Liu, L;
Wang, B;
Kuang, Z;
Xue, J-H;
Chen, Y;
Yang, W;
Liao, Q;
(2021)
GenDet: Meta Learning to Generate Detectors From Few Shots.
IEEE Transactions on Neural Networks and Learning Systems
10.1109/tnnls.2021.3053005.
(In press).
Preview |
Text
LiyangLiu-TNNLS-GenDec-final.pdf - Accepted Version Download (3MB) | Preview |
Abstract
Object detection has made enormous progress and has been widely used in many applications. However, it performs poorly when only limited training data is available for novel classes that the model has never seen before. Most existing approaches solve few-shot detection tasks implicitly without directly modeling the detectors for novel classes. In this article, we propose GenDet, a new meta-learning-based framework that can effectively generate object detectors for novel classes from few shots and, thus, conducts few-shot detection tasks explicitly. The detector generator is trained by numerous few-shot detection tasks sampled from base classes each with sufficient samples, and thus, it is expected to generalize well on novel classes. An adaptive pooling module is further introduced to suppress distracting samples and aggregate the detectors generated from multiple shots. Moreover, we propose to train a reference detector for each base class in the conventional way, with which to guide the training of the detector generator. The reference detectors and the detector generator can be trained simultaneously. Finally, the generated detectors of different classes are encouraged to be orthogonal to each other for better generalization. The proposed approach is extensively evaluated on the ImageNet, VOC, and COCO data sets under various few-shot detection settings, and it achieves new state-of-the-art results.
Type: | Article |
---|---|
Title: | GenDet: Meta Learning to Generate Detectors From Few Shots |
Open access status: | An open access version is available from UCL Discovery |
DOI: | 10.1109/tnnls.2021.3053005 |
Publisher version: | http://dx.doi.org/10.1109/tnnls.2021.3053005 |
Language: | English |
Additional information: | This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. |
Keywords: | Meta Learning, Few-shot Learning, Object Detection, Weight Generation |
UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences > Dept of Statistical Science |
URI: | https://discovery-pp.ucl.ac.uk/id/eprint/10120670 |
Archive Staff Only
![]() |
View Item |