Paper Info
Title
Co-Occurrence Matrix Analysis-Based Semi-Supervised Training For Object Detection
Abstract
One of the most important factors in training object recognition networks using convolutional neural networks (CNN) is the provision of annotated data accompanying human judgment. Particularly, in object detection or semantic segmentation, the annotation process requires considerable human effort. In this paper, we propose a semi-supervised learning (SSL)-based training methodology for object detection, which makes use of automatic labeling of un-annotated data by applying a network previously trained from an annotated dataset. Because an inferred label by the trained network is dependent on the learned parameters, it is often meaningless for re-training the network. To transfer a valuable inferred label to the unlabeled data, we propose a re-alignment method based on co-occurrence matrix analysis that takes into account one-hot-vector encoding of the estimated label and the correlation between the objects in the image. We used an MS-COCO detection dataset to verify the performance of the proposed SSL method and deformable neural networks (D-ConvNets) [1] as an object detector for basic training. The performance of the existing state-of-the-art detectors (D-ConvNets, YOLO v2 [2], and single shot multi-box detector (SSD) [3]) can be improved by the proposed SSL method without using the additional model parameter or modifying the network architecture.
Year
Venue
Keywords
2018
2018 25TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP)
Object detection, Semi-supervised learning, Convolutional neural networks, Co-occurrence matrix
DocType
Volume
ISSN
Conference
abs/1802.06964
1522-4880
Citations 
PageRank 
References 
0
0.34
0
Authors
9
Name
Order
Citations
PageRank
Min-Kook Choi1193.47
Jaehyeong Park220.78
Ji-Hun Jung353.12
Heechul Jung420810.24
Jinhee Lee58021.11
Woong Jae Won600.68
Woo Young Jung7497.39
Jincheol Kim810.70
Soon Kwon9265.77