Diffusion-based generators have made synthetic images ubiquitous, but detectors often fail under simultaneous shifts in generator, prompt/style, and source-domain. We study AI-generated image detection as a transfer system described by training prior, frozen encoder feature space, and decision rule, and ask when classifier head training adds value beyond what is already separable in modern features. As a controlled diagnostic, we fit a prior-conditioned Gaussian discriminant ladder: closed-form heads built from first- and second-order feature statistics under nested covariance assumptions. On Percept-Lens, a unified protocol over 39 public datasets (7.1 million images), the best rung is frequently competitive with, and sometimes exceeds, released AI-generated image detector heads when matched on both prior and encoder. We further quantify strong sensitivity to the training prior, data-efficiency of moment-based heads, and representation dependence of Gaussian shift metrics, motivating (prior, encoder, head)-level reporting and stronger analytical baselines for AIGI transfer.
Figures & tables
Figure 1: Training-prior-conditioned Gaussian discriminants in a frozen feature space. A frozen image encoder ϕ maps images x to embeddings z . Given a (possibly few-shot) support set S drawn from a training prior , we estimate class-conditional moments (μc,Σc) and instantiate a ladder of classical closed-form heads under nested covariance assumptions. By keeping the encoder and prior fixed, the ladder isolates what the decision rule contributes.
Figure 2: Gaussian discriminant ladder as nested covariance assumptions. Each rung is a classical generative classifier obtained by restricting the class-conditional covariance: isotropic (Euc-/Cos-NCM), diagonal (GNB), shared full covariance (Mah-NCM), or class-specific full covariance (QDA). This nested family makes it possible to diagnose how much transferable signal is captured by first- and second-order feature statistics.
Assumes spherical class distributions; decision is based on angular proximity, suitable for normalized embeddings.
Gaussian Naive Bayes (GNB)
Diagonal
Σc∈{0,1}=diag(σc,j2)
Non-Linear
Simplest model; assumes feature independence, useful for identifying decorrelated representations.
Mahalanobis Nearest Centroid Matching (Mah-NCM)
Homoscedastic
Σ0=Σ1=Σp
Linear
Assumes classes share the same elliptical shape. It accounts for feature correlations by whitening the space, yielding a correlation-aware linear boundary.
Quadratic Discriminant Analysis (QDA)
Heteroscedastic
Σ0=Σ1
Quadratic
Most general model; allows each class to have a unique elliptical shape and orientation, capturing complex separations.
Table 1: Gaussian discriminant ladder used as analytical baselines. Each rung is a generative classifier obtained by restricting the class-conditional covariance (isotropic, diagonal, homoscedastic, or heteroscedastic), which determines the geometry of the induced decision boundary. We use this ladder to isolate head effects in a fixed frozen encoder feature space rather than to propose a new detector.
Figure 3: Percept-Lens stress-tests detectors under joint distribution shift. Percept-Lens is an evaluation protocol built entirely from existing public datasets. Many AIGI evaluations vary either the generator family or the image source in isolation; we instead evaluate under joint shifts in generator family, prompt/style, and source domain, closer to deployment where these factors drift together.
Table 2: Closed-form Gaussian discriminants versus released AI-generated image detector heads under matched (prior, encoder) conditions. Mean class accuracy CA (dataset-wise balanced accuracy where defined; Section 5.1 ), macro-averaged across Percept-Lens evaluation datasets. For each released detector checkpoint, we report (i) the released decision head ( Out-of-the-Shelf ) and (ii) closed-form baselines fitted on the same frozen encoder features using the corresponding public training prior: Euc-NCM ( Wu et al., 2025b ) and the best-performing rung of the Gaussian ladder. The full ladder is reported in Section 5.2 . (Parentheses indicate the training subset reported by the original work when applicable.)
AI-generated image detection identifies synthetic or AI-edited images and develops methods that generalize across generators, domains, and image transformations.
