Learning Open-World Object Proposals Without Learning to Classify

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 49
  • Download : 0
Object proposals have become an integral pre-processing step of many vision pipelines including object detection, weakly supervised detection, object discovery, tracking, etc. Compared to the learning-free methods, learning-based proposals have become popular recently due to the growing interest in object detection. The common paradigm is to learn object proposals from data labeled with a set of object regions and their corresponding categories. However, this approach often struggles with novel objects in the open world that are absent in the training set. In this letter, we identify that the problem is that the binary classifiers in existing proposal methods tend to overfit to the training categories. Therefore, we propose a classification-free Object Localization Network (OLN) which estimates the objectness of each region purely by how well the location and shape of a region overlap with any ground-truth object (e.g., centerness and IoU). This strategy learns generalizable objectness and outperforms existing proposals on cross-category generalization on COCO. We further explore more challenging cross-dataset generalization onto RoboNet and EpicKitchens dataset, and long-tail detection on LVIS dataset. We demonstrate clear improvement over the state-of-the-art object detectors and object proposers. The code is publicly available at https://github.com/mcahny/object_localization_network.
Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Issue Date
2022-04
Language
English
Article Type
Article
Citation

IEEE ROBOTICS AND AUTOMATION LETTERS, v.7, no.2, pp.5453 - 5460

ISSN
2377-3766
DOI
10.1109/LRA.2022.3146922
URI
http://hdl.handle.net/10203/292548
Appears in Collection
EE-Journal Papers(저널논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0