共 50 条
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