DEDCA: Test-Time Adaptation for Generalized AI-Generated Image Detection
cs.CV
Submitted: 2026-11-12
Updated: 2026-11-12
Terminology
Sources
- Large Scale GAN Training for High Fidelity Natural Image Synthesis
- Adam: A Method for Stochastic Optimization
- Is Artificial Intelligence Generated Image Detection a Solved Problem?
- Think Twice before Adaptation: Improving Adaptability of DeepFake Detection via Online Test-Time Adaptation
- GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models
- Towards Stable Test-Time Adaptation in Dynamic Wild World
- Rethinking the Use of Vision Transformers for AI-Generated Image Detection
- ReservoirTTA: Prolonged Test-time Adaptation for Evolving and Recurring Domains
- Tent: Fully Test-time Adaptation by Entropy Minimization
- Few-Shot Learner Generalizes Across AI-Generated Image Detection
- MIRAGE: Towards AI-Generated Image Detection in the Wild
- MLEP: Multi-granularity Local Entropy Patterns for Universal AI-generated Image Detection
- COME: Test-time adaption by Conservatively Minimizing Entropy
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs