- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper explores the root cause of the high consistency between diffusion classifiers and human perception, as well as how the ability of diffusion classifiers to align with humans can be extended to ordinary classifiers. Therefore, the author proposes DISC, a classifier based on curve-driven methods, which maintains accuracy on clean data while narrowing the gap in shape deviation compared to diffusion classifiers, and improves robustness to data corruption and distribution shifts. Additionally, the curve performs better than the constant guidance in ADM-64 and DiT-XL/2 samplers.
Critical strengths
-
DISC transfers the useful properties of complex and resource-consuming generative models to ordinary classifiers. Moreover, DISC achieved an accuracy rate of 78.6% on clean data, and has demonstrated excellent performance in multiple scenarios with distribution shifts. The experimental results show that DISC can improve corrosion robustness while maintaining a high accuracy rate. It has good practicality and application value.
-
The author conducted extensive ablation experiments, conducting experiments under multiple seeds and making comparisons. The experimental results are convincing, and the author clearly stated that the contribution of a single sample could be negative, and provided curve comparisons for different sample sizes.
Critical weaknesses
-
The paper directly converts the KL contribution of the noise layer to the teacher's final prediction into the label smoothing coefficient. However, the meanings of the two are not equivalent: the KL contribution measures the degree to which the running prediction is close to the teacher's final output, while the label confidence should reflect the reliability of the category information in the current noise input. The position where the decision is formed is not necessarily equal to the position where the information is reliable, and the two are not naturally equivalent. It is suggested that the authors clarify the basis and applicable conditions of this mapping.
-
The paper uses the attribution curve itself as the noise sampling distribution, and uses its cumulative quantity as the label smoothing coefficient. The former determines the training allocation at each noise level, while the latter determines the confidence level of the supervisory signal. The two functions are different, and there is insufficient basis for this. It is suggested that the authors explain separately the two design choices. Why can the same attribution curve provide reasonable basis for both of them at the same time?
-
How many independent noise samples were used for the single noise level baseline? Can it provide the result of averaging scores with a fixed noise level and the same number of evaluation times for the model?
-
Have you compared the noise distribution after adjusting parameters within the same budget, such as log-normal sampling, combined with SNR label smoothing or fixed label smoothing? For Table 3, how did the original SNR label scheme perform at a 60% noise ratio?
Questions for authors
- Under the same sampler, number of steps and parameter adjustment budget, how does the curve in this paper compare with the one guided by a finite interval?
- Please clarify how the input normalization during DISC training is mapped to the sampling state of ADM, and whether the corresponding gradient scaling is included in the implementation.
3 comments
Reminder to Reviewer ABdN
Dear Reviewer ABdN,
We would like to kindly follow up on our rebuttal. We would appreciate any further feedback, and we would be glad to address any remaining concerns before the discussion closes.
Thank you again for your time and consideration.
Reply to rebuttal
Thank you for the detailed response. The clarification of the methods for W1 and W2, along with the additional experiments, helps readers better understand the motivation behind the proposed approach. The explanation that and are derived from the same underlying measurement, with representing its cumulative form, clarifies their relationship. The ImageNet ablation studies also support the usefulness of both components. Furthermore, the note regarding the revised experiments using 250 noise levels addresses my concern about relying on a single sampling noise level. Overall, the authors’ responses have resolved my concerns, and I find the contributions of this paper to be highly meaningful. I therefore increase my rating from “Weak Rejection” to “Weak Acceptance.”
Thank you for the careful review. We answer W1 and W2 first; revisions are mainly led by these.
W1 and W2. The basis of the method. We added it to the Introduction ("How an ordinary classifier can have it", L100–143) and to Sec. 3.1 (L246–254). In the paper's words:
W1. Points 3 and 4 above give the basis, and point 6 the conditions. We checked them (new App. B): the diffusion classifier is 96.5% accurate on the images used for the curves. The curves recomputed with gains in the log-probability of the GT label, instead of reductions in KL to the full prediction, are close to ours (Fig. 6b,c), and a classifier trained with them gives results similar to the original DISC (Table 5; L864–869). On the reliability of the class information in the noisy input: the gap between the class-conditional and the unconditional denoising error, which prior work links to mutual information, overlaps wgen (Fig. 6b; L875–882).
W2. Points 4 and 5 above: both curves come from one measurement. wgen is the contribution of each noise level, so we draw more training samples where the decision is formed. ρ is its cumulative sum, which sets the label confidence. There is no free parameter. Fig. 2b ablates the importance of combining the two visually on the checkerboard. Table 2 ablates this on ImageNet: removing wgen lowers clean accuracy from 73.6 to 64.0, and removing ρ lowers it to 71.0.
W4. Log-normal sampling; SNR labels at 60% noise.
W3. Noise draws at the single noise level. In the submission, the single-level rows of Table 1 used one noise draw; they now use 250, as many evaluations as 250 levels. Aggregation still adds +7.6 / +10.2 / +4.7 in shape bias / OOD accuracy / error consistency for EDM, and +5.0 / +17.2 / +9.5 for Stable Diffusion.
Q1. Guidance limited to an interval. We added it on DiT-XL/2 with the same sampler, number of steps and samples, sweeping the guidance weight for each method (new Table 6; App. D, L1001–1007). The interval alone reaches FID 1.99, better than wgen alone (2.11). wgen inside the interval is the best: 1.73.
Q2. Input normalization and gradient scaling. Yes. The ADM state xt is normalized to the input that DISC saw in training at the corresponding noise level. The gradient is taken with respect to xt, so it needs no separate rescaling (new App. D).