AI Paper Atlas

Research map / Continual learning / Class-incremental

Parameterized Prompt for Incremental Object Detection

Zijia An, Boyu Diao, Ruiqi Liu, Libo Huang, Chuanguang Yang, Fei Wang, Zhulin An, Yongjun Xu

CVPR 2026 · Continual learning › Class-incremental · approach: Incremental object detection with replay · 1 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 pseudo labeling to the baseline (ablation)Deformable-DETR baseline · VOC2007 5+5+5+5AP50 (1-20): 67.4 -> 66.8Hurt
add parameterized prompt structure (ablation)baseline with pseudo labeling · VOC2007 5+5+5+5AP50 (1-20): 66.8 -> 75.1Improved
add parameterized prompt fusion (ablation)P2IOD with parameterized prompts · VOC2007 5+5+5+5AP50 (1-20): 75.1 -> 75.3Improved
add sparse loss (ablation)P2IOD with fusion · VOC2007 5+5+5+5AP50 (1-20): 75.3 -> 76.4Improved
add pseudo labeling (ablation)P2IOD with prompts, fusion and sparse loss · VOC2007 5+5+5+5AP50 (1-20): 71.5 -> 76.4Improved
add prompt fusion (ablation)P2IOD · VOC2007 10+10AP50 (1-20): 80.13 -> 81.21Improved
keep only first-task prompts (top-k 1.0) instead of moderate fusion (ablation)P2IOD fusion · VOC2007 10+10AP50 (1-20): 81.21 -> 80.71Hurt
set sparse loss lambda to 1e-5 instead of 0 (ablation)P2IOD · VOC2007 5+5+5+5AP50 (1-20): 75.3 -> 76.4Improved
use too large sparse loss lambda 1e-4 instead of 1e-5 (ablation)P2IOD · VOC2007 5+5+5+5AP50 (1-20): 76.4 -> 76.1Hurt
replace query-localization with SAC compression (ablation)MD-DETR · VOC2007 5+5+5+5AP50 (1-20): 61.5 -> 64.0Improved
use average compression instead of SAC (ablation)P2IOD · VOC2007 5+5+5+5AP50 (1-20): 64.7 -> 76.4Improved
replace MD-DETR prompt pool with parameterized promptsDeformable-DETR COCO · VOC2007 10+10AP50 (1-20): 73.2 -> 81.2Improved

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