# Test-Time Curriculum for Open-Set AIGC Detection

arXiv: https://arxiv.org/abs/2608.00559 · HTML: https://mlsanity.com/paper/2608.00559/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 45 of its 73 references that are in the map.
- First posted on arXiv 1 Aug 2026.

## Builds on (most cited first, 30 of 45)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [Deep Clustering for Unsupervised Learning of Visual Features](https://mlsanity.com/paper/1807.05520/) (2018)
- [CNN-generated images are surprisingly easy to spot... for now](https://mlsanity.com/paper/1912.11035/) (2019)
- [Path Aggregation Network for Instance Segmentation](https://mlsanity.com/paper/1803.01534/) (2018)
- [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)
- [Efficient Test-Time Model Adaptation without Forgetting](https://mlsanity.com/paper/2204.02610/) (2022)
- [Improving robustness against common corruptions by covariate shift adaptation](https://mlsanity.com/paper/2006.16971/) (2020)
- [Towards Stable Test-Time Adaptation in Dynamic Wild World](https://mlsanity.com/paper/2302.12400/) (2023)
- [BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset](https://mlsanity.com/paper/2505.09568/) (2025)
- [A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts](https://mlsanity.com/paper/2303.15361/) (2023)
- [GenImage: A Million-Scale Benchmark for Detecting AI-Generated Image](https://mlsanity.com/paper/2306.08571/) (2023)
- [Infinity: Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis](https://mlsanity.com/paper/2412.04431/) (2024)
- [Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer](https://mlsanity.com/paper/2511.22699/) (2025)
- [Seedream 4.0: Toward Next-generation Multimodal Image Generation](https://mlsanity.com/paper/2509.20427/) (2025)
- [Evaluating Prediction-Time Batch Normalization for Robustness under Covariate Shift](https://mlsanity.com/paper/2006.10963/) (2020)
- [Robust Test-Time Adaptation in Dynamic Scenarios](https://mlsanity.com/paper/2303.13899/) (2023)
- [Forgery-aware Adaptive Transformer for Generalizable Synthetic Image Detection](https://mlsanity.com/paper/2312.16649/) (2023)
- [HunyuanImage 3.0 Technical Report](https://mlsanity.com/paper/2509.23951/) (2025)
- [Emu3.5: Native Multimodal Models are World Learners](https://mlsanity.com/paper/2510.26583/) (2025)
- [Detecting GAN generated Fake Images using Co-occurrence Matrices](https://mlsanity.com/paper/1903.06836/) (2019)
- [Cycle Self-Training for Domain Adaptation](https://mlsanity.com/paper/2103.03571/) (2021)
- [LongCat-Image Technical Report](https://mlsanity.com/paper/2512.07584/) (2025)
- [Improving Synthetic Image Detection Towards Generalization: An Image Transformation Perspective](https://mlsanity.com/paper/2408.06741/) (2024)
- [Detecting GAN-generated Imagery using Color Cues](https://mlsanity.com/paper/1812.08247/) (2018)
- [FakeInversion: Learning to Detect Images from Unseen Text-to-Image Models by Inverting Stable Diffusion](https://mlsanity.com/paper/2406.08603/) (2024)
- [Dual Data Alignment Makes AI-Generated Image Detector Easier Generalizable](https://mlsanity.com/paper/2505.14359/) (2025)
- [Uni-cot: Towards Unified Chain-of-Thought Reasoning Across Text and Vision](https://mlsanity.com/paper/2508.05606/) (2025)

## Abstract (arXiv)

AI-generated image detectors deployed in open-world environments inevitably face distribution shifts as new and stronger generative models continue to emerge. Although existing methods improve cross-generator generalization through better representations or training data construction, they typically follow a static train-once-and-deploy paradigm and cannot adapt after deployment. In this work, we study open-set AIGC image detection from a test-time adaptation perspective. We propose Test-Time Curriculum (TTC), a simple and model-agnostic framework that adapts a detector on unlabeled test data through curriculum-based self-training. TTC starts from highly reliable pseudo-labeled samples and progressively incorporates harder yet informative cases, while enforcing class-balanced selection to reduce biased updates under generator shift. To further improve pseudo-label quality, we introduce Cross-Scale Pseudo-Label Refinement, which aggregates complementary evidence across multiple resolutions for more reliable adaptation, and applies noisy-or fusion at inference to strengthen final predictions. In addition, we construct AIGCGuard, a new benchmark containing 3,100 representative real images and 124,000 generated images from 40 of the most advanced open-source and proprietary text-to-image models. Extensive experiments on five benchmarks show that TTC substantially improves overall detection performance under diverse unseen-generator shifts, establishing a practical and effective test-time adaptation framework for open-set generated image detection.