← Back to all news
arXiv Computer Vision By Yiheng Li, Yang Yang, Wenhao Wang, Zichang Tan, Zecheng Lin, Li Gao, Zhen Lei

Reduce the Artifacts Bias for More Generalizable AI-Generated Image Detection

Read the original on arXiv Computer Vision →

The paper proposes Artifact-Complementary Expert Fusion (ACEF), a two‑stage framework that enhances AI‑generated image detection by combining two types of reconstruction artifacts—VAE/DDIM and SRGAN—into aligned synthetic negatives. ACEF first builds artifact‑specific experts using LoRA adaptation on a frozen backbone, then fuses their multi‑layer evidence with Layer‑wise Artifact‑Complementary Fusion (LACF) to mitigate conflicts between artifact manifolds. Experiments on 13 benchmarks show that this approach improves generalizability over existing state‑of‑the‑art methods.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

arXiv Computer Vision
Sep 30

RED: Reconstruction Evolution Dynamics for Generalizable AI-Generated Image Detection

The paper introduces RED (Reconstruction Evolution Dynamics), a new framework for detecting AI-generated images that leverages the evolution of intermediate reconstruction stages rather than relying solely on static representations or endpoint discrepancies. RED uses a frozen multiscale VQ‑VAE and a frozen CLIP encoder to capture a reconstruction trajectory, then learns image‑adaptive stage weights from token negative log‑likelihoods provided by a frozen VAR model. Experiments on six benchmarks show RED achieves the highest average accuracy (92.5%) and precision (97.5%) among evaluated methods, and it remains robust to common image degradations.

By Wenpeng Mu, Junshan Jin, Tanfeng Sun, Xinghao Jiang, Qiang Xu
benchmarks
More like this →
arXiv AI
Aug 28

High-Fidelity Face Content Recovery via Tamper-Resilient Versatile Watermarking

The paper introduces VeriFi, a watermarking framework that protects face images from AI‑generated manipulation. It embeds a compact semantic latent watermark to preserve content, localizes pixel‑level edits without explicit payloads, and simulates realistic deepfake attacks to improve robustness. Experiments on CelebA‑HQ and FFHQ show that VeriFi outperforms existing methods in robustness, localization accuracy, and recovery quality.

By Peipeng Yu, Jinfeng Xie, Chengfu Ou, Xiaoyu Zhou, Jianwei Fei, Yunshu Dai, Zhihua Xia, Chip Hong Chang
ragroboticsbenchmarks
More like this →