|
|
|
|
| LEADER |
01000naa a22002652 4500 |
| 001 |
NLM378696459 |
| 003 |
DE-627 |
| 005 |
20241010232953.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
241010s2024 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TPAMI.2024.3476683
|2 doi
|
| 028 |
5 |
2 |
|a pubmed24n1563.xml
|
| 035 |
|
|
|a (DE-627)NLM378696459
|
| 035 |
|
|
|a (NLM)39383082
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Wu, Zhenyu
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a Pixel is All You Need
|b Adversarial Spatio-Temporal Ensemble Active Learning for Salient Object Detection
|
| 264 |
|
1 |
|c 2024
|
| 336 |
|
|
|a Text
|b txt
|2 rdacontent
|
| 337 |
|
|
|a ƒaComputermedien
|b c
|2 rdamedia
|
| 338 |
|
|
|a ƒa Online-Ressource
|b cr
|2 rdacarrier
|
| 500 |
|
|
|a Date Revised 10.10.2024
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status Publisher
|
| 520 |
|
|
|a Although weakly-supervised techniques can reduce the labeling effort, it is unclear whether a saliency model trained with weakly-supervised data (e.g., point annotation) can achieve the equivalent performance of its fully-supervised version. This paper attempts to answer this unexplored question by proving a hypothesis: there is a point-labeled dataset where saliency models trained on it can achieve equivalent performance when trained on the densely annotated dataset. To prove this conjecture, we proposed a novel yet effective adversarial spatio-temporal ensemble active learning. Our contributions are four- fold: 1) Our proposed adversarial attack triggering uncertainty can conquer the overconfidence of existing active learning methods and accurately locate these uncertain pixels. 2) Our proposed spatio-temporal ensemble strategy not only achieves outstanding performance but significantly reduces the model's computational cost. 3) Our proposed relationship-aware diversity sampling can conquer oversampling while boosting model performance. 4) We provide theoretical proof for the existence of such a point-labeled dataset. Experimental results show that our approach can find such a point-labeled dataset, where a saliency model trained on it obtained 98%-99% performance of its fully-supervised version with only ten annotated points per image. The code is available at https://github.com/wuzhenyubuaa/ASTE-AL
|
| 650 |
|
4 |
|a Journal Article
|
| 700 |
1 |
|
|a Wang, Wei
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Wang, Lin
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Li, Yacong
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Lv, Fengmao
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Xia, Qing
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Chen, Chenglizhao
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Hao, Aimin
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Li, Shuo
|e verfasserin
|4 aut
|
| 773 |
0 |
8 |
|i Enthalten in
|t IEEE transactions on pattern analysis and machine intelligence
|d 1979
|g PP(2024) vom: 09. Okt.
|w (DE-627)NLM098212257
|x 1939-3539
|7 nnns
|
| 773 |
1 |
8 |
|g volume:PP
|g year:2024
|g day:09
|g month:10
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TPAMI.2024.3476683
|3 Volltext
|
| 912 |
|
|
|a GBV_USEFLAG_A
|
| 912 |
|
|
|a SYSFLAG_A
|
| 912 |
|
|
|a GBV_NLM
|
| 912 |
|
|
|a GBV_ILN_350
|
| 951 |
|
|
|a AR
|
| 952 |
|
|
|d PP
|j 2024
|b 09
|c 10
|