AI Paper Atlas

Research map / Continual learning / Class-incremental

Alleviating Catastrophic Forgetting of Incremental Object Detection via Within-Class and Between-Class Knowledge Distillation

Mengxue Kang, Jinpeng Zhang, Jinming Zhang, Xiashuang Wang, Yang Chen, Zhe Ma, Xuhui Huang

ICCV 2023 · Continual learning › Class-incremental · approach: Incremental object detection with replay · 23 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add Interactive Feature Distillation (IFD) to the LwF baseline (ablation)Deformable DETR with LwF · COCO last 40 + first 40final mAP: 38.89 -> 39.68Improved
add Distance Matrix Distillation (DMD) to the LwF baseline (ablation)Deformable DETR with LwF · COCO last 40 + first 40final mAP: 38.89 -> 39.58Improved
combine DMD and IFD (ablation)Deformable DETR with LwF · COCO last 40 + first 40final mAP: 38.89 -> 39.80Improved
distill the whole feature map instead of selected features (ablation)IFD · COCO last 40 + first 40final mAP: 38.89 -> 38.93No clear effect
restrict feature distillation to foreground objects (ablation)IFD · COCO last 40 + first 40final mAP: 38.89 -> 39.36Improved
add high-level semantic interaction to foreground feature distillation (ablation)IFD · COCO last 40 + first 40final mAP: 39.36 -> 39.68Improved
use Manhattan distance instead of Euclidean in DMD (ablation)DMD · COCO last 40 + first 40final mAP: 38.89 -> 39.14 (Euclidean 39.58)No clear effect
multiply semantic and feature components instead of adding (ablation)DMD and IFD · COCO 70+10mAP: 37.50 -> 37.60Improved
add DMD+IFD to LwF label distillation (ablation)LwF · COCO 70+10mAP: 36.40 -> 37.60Improved
raise alpha and beta beyond 1.5 (ablation)Total loss weights · COCO 70+10mAP: 37.60 -> 37.10 (alpha 2, beta 1)Hurt
increase number of decoder queries from 100 to 300 (ablation)Deformable DETR · COCO 70+10mAP: 36.20 -> 37.60Improved
use a better AdaMixer teacher and student (ablation)Transformer detectors · COCO 70+10mAP: 37.60 -> 40.20Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy