervised Semantic Segmentation
    Zhu, Kaiyin
    Xiong, Neal N.
    Lu, Mingming
    2023 IEEE 9TH INTL CONFERENCE ON BIG DATA SECURITY ON CLOUD, BIGDATASECURITY, IEEE INTL CONFERENCE ON HIGH PERFORMANCE AND SMART COMPUTING, HPSC AND IEEE INTL CONFERENCE ON INTELLIGENT DATA AND SECURITY, IDS, 2023, : 10 - 15
  • [49] HiCT: Hierarchical Comprehend of Transformer for Weakly Supervised Object Localization
    Sun, Wanchun
    Feng, Xin
    Ma, Hui
    Liu, Jingyao
    IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2023, 72
  • [50] Rethinking the Localization in Weakly Supervised Object Localization
    Xu, Rui
    Luo, Yong
    Hu, Han
    Du, Bo
    Shen, Jialie
    Wen, Yonggang
    PROCEEDINGS OF THE 31ST ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA, MM 2023, 2023, : 5484 - 5494