2017
DOI: 10.48550/arxiv.1701.00352
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

Weakly Supervised Semantic Segmentation using Web-Crawled Videos

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

0
12
0

Year Published

2017
2017
2021
2021

Publication Types

Select...
5
3

Relationship

0
8

Authors

Journals

citations
Cited by 18 publications
(12 citation statements)
references
References 26 publications
0
12
0
Order By: Relevance
“…Our method also significantly outperforms methods based on additional supervision except AISI [11]. These methods include TransferNet [9], which was trained on pixel-level annotations of 60 classes (not Pascal VOC classes) of COCO [20] images, and CrawlSeg [10], which Table 3. Comparison of semi-supervised semantic segmentation methods on VOC 2012 validation sets.…”
Section: Training Val Testmentioning
confidence: 98%
See 1 more Smart Citation
“…Our method also significantly outperforms methods based on additional supervision except AISI [11]. These methods include TransferNet [9], which was trained on pixel-level annotations of 60 classes (not Pascal VOC classes) of COCO [20] images, and CrawlSeg [10], which Table 3. Comparison of semi-supervised semantic segmentation methods on VOC 2012 validation sets.…”
Section: Training Val Testmentioning
confidence: 98%
“…Supervision: Image-level and additional annotations MIL-seg CVPR '15 [23] 700K 42.0 40.6 STC TPAMI '17 [32] 50K 49.8 51.2 TransferNet CVPR '16 [9] 70K 52.1 51.2 CrawlSeg CVPR '17 [10] 970K 58.1 58.7 AISI ECCV '18 [11] 11K 61.3 62.1…”
Section: Training Val Testmentioning
confidence: 99%
“…In this context [16,50] work in the even more constrained scenario, where only two classes are considered: foreground vs. background. By contrast, to differentiate multiple foreground classes, but still assuming a single background, [35] relied on motion cues and [17] made use of a huge amount of web-crawled data (4606 videos with 960,517 frames).…”
Section: Related Workmentioning
confidence: 99%
“…Weak Supervision. Weakly supervised learning has been extensively used for various problems in computer vision such as semantic segmentation [73,74,75,76,77,78], object localization [79,80,81,82], saliency detection [83,84], scene recognition [85,86] and many more. However, this form of learning has been relatively unexplored for crowd counting.…”
Section: Related Workmentioning
confidence: 99%