Images as Tables: In-Context Learning with TabPFN for Low-Data Detection of AI-Generated Images

• URL: http://arxiv.org/abs/2606.00872v1
• Date: Sat, 30 May 2026 20:00:25 GMT
• Title: Images as Tables: In-Context Learning with TabPFN for Low-Data Detection of AI-Generated Images
• Abstract summary: Detectors trained on one generator often fail when a new generator appears.<n>We study a simple image-to-table formulation for this regime, where each image is encoded by a frozen DINOv3 backbone.<n>We find that DINOv3-PCA-TabPFN is stronger in the practically important low-data regime.
• Score: 21.11425002008934
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: AI-generated image detection is a moving-target problem: detectors trained on one generator often fail when a new generator appears, and only a few labeled examples are available. We study a simple image-to-table formulation for this regime, where each image is encoded by a frozen DINOv3 backbone, its CLS feature is reduced to a 500-dimensional structured row with PCA, and TabPFN performs real/fake classification by in-context tabular inference rather than task-specific classifier training. This turns fake-image detection into low-data structured prediction over learned visual features, making detector adaptation depend on the labeled context set instead of gradient-based fine-tuning. On GenImage, LATTE, a recent state-of-the-art detector, remains stronger when many labeled samples from all generators are available, by 7.4% in the largest pooled setting, but DINOv3-PCA-TabPFN is stronger in the practically important low-data regime, outperforming LATTE by up to 8.2%, and in transfer settings where the detector must generalize from one generator to another. These results position tabular foundation models as a strong complementary adaptation mechanism for image forensics, shifting adaptation from detector retraining to lightweight in-context updates with a small labeled set of examples. Code URL: https://github.com/jpwalter30/Towards-Generalizable-Detection-of-AI-Generated-Images

Related papers

• Test-Time Curriculum for Open-Set AIGC Detection [31.702537861903014]
  Test-Time Curriculum (TTC) adapts a detector on unlabeled test data through curriculum-based self-training.<n>TTC starts from highly reliable pseudo-labeled samples and incorporates harder yet informative cases.<n>Cross-Scale Pseudo-Label Refinement aggregates complementary evidence across multiple resolutions for more reliable adaptation.
  arXiv  Detail & Related papers  (2026-08-01T09:42:45Z)
• Where Detectors Fail: Probing Generative Space for Generalizable AI-Generated Image Detection [69.6123714120735]
  Detecting AI-generated images (AIGI) remains challenging because detectors often fail to generalize to unseen generators.<n>We propose PROBE, a framework that improves detector generalization by actively exploring challenging regions of the generative process.
  arXiv  Detail & Related papers  (2026-05-24T07:15:06Z)
• SubspaceAD: Training-Free Few-Shot Anomaly Detection via Subspace Modeling [6.476948781728136]
  SubspaceAD is a training-free method for detecting visual anomalies in industrial images.<n>It works across one-shot and few-shot settings without training, prompt tuning, or memory banks.<n>It achieves image-level and pixel-level AUROC of 98.0% and 97.6% on the MVTec-AD dataset, and 93.3% and 98.3% on the VisA dataset.
  arXiv  Detail & Related papers  (2026-02-26T13:52:57Z)
• Advancing Weakly-Supervised Change Detection in Satellite Images via Adversarial Class Prompting [49.15470825004932]
  We propose an Adversarial Class Prompting (AdvCP) method to address this co-occurring noise problem.<n>Our AdvCP can be seamlessly integrated into current WSCD methods without adding additional inference cost.
  arXiv  Detail & Related papers  (2025-08-24T02:02:16Z)
• Towards Generalizable AI-Generated Image Detection via Image-Adaptive Prompt Learning [33.269644831847636]
  Image-Adaptive Prompt Learning (IAPL) is a novel paradigm that adjusts the prompts according to each input image, rather than fixing them after training.<n>IAPL achieves state-of-the-art performance, with mean accuracies of 95.61% and 96.7% on the widely used UniversalFakeDetect and GenImage datasets.
  arXiv  Detail & Related papers  (2025-08-03T05:41:24Z)
• FakeInversion: Learning to Detect Images from Unseen Text-to-Image Models by Inverting Stable Diffusion [18.829659846356765]
  We propose a new synthetic image detector that uses features obtained by inverting an open-source pre-trained Stable Diffusion model. We show that these inversion features enable our detector to generalize well to unseen generators of high visual fidelity. We introduce a new challenging evaluation protocol that uses reverse image search to mitigate stylistic and thematic biases in the detector evaluation.
  arXiv  Detail & Related papers  (2024-06-12T19:14:58Z)
• Raising the Bar of AI-generated Image Detection with CLIP [50.345365081177555]
  The aim of this work is to explore the potential of pre-trained vision-language models (VLMs) for universal detection of AI-generated images. We develop a lightweight detection strategy based on CLIP features and study its performance in a wide variety of challenging scenarios.
  arXiv  Detail & Related papers  (2023-11-30T21:11:20Z)
• Simple Open-Vocabulary Object Detection with Vision Transformers [51.57562920090721]
  We propose a strong recipe for transferring image-text models to open-vocabulary object detection. We use a standard Vision Transformer architecture with minimal modifications, contrastive image-text pre-training, and end-to-end detection fine-tuning. We provide the adaptation strategies and regularizations needed to attain very strong performance on zero-shot text-conditioned and one-shot image-conditioned object detection.
  arXiv  Detail & Related papers  (2022-05-12T17:20:36Z)
• A Hierarchical Transformation-Discriminating Generative Model for Few Shot Anomaly Detection [93.38607559281601]
  We devise a hierarchical generative model that captures the multi-scale patch distribution of each training image. The anomaly score is obtained by aggregating the patch-based votes of the correct transformation across scales and image regions.
  arXiv  Detail & Related papers  (2021-04-29T17:49:48Z)
• CutPaste: Self-Supervised Learning for Anomaly Detection and Localization [59.719925639875036]
  We propose a framework for building anomaly detectors using normal training data only. We first learn self-supervised deep representations and then build a generative one-class classifier on learned representations. Our empirical study on MVTec anomaly detection dataset demonstrates the proposed algorithm is general to be able to detect various types of real-world defects.
  arXiv  Detail & Related papers  (2021-04-08T19:04:55Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.