MiraGe: Multimodal Discriminative Representation Learning for Generalizable AI-Generated Image Detection
This addresses the need for generalizable detectors to combat misinformation from evolving AI generators, though it is incremental as it builds on existing representation learning methods.
The paper tackles the problem of detecting AI-generated images across unseen generative models by proposing MiraGe, which learns generator-invariant features through multimodal discriminative representation learning, achieving state-of-the-art performance with robustness against models like Sora.
Recent advances in generative models have highlighted the need for robust detectors capable of distinguishing real images from AI-generated images. While existing methods perform well on known generators, their performance often declines when tested with newly emerging or unseen generative models due to overlapping feature embeddings that hinder accurate cross-generator classification. In this paper, we propose Multimodal Discriminative Representation Learning for Generalizable AI-generated Image Detection (MiraGe), a method designed to learn generator-invariant features. Motivated by theoretical insights on intra-class variation minimization and inter-class separation, MiraGe tightly aligns features within the same class while maximizing separation between classes, enhancing feature discriminability. Moreover, we apply multimodal prompt learning to further refine these principles into CLIP, leveraging text embeddings as semantic anchors for effective discriminative representation learning, thereby improving generalizability. Comprehensive experiments across multiple benchmarks show that MiraGe achieves state-of-the-art performance, maintaining robustness even against unseen generators like Sora.