AI Paper Atlas

Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning

Fleet: Few Shots Lead Effective AI-generated Image Detection

Jiaan Wang, Sirui Liu, Yu Li, Kaiyuan Yang, Juan Cao, Sheng Tang

ICML 2026 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Robust fine-tuning of zero-shot models · 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
add avoidance loss (ablation)Fleet · Treasure (8-subset ablation)mean accuracy: 89.25 -> 93.26Improved
add coverage loss (ablation)Fleet · Treasure (8-subset ablation)mean accuracy: 92.40 -> 93.26Improved
add all subspace losses (orth, cov, avoid) (ablation)Fleet · Treasure (8-subset ablation)mean accuracy: 89.22 -> 93.26Improved
use subspace routing instead of plain DINOv3+LoRA (ablation)Fleet · Treasure (8-subset ablation)mean accuracy: 91.35 -> 93.26Improved
use dynamic input-dependent addresses instead of static prototypes (ablation)Fleet · Treasure (8-subset ablation)mean accuracy: 92.21 -> 93.26Improved
structured MoE-style initialization (ablation)Fleet · Treasure (8-subset ablation)mean accuracy: 93.26 -> 93.53No clear effect
LoRA rank 8 vs 2 / 32 (ablation)Fleet · Treasure (8-subset ablation)mean accuracy: 91.25 (rank 2), 93.26 (rank 8), 91.46 (rank 32)No clear effect
shrink replay set to 20 images (ablation)Fleet · Treasure (8-subset ablation)mean accuracy: -13.92% accuracyHurt
shrink replay set to 20 images (pretrain val) (ablation)Fleet · Treasure (8-subset ablation)pretrain val accuracy: above 99.9%No clear effect
use 8 subspaces (ablation)Fleet · Treasure (8-subset ablation)mean accuracyImproved
increase few-shot support from 1 to 10 shotsFleet · AIGIBench-13AI accuracy: 92.12 -> 97.68 (AI acc)Improved
replace FSD with Fleet (anti-forgetting replay)Fleet · Treasure (64 generators)pretrain val accuracy: 74.81 -> 99.96 (Pretrain Val, 10-shot)Improved

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