UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

IncDet: In Defense of Elastic Weight Consolidation for Incremental Object Detection

Liu, L; Kuang, Z; Chen, Y; Xue, J-H; Yang, W; Zhang, W; (2020) IncDet: In Defense of Elastic Weight Consolidation for Incremental Object Detection. IEEE Transactions on Neural Networks and Learning Systems 10.1109/tnnls.2020.3002583. (In press). Green open access

[thumbnail of TNNLS-2019-P-11867.R2-UCL.pdf]
Preview
Text
TNNLS-2019-P-11867.R2-UCL.pdf - Accepted Version

Download (5MB) | Preview

Abstract

Elastic weight consolidation (EWC) has been successfully applied for general incremental learning to overcome the catastrophic forgetting issue. It adaptively constrains each parameter of the new model not to deviate much from its counterpart in the old model during fine-tuning on new class data sets, according to its importance weight for old tasks. However, the previous study demonstrates that it still suffers from catastrophic forgetting when directly used in object detection. In this article, we show EWC is effective for incremental object detection if with critical adaptations. First, we conduct controlled experiments to identify two core issues why EWC fails if trivially applied to incremental detection: 1) the absence of old class annotations in new class images makes EWC misclassify objects of old classes in these images as background and 2) the quadratic regularization loss in EWC easily leads to gradient explosion when balancing old and new classes. Then, based on the abovementioned findings, we propose the corresponding solutions to tackle these issues: 1) utilize pseudobounding box annotations of old classes on new data sets to compensate for the absence of old class annotations and 2) adopt a novel Huber regularization instead of the original quadratic loss to prevent from unstable training. Finally, we propose a general EWC-based incremental object detection framework and implement it under both Fast R-CNN and Faster R-CNN, showing its flexibility and versatility. In terms of either the final performance or the performance drop with respect to the upper bound of joint training on all seen classes, evaluations on the PASCAL VOC and COCO data sets show that our method achieves a new state of the art.

Type: Article
Title: IncDet: In Defense of Elastic Weight Consolidation for Incremental Object Detection
Open access status: An open access version is available from UCL Discovery
DOI: 10.1109/tnnls.2020.3002583
Publisher version: https://doi.org/10.1109/tnnls.2020.3002583
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: Bayesian online learning , catastrophic forgetting , incremental detection , object detection.
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.ucl.ac.uk/id/eprint/10103165
Downloads since deposit
1,164Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item