2022
DOI: 10.1007/978-3-031-20080-9_11
|View full text |Cite
|
Sign up to set email alerts
|

Bagging Regional Classification Activation Maps for Weakly Supervised Object Localization

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
4
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
5
1
1

Relationship

0
7

Authors

Journals

citations
Cited by 14 publications
(4 citation statements)
references
References 35 publications
0
4
0
Order By: Relevance
“…Table 2 shows the performance of our method and the state-of-the-art weakly supervised object localization methods, including FAM [33], CREAM [49], BGC [24], BAS [47], DAOL [61], BagCAM [60], TS-CAM [15], LCTR [10], ViTOL [18], and SCM [2] on CUB-200-2011 and ImageNet-1K datasets. We also compare our method with PSOL [53] and C 2 AM [48] which are self-supervised methods.…”
Section: Resultsmentioning
confidence: 99%
See 2 more Smart Citations
“…Table 2 shows the performance of our method and the state-of-the-art weakly supervised object localization methods, including FAM [33], CREAM [49], BGC [24], BAS [47], DAOL [61], BagCAM [60], TS-CAM [15], LCTR [10], ViTOL [18], and SCM [2] on CUB-200-2011 and ImageNet-1K datasets. We also compare our method with PSOL [53] and C 2 AM [48] which are self-supervised methods.…”
Section: Resultsmentioning
confidence: 99%
“…We present the results of both supervised and self-supervised pre-trained models in Table 10. Interestingly, we found that [60] ResNet50 84.88 69.97 ViTOL '22 [18] ViT-S 73.17 70.47 SCM '22 [2] ViT-S 89.90 -Self-supervised methods C 2 AM '22 [48] ResNet50 the results of the supervised model were inferior to those of the self-supervised model. This disparity can be linked to a wellestablished challenge in object localization with class-level supervision [13,27,46].…”
Section: Advantage Of Ssl Pre-trained Backbonementioning
confidence: 86%
See 1 more Smart Citation
“…This method is also cost-intensive as CAMs must be averaged from different classes. To overcome this limitation, [43,44] proposes a method to suppress the background regions to help the network identify foreground regions with high confidence.…”
Section: Related Workmentioning
confidence: 99%