- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
The manuscript proposes a cross-layer representation modeling for the problem of few-shot AI-generated image detection and generator attribution. It combines information from intermediate and final layers of a frozen image encoder through bidirectional cross-attention. A prototypical network applied as a standard application for few-shot image classification problem. Experiments evaluate transfer to unseen generators, different image encoders, and the perturbation condition.
Critical strengths
-
Evidence of generalization across generators and model architectures. The method performs well on unseen generators and improves results with diferent architectural encoders. The prototype-based design also allows adaptation using a small labeled support set without retraining at test time. However, the contribution of prototypical learning itself is not separately established.
-
An interesting observation about intermediate and final features. The observation of using cross-layer behaviour between final and intermediate layers as a measurement for AI generated image detector is interesting
Critical weaknesses
- Limited few-shot evaluation settings and missing recent baselines . The main training setup is 3-way 5-shot. Although several more classification tasks are evaluated, the results do not show how the method behaves with fewer or more shots settings. Furthermore, there are some recent baselines seems to be missing such as [1,2]
[1] Diversity over Uniformity: Rethinking Representation in Generated Image, CVPR 2026
[2] Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samples, ECCV 2026
- The specific benefit of cross-layer modeling is not fully developed.
FSD already uses prototype-based few-shot learning, so the main new contribution in this paper lies in the representation module. It would be more interesting to test CLRM as an add-on to other detection frameworks, because it would further show whether its benefits extend beyond this current prototype-based setup. The ablation also does not fully isolated the improved performance comes from cross-layer modeling or prototypical networkmodeling
Questions for authors
-
How does the proposed method deal with the problem of imbalanced data in binary classification setting, where the number of fake samples should be much more than the number of real samples?
-
Could the authors report results with variant number of shots such as (1, 5, 10)?
-
Does the method also work when comparing two intermediate layers instead of comparing with the final layer? A small experiment might be adequate for this. It would be interesting to see if this method could also work.
4 comments
Rebuttal #2
4. Additional ablation variants
We extend the architectural analysis with MLP alternatives that incorporate patch tokens and with a bidirectional inner-layer attention control. The results are averaged over 6 subsets (M, G, A, S, V, B).
| Architecture | Binary classification (%) | Source attribution (%) |
|---|---|---|
| (i) MLP (class tokens only), variant (c) | 92.9 | 82.2 |
| (ii) MLP (class tokens + mean-pooled patch tokens) | 93.4 | 85.3 |
| (iii) MLP (class tokens + flattened patch tokens) | 92.2 | 83.3 |
| (iv) Bidirectional inner-layer attention | 95.3 | 87.9 |
| (v) Bidirectional cross-layer attention (CLRM) | 95.9 | 88.8 |
(ii) receives the class tokens and the mean-pooled patch tokens of both layers. (iii) retains all 196 patch positions after a learned per-token 768→8 projection before MLP fusion. Both underperform CLRM despite having access to the same inputs, so the gains cannot be explained by the mere inclusion of intermediate and final CLIP features.
(iv) The inner-layer control uses Proj([CA(f_cls, f_pat, f_pat); CA(g_cls, g_pat, g_pat)]), maintaining two attention branches but restricting each branch to a single layer. It performs competitively, demonstrating that class–patch attention itself is useful. However, CLRM further improves both binary classification and source attribution. This controlled comparison supports an additional benefit from cross-layer rather than only within-layer correspondence.
To further isolate the effect of directionality from additional parameters, we also trained a two-branch unidirectional control that concatenates CA(f_cls, g_pat, g_pat; θ₁) and CA(f_cls, g_pat, g_pat; θ₂) with independent parameters, matching CLRM’s two-branch capacity.
| Architecture | Binary Classification (%) | Source Attribution (%) |
|---|---|---|
| Single-direction cross-layer attention - variant (e) | 94.1 | 85.3 |
| Two parallel copies of the same direction | 94.8 | 87.7 |
| Opposite-direction branches (CLRM) | 95.9 | 88.8 |
The parallel control improves upon the single branch but remains 1.1 points below CLRM on both tasks. Therefore, the improvement is not solely attributable to doubling the number of attention branches. The reverse-direction relationship contributes additional information.
