AI Paper Atlas

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

Can We Build a Monolithic Model for Fake Image Detection? SICA: Semantic-Induced Constrained Adaptation for Unified-Yet-Discriminative Artifact Feature Space Reconstruction

Bo Du, Xiaochen Ma, Xuekang Zhu, Zhe Yang, Chaoqun Niu, Jian liu, Ji-Zhe Zhou

ICML 2026 · Detection and segmentation › Open-set and few-shot detection · approach: Cross-domain translation and pose

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 full fine-tuning with SICA low-rank adaptation on CLIPCLIP-FFT · OpenMMSec overallaccuracy: 80.2 -> 85.4Improved
replace Effort SVD-residual adaptation with SICAEffort · OpenMMSec overallaccuracy: 80.1 -> 85.4Improved
use SICA instead of FFT under unified trainingCLIP · DeepfakeAUC: 0.7900 -> 0.9234Improved
use SICA instead of FFT under unified trainingCLIP · DocAUC: 0.8080 -> 0.8646Improved
unified training instead of single-domain training for FFT (ablation)FFT · DeepfakeAUC: 0.8183 -> 0.7900Hurt
unified training instead of single-domain training for SICA (ablation)SICA · DeepfakeAUC: 0.9235 -> 0.9234No clear effect
unified training instead of single-domain training for FFT (ablation)FFT · AIGCAUC: 0.9291 -> 0.8987Hurt
add leave-one-domain-out training data from other domains (ablation)SICA · held-out DeepfakeAUC: 0.9235 single-domain vs 0.7660 LODOHurt
use CLIP-pretrained instead of ImageNet-1K ResNet-50 (ablation)ResNet-50 · OpenMMSec overallaccuracy: 72.7 -> 78.3Improved
use CLIP ViT-L/14 instead of DINOv2 (ablation)SICA · OpenMMSec overallaccuracy: 82.9 -> 85.4Improved
use CLIP ViT-L/14 instead of SigLIP (ablation)SICA · OpenMMSec overallaccuracy: 82.2 -> 85.4Improved
increase LoRA rank beyond 8-32 (ablation)SICA · OpenMMSecaccuracy: peak plateau at rank 8 to 32Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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