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
  • [31] Weakly Supervised Semantic Segmentation of Satellite Images
    Nivaggioli, Adrien
    Randrianarivo, Hicham
    2019 JOINT URBAN REMOTE SENSING EVENT (JURSE), 2019,
  • [32] Weakly-supervised Object Representation Learning for Few-shot Semantic Segmentation
    Ying, Xiaowen
    Li, Xin
    Chuah, Mooi Choo
    2021 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2021), 2021, : 1496 - 1505
  • [33] Weakly Supervised Semantic Segmentation for Social Images
    Zhang, Wei
    Zeng, Sheng
    Wang, Dequan
    Xue, Xiangyang
    2015 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2015, : 2718 - 2726
  • [34] Complementary Patch for Weakly Supervised Semantic Segmentation
    Zhang, Fei
    Gu, Chaochen
    Zhang, Chenyue
    Dai, Yuchao
    2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021), 2021, : 7222 - 7231
  • [35] Weakly Supervised Semantic Segmentation with a Multiscale Model
    Wang, Shuo
    Wang, Yizhou
    IEEE SIGNAL PROCESSING LETTERS, 2015, 22 (03) : 308 - 312
  • [36] Adversarial Decoupling for Weakly Supervised Semantic Segmentation
    Sun, Guoying
    Yang, Meng
    Luo, Wenfeng
    PATTERN RECOGNITION AND COMPUTER VISION, PT IV, 2021, 13022 : 188 - 200
  • [37] 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
  • [38] Semi-supervised Domain Adaptation for Weakly Labeled Semantic Video Object Segmentation
    Wang, Huiling
    Raiko, Tapani
    Lensu, Lasse
    Wang, Tinghuai
    Karhunen, Juha
    COMPUTER VISION - ACCV 2016, PT I, 2017, 10111 : 163 - 179
  • [39] WegFormer : Transformers for weakly supervised semantic segmentation
    Liu, Chunmeng
    Li, Guangyao
    EXPERT SYSTEMS, 2024, 41 (03)
  • [40] Semantic-Aware Superpixel for Weakly Supervised Semantic Segmentation
    Kim, Sangtae
    Park, Daeyoung
    Shim, Byonghyo
    THIRTY-SEVENTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 37 NO 1, 2023, : 1142 - 1150