Index-Aligned Query Distillation for Transformer-based Incremental Object Detection
Mingxiao Ma, Shunyao Zhu, Guoliang Kang

TL;DR
This paper introduces Index-Aligned Query Distillation (IAQD), a novel method for transformer-based incremental object detection that preserves previous knowledge by aligning query indices, outperforming existing distillation techniques.
Contribution
The paper proposes IAQD, a new query distillation approach that aligns queries by index to better retain old category knowledge during incremental learning with transformers.
Findings
IAQD outperforms existing methods on benchmark datasets.
It effectively mitigates catastrophic forgetting in incremental object detection.
Achieves state-of-the-art results in transformer-based IOD.
Abstract
Incremental object detection (IOD) aims to continuously expand the capability of a model to detect novel categories while preserving its performance on previously learned ones. When adopting a transformer-based detection model to perform IOD, catastrophic knowledge forgetting may inevitably occur, meaning the detection performance on previously learned categories may severely degenerate. Previous typical methods mainly rely on knowledge distillation (KD) to mitigate the catastrophic knowledge forgetting of transformer-based detection models. Specifically, they utilize Hungarian Matching to build a correspondence between the queries of the last-phase and current-phase detection models and align the classifier and regressor outputs between matched queries to avoid knowledge forgetting. However, we observe that in IOD task, Hungarian Matching is not a good choice. With Hungarian Matching,…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
