Please use this identifier to cite or link to this item:
|Title:||S-CNN : subcategory-aware convolutional networks for object detection||Authors:||Chen, Tao
|Keywords:||Engineering::Computer science and engineering||Issue Date:||2017||Source:||Chen, T., Lu, S., & Fan, J. (2018). S-CNN : subcategory-aware convolutional networks for object detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 40(10), 2522-2528. doi:10.1109/TPAMI.2017.2756936||Journal:||IEEE Transactions on Pattern Analysis and Machine Intelligence||Abstract:||The marriage between the deep convolutional neural network (CNN) and region proposals has made breakthroughs for object detection in recent years. While the discriminative object features are learned via a deep CNN for classification, the large intra-class variation and deformation still limit the performance of the CNN based object detection. We propose a subcategory-aware CNN (S-CNN) to solve the object intra-class variation problem. In the proposed technique, the training samples are first grouped into multiple subcategories automatically through a novel instance sharing maximum margin clustering process. A multi-component Aggregated Channel Feature (ACF) detector is then trained to produce more latent training samples, where each ACF component corresponds to one clustered subcategory. The produced latent samples together with their subcategory labels are further fed into a CNN classifier to filter out false proposals for object detection. An iterative learning algorithm is designed for the joint optimization of image subcategorization, multi-component ACF detector, and subcategory-aware CNN classifier. Experiments on INRIA Person dataset, Pascal VOC 2007 dataset and MS COCO dataset show that the proposed technique clearly outperforms the state-of-the-art methods for generic object detection.||URI:||https://hdl.handle.net/10356/139870||ISSN:||0162-8828||DOI:||10.1109/TPAMI.2017.2756936||Rights:||© 2017 IEEE. All rights reserved.||Fulltext Permission:||none||Fulltext Availability:||No Fulltext|
|Appears in Collections:||SCSE Journal Articles|
Updated on Mar 10, 2021
Updated on Mar 8, 2021
Updated on Jun 29, 2022
Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.