Learning to Segment Object Candidates via Recursive Neural Networks

Learning to Segment Object Candidates via Recursive Neural Networks

To avoid the exhaustive search over locations and scales, current state-of-the-art object detection systems usually involve a crucial component generating a batch of candidate object proposals from images. In this paper, we present a simple yet effective approach for segmenting object proposals via...

Description complète

Détails bibliographiques
Publié dans:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. - 1992. - 27(2018), 12 vom: 23. Dez., Seite 5827-5839
Auteur principal: Chen, Tianshui (Auteur)
Autres auteurs: Lin, Liang, Wu, Xian, Xiao, Nong, Luo, Xiaonan
Format: Article en ligne
Langue:English
Publié: 2018
Accès à la collection:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
Sujets:Journal Article
LEADER 01000caa a22002652 4500
001 NLM286809338
003 DE-627
005 20250223205358.0
007 cr uuu---uuuuu
008 231225s2018 xx |||||o 00| ||eng c
024 7 |a 10.1109/TIP.2018.2859025  |2 doi 
028 5 2 |a pubmed25n0955.xml 
035 |a (DE-627)NLM286809338 
035 |a (NLM)30040644 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Chen, Tianshui  |e verfasserin  |4 aut 
245 1 0 |a Learning to Segment Object Candidates via Recursive Neural Networks 
264 1 |c 2018 
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 Completed 17.12.2018 
500 |a Date Revised 10.12.2019 
500 |a published: Print-Electronic 
500 |a Citation Status MEDLINE 
520 |a To avoid the exhaustive search over locations and scales, current state-of-the-art object detection systems usually involve a crucial component generating a batch of candidate object proposals from images. In this paper, we present a simple yet effective approach for segmenting object proposals via a deep architecture of recursive neural networks (ReNNs), which hierarchically groups regions for detecting object candidates over scales. Unlike traditional methods that mainly adopt fixed similarity measures for merging regions or finding object proposals, our approach adaptively learns the region merging similarity and the objectness measure during the process of hierarchical region grouping. Specifically, guided by a structured loss, the ReNN model jointly optimizes the cross-region similarity metric with the region merging process as well as the objectness prediction. During inference of the object proposal generation, we introduce randomness into the greedy search to cope with the ambiguity of grouping regions. Extensive experiments on standard benchmarks, e.g., PASCAL VOC and ImageNet, suggest that our approach is capable of producing object proposals with high recall while well preserving the object boundaries and outperforms other existing methods in both accuracy and efficiency 
650 4 |a Journal Article 
700 1 |a Lin, Liang  |e verfasserin  |4 aut 
700 1 |a Wu, Xian  |e verfasserin  |4 aut 
700 1 |a Xiao, Nong  |e verfasserin  |4 aut 
700 1 |a Luo, Xiaonan  |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 27(2018), 12 vom: 23. Dez., Seite 5827-5839  |w (DE-627)NLM09821456X  |x 1941-0042  |7 nnns 
773 1 8 |g volume:27  |g year:2018  |g number:12  |g day:23  |g month:12  |g pages:5827-5839 
856 4 0 |u http://dx.doi.org/10.1109/TIP.2018.2859025  |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 27  |j 2018  |e 12  |b 23  |c 12  |h 5827-5839