# Mixture of Low-rank Experts for Transferable AI-Generated Image Detection

arXiv: https://arxiv.org/abs/2404.04883 · HTML: https://mlsanity.com/paper/2404.04883/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Builds on 50 of its 67 references that are in the map.
- First posted on arXiv 7 Apr 2024.

## Builds on (most cited first, 30 of 50)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016)
- [Density estimation using Real NVP](https://mlsanity.com/paper/1605.08803/) (2016)
- [GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding](https://mlsanity.com/paper/2006.16668/) (2020)
- [LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop](https://mlsanity.com/paper/1506.03365/) (2015)
- [Transformer Feed-Forward Layers Are Key-Value Memories](https://mlsanity.com/paper/2012.14913/) (2020)
- [Semantic Image Synthesis with Spatially-Adaptive Normalization](https://mlsanity.com/paper/1903.07291/) (2019)
- [FaceForensics++: Learning to Detect Manipulated Facial Images](https://mlsanity.com/paper/1901.08971/) (2019)
- [StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation](https://mlsanity.com/paper/1711.09020/) (2017)
- [CNN-generated images are surprisingly easy to spot... for now](https://mlsanity.com/paper/1912.11035/) (2019)
- [Vector Quantized Diffusion Model for Text-to-Image Synthesis](https://mlsanity.com/paper/2111.14822/) (2021)
- [Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution](https://mlsanity.com/paper/2202.10054/) (2022)
- [Pseudo Numerical Methods for Diffusion Models on Manifolds](https://mlsanity.com/paper/2202.09778/) (2022)
- [Leveraging Frequency Analysis for Deep Fake Image Recognition](https://mlsanity.com/paper/2003.08685/) (2020)
- [Towards Universal Fake Image Detectors that Generalize Across Generative Models](https://mlsanity.com/paper/2302.10174/) (2023)

## Built on by (most cited first, 21 of 21)

- [Low-Rank Adaptation for Foundation Models: A Comprehensive Review](https://mlsanity.com/paper/2501.00365/) (2024)
- [Bridging the Gap Between Ideal and Real-world Evaluation: Benchmarking AI-Generated Image Detection in Challenging Scenarios](https://mlsanity.com/paper/2509.09172/) (2025)
- [DNA: Uncovering Universal Latent Forgery Knowledge](https://mlsanity.com/paper/2601.22515/) (2026)
- [Methods and Trends in Detecting AI-Generated Images: A Comprehensive Review](https://mlsanity.com/paper/2502.15176/) (2025)
- [Dual Frequency Branch Framework with Reconstructed Sliding Windows Attention for AI-Generated Image Detection](https://mlsanity.com/paper/2501.15253/) (2025)
- [NS-Net: Decoupling CLIP Semantic Information through NULL-Space for Generalizable AI-Generated Image Detection](https://mlsanity.com/paper/2508.01248/) (2025)
- [Evolving from Single-modal to Multi-modal Facial Deepfake Detection: Progress and Challenges](https://mlsanity.com/paper/2406.06965/) (2024)
- [EvoGuard: An Extensible Agentic RL-based Framework for Practical and Evolving AI-Generated Image Detection](https://mlsanity.com/paper/2603.17343/) (2026)
- [Are Images Indistinguishable to Humans Also Indistinguishable to Classifiers?](https://mlsanity.com/paper/2405.18029/) (2024)
- [CAMEx: Curvature-aware Merging of Experts](https://mlsanity.com/paper/2502.18821/) (2025)
- [DGS-Net: Distillation-Guided Gradient Surgery for CLIP Fine-Tuning in AI-Generated Image Detection](https://mlsanity.com/paper/2511.13108/) (2025)
- [The Cat and Mouse Game: The Ongoing Arms Race Between Diffusion Models and Detection Methods](https://mlsanity.com/paper/2410.18866/) (2024)
- [Fully AI-Generated Image Detection: Definition, Recent Advances and Challenges](https://mlsanity.com/paper/2502.19716/) (2025)
- [HyperDet: Generalizable Detection of Synthesized Images by Generating and Merging A Mixture of Hyper LoRAs](https://mlsanity.com/paper/2410.06044/) (2024)
- [Rethinking the Use of Vision Transformers for AI-Generated Image Detection](https://mlsanity.com/paper/2512.04969/) (2025)
- [INSIGHT: An Interpretable Neural Vision-Language Framework for Reasoning of Generative Artifacts](https://mlsanity.com/paper/2511.22351/) (2025)
- [When Detectors Forget Forensics: Blocking Semantic Shortcuts for Generalizable AI-Generated Image Detection](https://mlsanity.com/paper/2603.09242/) (2026)
- [Detect Fake with Fake: Leveraging Synthetic Data-driven Representation for Synthetic Image Detection](https://mlsanity.com/paper/2409.08884/) (2024)
- [Towards More Accurate Fake Detection on Images Generated from Advanced Generative and Neural Rendering Models](https://mlsanity.com/paper/2411.08642/) (2024)
- [FUSE: Unifying Spectral and Semantic Cues for Robust AI-Generated Image Detection](https://mlsanity.com/paper/2512.21695/) (2025)
- [Beyond Natural Images: Rethinking AI-Generated Image Detection in Documents](https://mlsanity.com/paper/2609.14352/) (2026)

## Abstract (arXiv)

Generative models have shown a giant leap in synthesizing photo-realistic images with minimal expertise, sparking concerns about the authenticity of online information. This study aims to develop a universal AI-generated image detector capable of identifying images from diverse sources. Existing methods struggle to generalize across unseen generative models when provided with limited sample sources. Inspired by the zero-shot transferability of pre-trained vision-language models, we seek to harness the nontrivial visual-world knowledge and descriptive proficiency of CLIP-ViT to generalize over unknown domains. This paper presents a novel parameter-efficient fine-tuning approach, mixture of low-rank experts, to fully exploit CLIP-ViT's potential while preserving knowledge and expanding capacity for transferable detection. We adapt only the MLP layers of deeper ViT blocks via an integration of shared and separate LoRAs within an MoE-based structure. Extensive experiments on public benchmarks show that our method achieves superiority over state-of-the-art approaches in cross-generator generalization and robustness to perturbations. Remarkably, our best-performing ViT-L/14 variant requires training only 0.08% of its parameters to surpass the leading baseline by +3.64% mAP and +12.72% avg.Acc across unseen diffusion and autoregressive models. This even outperforms the baseline with just 0.28% of the training data. Our code and pre-trained models will be available at https://github.com/zhliuworks/CLIPMoLE.