5. Class imbalance
Our episodic training samples an equal number of support and query examples per selected class, even when the available training pool contains many more fake images than real images. This prevents the episode-level learning objective from being dominated by the more frequent class. To assess sensitivity to the size of the underlying class pools, we further reduced either the real-image pool or the fake-image pool to 1% of its original size, while keeping the other pool unchanged.
| Real training pool retained | Fake training pool retained | Binary acc. (%) | Attribution acc. (%) |
|---|---|---|---|
| 100% | 100% | 95.9 | 88.8 |
| 1% | 100% | 95.9 | 88.3 |
| 100% | 1% | 94.8 | 84.9 |
CLRM is robust to training-pool imbalance; reducing the fake pool mainly lowers attribution accuracy, as fewer images per generator remain.
6. Alternative two intermediate layers
We replaced the original pair (block 5 + final block) with blocks 3 and 9, and retrained CLRM with all other settings unchanged.
| Layer configuration | Binary acc. (%) | Attribution acc. (%) |
|---|---|---|
| Final-layer class token only | 92.8 | 71.7 |
| CLRM: blocks 3 and 9 | 94.9 | 86.4 |
| CLRM: block 5 and final block | 95.9 | 88.8 |
Using two intermediate layers substantially outperforms the final-layer-only baseline. The original block-5/final configuration remains strongest, but the intermediate/intermediate result shows that CLRM does not require the final block and can model informative class–patch correspondence between two intermediate depths of a frozen encoder.
We thank the reviewer again for the constructive comments. We will carefully incorporate them, together with the additional results above, into the revised manuscript.
Further Analysis
Why cross-layer pairing helps
We would like to share an additional analysis on the benefits of cross-layer modeling. In our earlier response, the bidirectional inner-layer attention control (variant (iv) of the additional ablation table) reached 95.3% / 87.9% in binary classification / source attribution, close to CLRM's 95.9% / 88.8%. This control is identical to CLRM in architecture, parameter count (4.7M), and training, and the only difference is whether each class token attends to the patch tokens of its own layer or of the other layer. It therefore isolates the effect of cross-layer pairing. To examine whether this effect is specific to CLIP, we repeated the comparison on DINOv2 (ViT-B/14), following the setting of Sec. 5.3 of the paper.
Binary / attribution accuracy (%), 5-shot, averaged over the six leave-one-generator-out splits. | Backbone | Bidirectional inner-layer attention | Cross-layer attention (CLRM) | Gain from cross-layer pairing | |---|---|---|---| | CLIP ViT-B/16 | 95.3 / 87.9 | 95.9 / 88.8 | +0.6 / +0.9 | | DINOv2 ViT-B/14 | 85.6 / 82.2 | 87.0 / 83.9 | +1.4 / +1.7 |
Cross-layer pairing improves both tasks on both backbones, and the gain on DINOv2 is about twice that on CLIP.
Why cross-layer pairing helps. Cross-layer pairing exposes the mismatch between depths, which Fig. 1 shows to be generator-dependent. CLRM is designed around this: its attention (Eqs. 3-4) relates the class token of one layer to the patch tokens of the other, whereas the inner-layer control relates tokens within the same layer. Within a layer, the class token and the patch tokens are entangled. Specifically, at every block, ViT self-attention relates the class token to the patch tokens of the same depth, and pre-training optimizes this relation jointly with the tokens themselves. The within-layer correspondence therefore largely follows the encoder's own aggregation and captures less of the mismatch, and the inner-layer control combines the two depths only after aggregating each separately. In contrast, the encoder's self-attention never relates tokens of different depths, so the cross-layer correspondence reflects how the image changes between depths. This reasoning applies to ViT encoders in general, in line with the DINOv2 result. We believe this is why cross-layer pairing adds a consistent gain on top of class–patch attention: attention provides the mechanism for selecting evidence, and cross-layer pairing determines what that selection measures.
