arXiv Analytics

Sign in

arXiv:1901.08225 [cs.CV]AbstractReferencesReviewsResources

Object Detection based on Region Decomposition and Assembly

Seung-Hwan Bae

Published 2019-01-24Version 1

Region-based object detection infers object regions for one or more categories in an image. Due to the recent advances in deep learning and region proposal methods, object detectors based on convolutional neural networks (CNNs) have been flourishing and provided the promising detection results. However, the detection accuracy is degraded often because of the low discriminability of object CNN features caused by occlusions and inaccurate region proposals. In this paper, we therefore propose a region decomposition and assembly detector (R-DAD) for more accurate object detection. In the proposed R-DAD, we first decompose an object region into multiple small regions. To capture an entire appearance and part details of the object jointly, we extract CNN features within the whole object region and decomposed regions. We then learn the semantic relations between the object and its parts by combining the multi-region features stage by stage with region assembly blocks, and use the combined and high-level semantic features for the object classification and localization. In addition, for more accurate region proposals, we propose a multi-scale proposal layer that can generate object proposals of various scales. We integrate the R-DAD into several feature extractors, and prove the distinct performance improvement on PASCAL07/12 and MSCOCO18 compared to the recent convolutional detectors.

Comments: Accepted to 2019 AAAI Conference on Artificial Intelligence (AAAI)
Categories: cs.CV
Related articles: Most relevant | Search more
arXiv:1703.08013 [cs.CV] (Published 2017-03-23)
A learning-based approach to text image retrieval: using CNN features and improved similarity metrics
arXiv:2003.02065 [cs.CV] (Published 2020-03-04)
Mixup Regularization for Region Proposal based Object Detectors
arXiv:2005.10550 [cs.CV] (Published 2020-05-21)
Region Proposals for Saliency Map Refinement for Weakly-supervised Disease Localisation and Classification