ACTIVE IMAGE SAMPLING ON CANONICAL VIEWS FOR NOVEL OBJECT DETECTION

ACTIVE IMAGE SAMPLING ON CANONICAL VIEWS FOR NOVEL OBJECT DETECTION
Title:
ACTIVE IMAGE SAMPLING ON CANONICAL VIEWS FOR NOVEL OBJECT DETECTION
Other Titles:
ICIP 2020
Publication Date:
30 September 2020
Citation:
Abstract:
To alleviate the costly data annotation problem in deep learning-based object detection, we leverage the canonical view model for active sample selection to improve the ef- fectiveness of learning. Inspired by the view-approximation model, we hypothesize that visual features learned from canonical views denote better representations of objects, thus boosting the effectiveness of object learning. We validate the hypothesis empirically in the context of robot learning for novel object detection. Based on this, we propose a novel on-line viewpoint exploration (OLIVE) method that (1) defines goodness-of-view by combining informativeness of visual features and consistency of model-based object detec- tion, and (2) systematically explores and selects viewpoints to boost learning efficiency. Furthermore, we train a legacy Faster R-CNN model with a data augmentation method while leveraging data samples generated by the OLIVE pipeline. We test our method on the T-LESS dataset and show that the proposed method outperforms competitive benchmarking methods, especially when the samples are few.
License type:
http://creativecommons.org/licenses/by-nc-nd/4.0/
Funding Info:
Agency for Science, Technology and Research (A*STAR) under AME Programmatic Funding Scheme (Project #A18A2b0046)
Description:
“© 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.”
ISBN:

Files uploaded:

File Size Format Action
icip-canonical.pdf 789.62 KB PDF Open