Continual Detection Transformer for Incremental Object Detection
Authors:
- 1 June 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 23799-23808
Abstract
Incremental object detection (IOD) aims to train an object detector in phases, each with annotations for new object categories. As other incremental settings, IOD is subject to catastrophic forgetting, which is often addressed by techniques such as knowledge distillation (KD) and exem-plar replay (ER). However, KD and ER do not work well if applied directly to state-of-the-art transformer-based object detectors such as Deformable DETR [59] and UP-DETR [9]. In this paper, we solve these issues by proposing a ContinuaL DEtection TRansformer (CL-DETR), a new method for transformer-based IOD which enables effective usage of KD and ER in this context. First, we introduce a Detector Knowledge Distillation (DKD) loss, focusing on the most informative and reliable predictions from old versions of the model, ignoring redundant background predictions, and ensuring compatibility with the available ground-truth labels. We also improve ER by proposing a calibration strategy to preserve the label distribution of the training set, therefore better matching training and testing statistics. We conduct extensive experiments on COCO 2017 and demonstrate that CL-DETR achieves state-of-the-art results in the IOD setting. 1 1 Code: https://1yy.mpi-inf.mpg.de/CL-DETR/Keywords
All Related Versions
This publication has 34 references indexed in Scilit:
- Learning without ForgettingIEEE Transactions on Pattern Analysis and Machine Intelligence, 2017
- Expert Gate: Lifelong Learning with a Network of Experts2017
- iCaRL: Incremental Classifier and Representation Learning2017
- Overcoming catastrophic forgetting in neural networksProceedings of the National Academy of Sciences, 2017
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- End-to-End People Detection in Crowded Scenes2016
- Fast R-CNN2015
- Catastrophic Interference in Connectionist Networks: The Sequential Learning Problem1989
- The Hungarian method for the assignment problemNaval Research Logistics Quarterly, 1955
- On Information and SufficiencyThe Annals of Mathematical Statistics, 1951