AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Retain and Adapt: Auto-Balanced Model Editing for Open-Vocabulary Object Detection under Domain Shifts

Zixuan Duan, Fengyuan Lu, Xunzhi Xiang, Wenbin Li, Yang Gao, Qi Fan

ICLR 2026 · Detection and segmentation › Open-set and few-shot detection · approach: Open-vocabulary object detection

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
edit FFN output layers with auto-balanced KV objective instead of continual learning baselinesGrounding DINO · CDFSOD-6 (5-shot)AP: 31.0 (EWC) -> 38.5Improved
use auto-balanced Gamma regularizer instead of manually tuned lambda (ablation)ABME · CDFSOD-6, 1 to 6 tasksnew-task mAPImproved
use exponent 1/4 instead of 1/2 in Gamma (ablation)ABME · CDFSOD-6 (5-shot)AP: 36.6 -> 38.5Improved
use exponent 1/8 instead of 1/4 in Gamma (ablation)ABME · CDFSOD-6 (5-shot)AP: 38.5 -> 38.5No clear effect
edit all FFNs instead of a sub-module only (ablation)ABME · CDFSOD-6 (5-shot)new-task AP: 35.1 (all backbone) -> 38.5Improved
edit FFN output layers instead of self-attention layers (ablation)ABME · CDFSOD-6 (5-shot)AP: 36.3 -> 38.5Improved
add ABME on top of EWCEWC · CDFSOD-6 (10-shot)AP: 31.9 -> 41.7Improved
add ABME on top of SD-LoRASD-LoRA · CDFSOD-6 (10-shot)AP: 28.4 -> 38.5Improved
aggregate task KV statistics additively rather than sequential fine-tuningABME · CDFSOD-6 task orderAP stabilityImproved
apply ABME to GLIP and CLIPABME · CDFSOD-6 GLIP; CLIP 11 datasetsAP / accuracy: GLIP 19.1 -> 35.2 (5-shot); CLIP 65.3 -> 74.1Improved
ABME versus continual learning on COCO retentionABME · CDFSOD-6 5-shot COCO APCOCO AP: Adam-NSCL 57.8 vs Ours 57.0Mixed

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