AI Paper Atlas

Research map / Continual learning / Class-incremental

IncreFA: Breaking the Static Wall of Generative Model Attribution

Haotian Qin, Dongliang Chang, Yueying Gao, Yuexuan Tan, Lei Chen, Zhanyu Ma

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 latent replay loss (ablation)IncreFA baseline · IABench EP1 final taskaccuracy (%): 35.24 -> 52.99Improved
add model-level hierarchical constraint L1 (ablation)IncreFA · IABench EP1 final taskaccuracy (%): 52.99 -> 73.16Improved
add family-level hierarchical constraint L2 (ablation)IncreFA · IABench EP1 final taskaccuracy (%): 73.16 -> 76.16Improved
add open-set loss L_u (ablation)IncreFA · IABench EP1 unseen detectionunseen accuracy (%): 81.94 -> 98.93Improved
add open-set loss L_u (ablation)IncreFA · IABench EP1 final taskaccuracy (%): 76.16 -> 78.80Improved
add L1 on top of replay (ablation)IncreFA · IABench EP1 unseen detectionunseen accuracy (%): 73.98 -> 72.19Hurt
raise tau from 0.5 to 0.65 (ablation)IncreFA open-set threshold · IABench EP1unseen accuracy (%): 65.01 -> 98.93Improved
raise tau from 0.65 to 0.90 (ablation)IncreFA open-set threshold · IABench EP1seen accuracy (%): 78.80 -> 41.80Hurt
increase memory bank from 5 to 150 samples per model (ablation)IncreFA latent memory bank · IABench EP1final accuracy (%): 56.04 -> 77.80Improved
increase memory bank from 150 to 500 samples per model (ablation)IncreFA latent memory bank · IABench EP1final accuracy (%): 77.80 -> 82.00Improved
use hierarchical structure with correct family labels instead of wrong D->G family labels (ablation)IncreFA · IABench EP1increment accuracy (%): 71.47 -> 78.80Improved
replace best baseline with IncreFA under incremental learningDGR · IABench EP1 final taskaccuracy (%): 75.68 -> 78.80Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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