Cyclic Self-Training with Proposal Weight Modulation for Cross-Supervised Object Detection

Weakly-supervised object detection (WSOD), which requires only image-level annotations for training detectors, has gained enormous attention. Despite recent rapid advance in WSOD, there remains a large performance gap compared with fully-supervised object detection. To narrow the performance gap, we...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. - 1992. - PP(2023) vom: 29. März
1. Verfasser: Xu, Yunqiu (VerfasserIn)
Weitere Verfasser: Zhou, Chunluan, Yu, Xin, Yang, Yi
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2023
Zugriff auf das übergeordnete Werk:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
Schlagworte:Journal Article
LEADER 01000naa a22002652 4500
001 NLM355198681
003 DE-627
005 20231226063835.0
007 cr uuu---uuuuu
008 231226s2023 xx |||||o 00| ||eng c
024 7 |a 10.1109/TIP.2023.3261752  |2 doi 
028 5 2 |a pubmed24n1183.xml 
035 |a (DE-627)NLM355198681 
035 |a (NLM)37015123 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Xu, Yunqiu  |e verfasserin  |4 aut 
245 1 0 |a Cyclic Self-Training with Proposal Weight Modulation for Cross-Supervised Object Detection 
264 1 |c 2023 
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 04.04.2023 
500 |a published: Print-Electronic 
500 |a Citation Status Publisher 
520 |a Weakly-supervised object detection (WSOD), which requires only image-level annotations for training detectors, has gained enormous attention. Despite recent rapid advance in WSOD, there remains a large performance gap compared with fully-supervised object detection. To narrow the performance gap, we study cross-supervised object detection (CSOD), where existing classes (base classes) have instance-level annotations while newly added classes (novel classes) only need image-level annotations. For improving localization accuracy, we propose a Cyclic Self-Training (CST) method to introduce instance-level supervision into a commonly used WSOD method, online instance classifier refinement (OICR). Our proposed CST consists of forward pseudo labeling and backward pseudo labeling. Specifically, OICR exploits the forward pseudo labeling to generate pseudo ground-truth bounding-boxes for all classes, thus enabling instance classifier training. Then, the backward pseudo labeling is designed to generate pseudo ground-truth bounding-boxes of higher quality for novel classes by fusing the predictions of the instance classifiers. As a result, both novel and base classes will have bounding-box annotations for training, alleviating the supervision inconsistency between base and novel classes. In the forward pseudo labeling, the generated pseudo ground-truths may be misaligned with objects and thus introduce poor-quality examples for training the ICs. To reduce the impacts of these poor-quality training examples, we propose a Proposal Weight Modulation (PWM) module learned in a class-agnostic and contrastive manner by exploiting bounding-box annotations of base classes. Experiments on PASCAL VOC and MS COCO datasets demonstrate the superiority of our proposed method 
650 4 |a Journal Article 
700 1 |a Zhou, Chunluan  |e verfasserin  |4 aut 
700 1 |a Yu, Xin  |e verfasserin  |4 aut 
700 1 |a Yang, Yi  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on image processing : a publication of the IEEE Signal Processing Society  |d 1992  |g PP(2023) vom: 29. März  |w (DE-627)NLM09821456X  |x 1941-0042  |7 nnns 
773 1 8 |g volume:PP  |g year:2023  |g day:29  |g month:03 
856 4 0 |u http://dx.doi.org/10.1109/TIP.2023.3261752  |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 2023  |b 29  |c 03