< Back to previous page


Detecting and Grouping Identical Objects for Region Proposal and Classification

Journal Contribution - Journal Article Conference Contribution

Often multiple instances of an object occur in the same scene, for example in a warehouse. Unsupervised multi-instance object discovery algorithms are able to detect and identify such objects. We use such an algorithm to provide object proposals to a convolutional neural network (CNN) based classifier. This results in fewer regions to evaluate, compared to traditional region proposal algorithms. Additionally, it enables using the joint probability of multiple instances of an object, resulting in improved classification accuracy. The proposed technique can also split a single class into multiple sub-classes corresponding to the different object types, enabling hierarchical classification.
Journal: Conference on Computer Vision and Pattern Recognition Workshops. Proceedings
ISSN: 2160-7508
Volume: abs/1707.0
Pages: 501 - 502
Number of pages: 2
Publication year:2017