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
  • [1] Background Activation Suppression for Weakly Supervised Object Localization and Semantic Segmentation
    Wei Zhai
    Pingyu Wu
    Kai Zhu
    Yang Cao
    Feng Wu
    Zheng-Jun Zha
    International Journal of Computer Vision, 2024, 132 (3) : 750 - 775
  • [2] Background Activation Suppression for Weakly Supervised Object Localization and Semantic Segmentation
    Zhai, Wei
    Wu, Pingyu
    Zhu, Kai
    Cao, Yang
    Wu, Feng
    Zha, Zheng-Jun
    INTERNATIONAL JOURNAL OF COMPUTER VISION, 2024, 132 (03) : 750 - 775
  • [3] From Weakly Supervised Object Localization to Semantic Segmentation by Probabilistic Image Modeling
    Wilhelm, Thorsten
    Grzeszick, Rene
    Fink, Gernot A.
    Woehler, Christian
    2017 INTERNATIONAL CONFERENCE ON DIGITAL IMAGE COMPUTING - TECHNIQUES AND APPLICATIONS (DICTA), 2017, : 119 - 125
  • [4] Contrastive and consistent feature learning for weakly supervised object localization and semantic segmentation
    Ki, Minsong
    Uh, Youngjung
    Lee, Wonyoung
    Byun, Hyeran
    NEUROCOMPUTING, 2021, 445 : 244 - 254
  • [5] Weakly supervised object localization and segmentation in videos
    Rochan, Mrigank
    Rahman, Shafin
    Bruce, Neil D. B.
    Wang, Yang
    IMAGE AND VISION COMPUTING, 2016, 56 : 1 - 12
  • [6] Attention-Based Dropout Layer for Weakly Supervised Single Object Localization and Semantic Segmentation
    Choe, Junsuk
    Lee, Seungho
    Shim, Hyunjung
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2021, 43 (12) : 4256 - 4271
  • [7] 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
  • [8] 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
  • [9] Towards Noiseless Object Contours for Weakly Supervised Semantic Segmentation
    Li, Jing
    Fan, Junsong
    Zhang, Zhaoxiang
    2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022), 2022, : 16835 - 16844
  • [10] Expansion and Shrinkage of Localization for Weakly-Supervised Semantic Segmentation
    Li, Jinlong
    Jie, Zequn
    Wang, Xu
    Wei, Xiaolin
    Ma, Lin
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 35 (NEURIPS 2022), 2022,