CBASH: Combined Backbone and Advanced Selection Heads With Object Semantic Proposals for Weakly Supervised Object Detection
- 18 April 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 32 (10) , 6502-6514
Abstract
Most recent object detection methods have achieved growing performance on public datasets. However, enormous efforts are needed for these methods due to the extensive annotations of ground-truth boxes. Weakly Supervised Object Detection (WSOD) methods hence have been proposed to solve this problem as only image-level annotations are required and then output bounding boxes related to the objects. In order to further elevate the weakly supervised detection methods on the extraction of reasonable features, the training of potential positive proposals, and the generation of proposals before training, we propose a new Combined Backbone and Advanced Selection Heads (CBASH) method with the proposals generated from the object semantic information. Specifically, Combined Backbone will make the unobvious object features more noticeable, Advanced Selection Heads promote more potential positive proposals to get training, and the generated object semantic proposals elevate the quality and quantity of positive proposals. The proposed method is evaluated on the challenging PASCAL VOC 2007 and 2012 benchmark datasets. Experimental results show that our proposed method can achieve improved performance on both VOC 2007 and VOC 2012 datasets and outperforms the existing state-of-the-art methods.Keywords
Funding Information
- National Natural Science Foundation of China (61971079, U21A20447)
- Basic Research and Frontier Exploration Project of Chongqing (cstc2019jcyj- msxmX0666)
- National Key Research and Development Program of China (2019YFC1511300)
- Regional Creative Cooperation Program of Sichuan (2020YFQ0025)
- Innovative Group Project of the National Natural Science Foundation of Chongqing (cstc2020jcyj-cxttX0002)
This publication has 39 references indexed in Scilit:
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- Bilinear CNN Models for Fine-Grained Visual Recognition2015
- Fully convolutional networks for semantic segmentation2015
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- Spatial Pyramid Pooling in Deep Convolutional Networks for Visual RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- The Pascal Visual Object Classes Challenge: A RetrospectiveInternational Journal of Computer Vision, 2014
- Multi-fold MIL Training for Weakly Supervised Object Localization2014
- Selective Search for Object RecognitionInternational Journal of Computer Vision, 2013
- Weakly Supervised Localization and Learning with Generic KnowledgeInternational Journal of Computer Vision, 2012
- Solving the multiple instance problem with axis-parallel rectanglesArtificial Intelligence, 1997