AI-generated image detectors generalize poorly when their training and test images originate from different generators or datasets. Despite the rich spatial representations produced by vision foundation models like DINO, existing detectors typically classify images using only the globally aggregated CLS token. We hypothesize that globally aggregating DINO features into a single CLS token obscures spatially distributed generation traces. To test this hypothesis, we introduce PatchHead, a lightweight spatial aggregation head that preserves the two-dimensional organization of DINO patch tokens and integrates evidence across neighboring regions. During training, we freeze the pretrained DINO backbone and optimize only the inserted LoRA adapters, PatchHead, and auxiliary projection head. Across nine cross-dataset benchmarks spanning manually curated and in-the-wild settings, PatchHead ranks first on seven datasets and second on the remaining two. It improves the strongest prior method from 91.6% to 94.6% in average balanced accuracy (+3.0 points) and raises the worst-case accuracy from 82.4% to 89.4% (+6.9 points), while introducing only 8.6% more trainable parameters and 0.08% additional FLOPs. Further qualitative analysis suggests that PatchHead (i) reduces class-conditional domain discrepancy, and (ii) redirects the representation from content-dominated saliency toward spatially distributed authenticity evidence. Together, these observations provide a representation-level account of why spatial patch aggregation transfers more reliably across generators and datasets than a single CLS-based global representation. Our code and models will be made available upon acceptance.
Shengbo Qi, Hongyi Fang, Benjia Zhou +1
Beijing Institute of Technology, Zhuhai · Shenzhen University
Generalization remains a critical bottleneck in AI-generated image detection. Because many modern generators are proprietary or adversarially modified, existing detectors overfit to the low-level textural patterns of accessible training data, resulting in severe failures on unseen domains. Conventional regularization techniques (e.g., L1/L2 norms, Dropout) apply indiscriminate parametric constraints and fail to provide the domain-invariant structure necessary for cross-generator robustness. To address this, we propose Feature-Augmented Implicit Regularization (FAIR). FAIR introduces an orthogonal, macro-structural prior, specifically, Scene Composition Structure (SCS), during training to geometrically constrain the model's optimization trajectory. By augmenting the primary feature space with domain-invariant SCS features, FAIR explicitly penalizes texture-biased shortcut learning. Crucially, this structural prior is entirely discarded at inference, yielding a smoothed, generalized decision boundary with zero architectural or computational overhead. Extensive evaluations across five massive benchmarks demonstrate that integrating FAIR into state-of-the-art detectors significantly improves cross-generator generalization, boosting accuracy by up to 8.04% and establishing new state-of-the-art robustness in zero-shot transfer scenarios.
Md Redwanul Haque, Manzur Murshed, Manoranjan Paul +1
Deakin University, Burwood, VIC, Australia · Charles Sturt University, Bathurst, NSW, Australia
Recent advances in AI-Generated Image (AIGI) detection have largely focused on model architectures, loss design, and training strategies, while overlooking a more fundamental factor: how supervision is structured. Existing detectors typically train on benchmark-defined data that implicitly blends semantic and artifact signals, leaving supervision design unexplored. In this paper, we examine supervision structure through controlled experiments and show that such blended supervision is not merely suboptimal but fundamentally counterproductive. Replacing it with disentangled, orthogonal supervision - paired with inductively matched models - suffices to achieve strong cross-generator generalization. We formalize this as Orthogonal Supervision Disentanglement and instantiate it in AlignGemini, a two-branch detector in which a VLM receives purely semantic supervision and a vision expert receives purely artifact supervision. With disentangled supervision coupled with inductively matched models, even the simplest training recipe achieves a significant improvement of 9.5% across five in-the-wild benchmarks - trained on images from only two generators, without complex training strategies or diverse generator coverage. We further introduce AIGI-Now, a diagnostic benchmark covering eight contemporary generators, including five closed-source commercial models, with disentangled semantic and pixel evaluation subsets for fine-grained analysis of detector capabilities. Our code is publicly available at https://github.com/GzZning/Align-Don-t-Blend.
Ruoxin Chen, Jiahui Gao, Kaiqing Lin +5
Tencent Youtu Lab · East China University of Science and Technology · Shenzhen University +1