- Rating
- 3
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes an image editing method that uses ControlNet to generate camouflage on images, with both image-level and scene-level generation approaches, achieving better attack effects while preserving the vehicle structure and improving visual concealment for the human eye.
Critical strengths
- For the first time, the camouflage attacks on real images are formalized as a way to fine-tune a control net, which is very novel, and two specific camouflage strategies are proposed.
- The attack is highly effective, capable of reducing the detector's AP 50 by more than 38%.
- A complex loss combination is designed to ensure that the generated paint patterns meet expectations.
- Significant improvement compared to other baselines.
Critical weaknesses
- Ablation experiments on the effects of the two stages should include in the main text and need quantitively result.
- Lack the human experiments details, like the number of participants.
Questions for authors
Same as weakness
4 comments
Follow-up on Our Rebuttal
Dear Reviewer xYfZ,
Thank you again for your valuable feedback and for taking the time to review our paper.
As the discussion period is approaching its end, with approximately three days remaining, we would like to kindly follow up on our response submitted three days ago. We hope our responses have adequately addressed your questions and concerns.
If there are any remaining concerns or points that require further clarification, we would greatly appreciate your feedback and would be happy to provide additional explanations before the discussion deadline.
Thank you again for your time and consideration.
Best regards, The Authors
Thank the authors for the detailed response. My concerns have been addressed with the revised claim and additional experiments. I will keep my previous score.
Thank you for your feedback and for supporting our previous rebuttal.
Dear Reviewer xYfZ,
Thank you for your feedback and for supporting our work and rebuttal.
Response to Reviewer xYfZ
W1. Quantitative ablation of the two-stage design.
Table 1. Ablation Study (Image-Level, Faster-RCNN). We report AP50, SSIM, LPIPS, and SWD on COCO and LINZ. SSIM and LPIPS are computed on grayscale crops around each vehicle following reviewer QR3f Q3/Q5. SSIM values therefore differ from those in the original submission. Bold = best, italic = second best.
Table 2. Ablation Study (Scene-Level, Faster-RCNN).
We thank the reviewer for this suggestion. We added a quantitative ablation of the two-stage design under the same total training budget and hyperparameters (Table 1 and Table 2 in this response), comparing one-stage joint training, two-stage training without the color-consistency loss Lc, and the complete model, using AP50 for attack effectiveness, SSIM and LPIPS for structural preservation, and reference-style SWD for appearance consistency. The results support our motivation that jointly optimizing all objectives is unstable: one-stage training sacrifices attack effectiveness, structural preservation, or both in every setting, and its AP50 varies widely across settings, from 8.8% on COCO scene-level to 59.7% on LINZ scene-level, whereas the complete model remains between 15.0% and 27.5%. For example, on LINZ image-level, two-stage training without Lc reduces AP50 from 36.4% to 29.1% compared with one-stage training, and the complete model further reduces it to 18.3% while lowering reference-style SWD from 0.090 to 0.074. Overall, the complete model achieves lower SWD than one-stage training in all four settings and lower AP50 in three of the four; the exception is COCO scene-level, where one-stage training yields a stronger attack (8.8% vs. 16.6%) at the cost of lower structural and style consistency (SSIM 0.786 vs. 0.802; SWD 0.129 vs. 0.107).
As the reviewer suggests, we moved this quantitative ablation into Section 4.3 (page 9) of the revised manuscript, alongside the qualitative examples.
W2. Human evaluation details.
We thank the reviewer for pointing this out and we provide the participant statistics below. In the comparison with existing methods (Appendix D.2), we recorded 758 responses from 26 participants, 22 of whom completed all 30 questions (15 image-level and 15 scene-level), drawn from a pool of 30 images covering 10 scene types with three images each. In the ablation study (Appendix D.3), 15 participants each answered 10 questions randomly drawn from image-level groups on COCO and LINZ. We received 144 responses. The complete model was preferred over its ablation variants in 94.6% (95% CI: 86.9–97.9%) of COCO responses and 71.4% (95% CI: 60.0–80.7%) of LINZ responses, well above the chance rate of 33.3%. All participants were unpaid volunteers, and in both studies the options were unlabeled and presented in randomized order, which means participants were blind to the method. Confidence intervals are 95% Wilson score intervals.
We added participant and response counts in Appendix D.2 (page 26) and Appendix D.3 (page 27), including the COCO/LINZ response breakdown for the ablation study. We hope these additions address the reviewer's concerns, and we thank the reviewer again for the positive assessment of our work.