We hope this additional analysis further clarifies the contribution of cross-layer modeling, and we would be glad to answer any further questions.
Reminder
Thank you again for your review and valuable feedback.
We have provided detailed responses to your comments and uploaded a revised manuscript incorporating the corresponding changes.
We would greatly appreciate it if you could take a moment to review our responses and the updated manuscript. Please let us know if you have any remaining questions or concerns, and we would be happy to address them.
Thank you for your time and consideration.
Rebuttal #1
We thank the reviewer for the valuable suggestions concerning shot sensitivity, recent related work, transferability to other detection frameworks, class imbalance, and layer selection. We have added experiments addressing these points. Throughout, M, G, A, S, V, and B denote Midjourney, GLIDE, ADM, Stable Diffusion, VQDM, and BigGAN.
1. Shot ablation study
We report 1-, 3-, 5-, and 10-shot results for both binary classification and source attribution.
1-1. Binary classification accuracy (%)
1-2. Generator source attribution accuracy (%)
CLRM achieves the highest accuracy at every shot count.
2. Recent baselines
We appreciate the references. Diversity over Uniformity uses anti-feature-collapse learning to preserve diverse forgery cues for cross-generator detection, whereas we construct cross-layer class-patch correspondence representations for few-shot adaptation. Few-Shot Synthetic Image Attribution introduces the OmniFake dataset and the OmniDFA framework, which jointly addresses authenticity detection and few-shot source attribution with an emphasis on unseen generators.
We trained OmniDFA on GenImage under our leave-one-generator-out protocol. With 5-shot prototype-based evaluation, OmniDFA representations obtain 85.2% binary accuracy, and OmniDFA obtains 85.8% with its own zero-shot binary detector. Because OmniDFA's main strength comes from large-scale training on OmniFake, which our GenImage setting does not provide, these numbers should not be read as a direct comparison with Table 1.
We further integrated CLRM into OmniDFA. In each TwinNeXt branch, CLRM relates a middle ConvNeXt stage to the last stage, with the global-average-pooled feature as the class token and the spatial positions as patch tokens; the concatenated outputs replace the pooled backbone features before OmniDFA's projection head, and OmniDFA's training losses are unchanged. This improves the few-shot and zero-shot binary accuracy to 86.6% and 87.6% (+1.4 / +1.8), indicating that CLRM is complementary to OmniDFA.
3. CLRM with other detectors
We agree that this is an important test of generality. We therefore applied CLRM-style cross-layer relational modeling to three different feature-extraction frameworks: FSD (ResNet-based), DINOv2, and DRCT. The results below are leave-one-generator-out 5-shot average accuracies on GenImage. DINOv2 rows are from Table 5 of the paper.
For FSD (ResNet-50), we use the outputs of the 2nd and 4th residual stages. The globally pooled feature of each stage serves as its class token and the spatial positions of its feature map serve as patch tokens. Because the two stages have different channel dimensions, we project them to a common dimension with a 1×1 convolution before cross-attention.
For DRCT, we use its CLIP version (a frozen CLIP ViT-L/14 followed by a trainable 1024-d embedding layer) and retrain it under our few-shot protocol: DRCT's binary cross-entropy is replaced by the prototypical loss, while its contrastive loss on diffusion-reconstructed images (α = 0.3). Reconstructions are generated online with the Stable Diffusion VAE. DRCT + CLRM differs only in the input to this embedding layer: instead of CLIP's projected class token, it receives the CLRM output computed between the outputs of block 12 (intermediate) and block 24 (final) of the frozen CLIP ViT-L/14.
Adding CLRM improves the average accuracy of both tasks for all three feature extractors, with the largest gains in attribution.