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
  • [21] Survey of Weakly Supervised Semantic Segmentation Methods
    Lu, Zheng
    Chen, Dali
    Xue, Dingyu
    PROCEEDINGS OF THE 30TH CHINESE CONTROL AND DECISION CONFERENCE (2018 CCDC), 2018, : 1176 - 1180
  • [22] Branches Mutual Promotion for End-to-End Weakly Supervised Semantic Segmentation
    Zhu, Lei
    Zhang, Xinliang
    He, Hangzhou
    Chen, Qian
    Li, Sha
    Zeng, Shuang
    Zhang, Yibao
    Ren, Qiushi
    Lu, Yanye
    IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2024,
  • [23] Modeling the Background for Incremental and Weakly-Supervised Semantic Segmentation
    Cermelli, Fabio
    Mancini, Massimiliano
    Bulo, Samuel Rota
    Ricci, Elisa
    Caputo, Barbara
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2022, 44 (12) : 10099 - 10113
  • [24] SAL:Selection and Attention Losses for Weakly Supervised Semantic Segmentation
    Zhou, Lei
    Gong, Chen
    Liu, Zhi
    Fu, Keren
    IEEE TRANSACTIONS ON MULTIMEDIA, 2021, 23 : 1035 - 1048
  • [25] Adaptive Generation of Weakly Supervised Semantic Segmentation for Object Detection
    Shibao Li
    Yixuan Liu
    Yunwu Zhang
    Yi Luo
    Jianhang Liu
    Neural Processing Letters, 2023, 55 : 657 - 670
  • [26] Adaptive Generation of Weakly Supervised Semantic Segmentation for Object Detection
    Li, Shibao
    Liu, Yixuan
    Zhang, Yunwu
    Luo, Yi
    Liu, Jianhang
    NEURAL PROCESSING LETTERS, 2023, 55 (01) : 657 - 670
  • [27] Memory-Based Cross-Image Contexts for Weakly Supervised Semantic Segmentation
    Fan, Junsong
    Zhang, Zhaoxiang
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2023, 45 (05) : 6006 - 6020
  • [28] Superpixel Guided Network for Weakly Supervised Semantic Segmentation
    Xie, Zhaozhi
    Jiang, Weihao
    Yang, Yuwen
    Lu, Hongtao
    IEEE SIGNAL PROCESSING LETTERS, 2024, 31 : 2885 - 2889
  • [29] Weakly Supervised Learning for Point Cloud Semantic Segmentation With Dual Teacher
    Yao, Baochen
    Xiao, Hui
    Zhuang, Jiayan
    Peng, Chengbin
    IEEE ROBOTICS AND AUTOMATION LETTERS, 2023, 8 (10) : 6347 - 6354
  • [30] Segmentation from localization: a weakly supervised semantic segmentation method for resegmenting CAM
    Jiang, Jingjing
    Wang, Hongxia
    Wu, Jiali
    Liu, Chun
    MULTIMEDIA TOOLS AND APPLICATIONS, 2023, 83 (19) : 57785 - 57810