- Rating
- 3
- Confidence
- 3(+1)
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
Chain of Evidence localizes forged content in images and videos using a frozen SAM 3 backbone. An evidence transformer extracts multiscale forensic cues from clean and noise-perturbed features, guiding feature refinement, mask prompting, and forgery detection. A lightweight causal memory then incorporates preceding frames, with video training updating only the memory and presence head. The paper also introduces a gated spatiotemporal evaluation protocol that penalizes missed forged frames and false-positive masks within forged videos. Evaluation across seven image and five video benchmarks shows strong image localization and substantial video-adaptation gains for local edits, while documenting weaker transfer to whole-segment generation.
Critical strengths
-
A well-motivated, parameter-efficient image-to-video design. Learning forensic cues from diverse image data and freezing that representation during video adaptation directly addresses scarce video mask annotations (Section 3). The evidence-guided segmentation and compact causal memory form a coherent approach, with only 8.57M parameters trained in the video stage.
-
Broad evaluation with substantial gains and transparent limitations. Average localization IoU reaches 0.299 versus 0.218 for the strongest baseline on four jointly unseen image datasets; video adaptation raises AINPAINT ST from 0.162 to 0.420 (Tables 2–3). The joint evaluation, corruption tests, and explicit failure analysis make the findings particularly useful.
Critical weaknesses
-
The memory contribution is not fully isolated. The framewise comparison removes both memory and the video-retrained presence head (Section 4.4). A presence-head-only adaptation control would clarify how much of the gain specifically requires temporal context.
-
The image-stage mechanism needs more targeted ablation. The results establish the full system’s effectiveness, but do not isolate the benefit of perturbation-derived evidence from clean-feature adaptation or the multiscale transformer (Section 3.2). These controls would strengthen the architectural claims.
Questions for authors
- Are results available for video adaptation of the presence head alone, without temporal memory?
- Do existing ablations compare perturbation-derived evidence with clean features alone under the same backbone and training data?
Reply to Reviewer Gup1
We thank the reviewer for the positive assessment and for the two controls suggested. Both have now been run.
Weaknesses
[AW1] Yes, and Table A in the general comment is exactly this control. Retraining the presence head on video without a memory leaves all three scores at the framewise level, and adding the memory brings the whole gain. The improvement does need temporal context. Table A will go into Section 4.4.
[AW2] Table C in the general comment isolates each piece on the same backbone and training data. Every removal lowers the mean L. No variant beats the full model on any test set. Clean features alone cost the most (see Q2).
Questions
[AQ1] Yes. Row 2 of Table A in the general comment is this setting: the same frozen image stage, the presence head retrained on the video data, and no memory. FakeParts ST goes from .099 to .113, AINPAINT ST from .162 to .160 and TVIL T from .133 to .121, so the head alone stays at the framewise level. Adding the memory (row 3) brings ST to .425 and .420 and TVIL T to .370.
[AQ2] Not in the submission. Table C in the general comment adds this comparison. The clean-only row keeps the backbone, the adapters, the training dataset, the hyperparameters and the seed, and replaces the perturbed view with a second copy of the clean image, so the difference channels are zero and the model is a plain SAM 3 adaptation. Its L is lower on all four test sets, by .023 on BBC-PAIR, .029 on SID-Set, .012 on DiffSeg30k and .046 on BR-Gen, and the mean drops from .457 to .430. The revision will add Table C to Section 4.4.
We hope this addresses the reviewer's points and would be glad to answer anything further.