AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

Unlearning in Cross-Modal Retrieval via Prior-Prototype Guided Partitioned Dampening

Yi Lu, Shu Li, Yurong Qian

AAAI 2026 · Vision-language and multimodal › Cross-modal learning · approach: Unimodal-to-multimodal representation transfer · 0 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
replace uniform dampening (SSD) with prototype-guided hierarchical dampening (PPP)SSD · COCO (dog), Dravg |delta| mAP vs Original: 2.07 -> 0.66Improved
replace uniform dampening (SSD) with PPPSSD · Flickr25K (dog), Dfavg |delta| mAP vs Retrain: 10.8 -> 6.37Improved
replace uniform dampening (SSD) with PPPSSD · DeepFashion (Trunks), Draccuracy (%): 79.5 -> 86.9Improved
replace SSD with PPPSSD · ImageNet-100 (Doberman), Draccuracy (%): 96.4 -> 96.0No clear effect
increase number of forgotten classes from 1-2 to 4 and 8 (ablation)PPP · COCO multi-class unlearning, DrmAP: 6.26% overall mAP drop with eight classesHurt
increase number of forgetting classes (ablation)PPP · COCO multi-class unlearning, DfmAP deviation from retrainMixed
increase forgetting sample size from 20 to 100 (ablation)PPP · COCO, 64-bit T2Iconfidence interval width on Df: 2.16 -> 0.56Improved
use only 20 forgetting samples (ablation)PPP · COCOmAP on Df and DrNo clear effect

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