- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper addresses the issue that when the number of categories is large in the label noise problem, TDSM incurs significant computational overhead. The authors propose a hybrid label conditioning approach, where the posterior weights are used to linearly combine the learnable category embeddings, and then the mixed conditional prediction is obtained through a forward computation of the denoising network once, thereby reducing the need for individual category calculations. The paper reports the generation quality, category condition consistency, and training time per round under the synthetic label noise settings of CIFAR-10 and CIFAR-100.
Critical strengths
- The author addressed the bottleneck of TDSM, which involves multiple forward calculations of category conditions. By changing the output mixture to category embedding mixture, the repetitive calculations of the denoising network can be reduced, without adding additional modules in the generation stage. This significantly reduces the computational bottleneck and has excellent practical application value.
- The author's experiment was quite comprehensive. Besides generating indicators, the author also reported category-level indicators and included the additional reference predictions required for sample screening in the efficiency statistics. The evaluation dimensions were quite comprehensive.
Critical weaknesses
- By screening samples based on the reconstruction benefits of the current model, there is a possibility of continuously favoring samples that are easier to model, while reducing the training opportunities for difficult samples, rare patterns, or certain noise intervals. The author should further explain how this model avoids the problem of internal imbalance within categories when dealing with rare samples and other issues.
- There is insufficient evidence to explain why mixed-condition training can restore the clean distribution of a single category. The statistical interpretation of TDSM relies on the explicit weighted combination of the scores of each clean category. The manuscript replaces this structure with a general nonlinear function: $s_\theta(x_t,v,t) = F_\theta!\left(x_t,e_{\mathrm{time}}(t)+\sum_i v_iE_i\right). $ The authors correctly point out that the two forms are usually not equivalent. However, the subsequent training directly constrains the mixed-condition prediction corresponding to the estimated posterior , while the category vertices are used during generation. During the noisy stage where the label posterior is less clear, there may be significant differences between the two types of conditions.
- The article mainly focuses on comparing DSM and TDSM, but has not fully covered the recent methods for generating noise labels. Although the paper discusses related works such as SBDC and SPFM, there is a lack of corresponding comparisons or detailed explanations that are not directly comparable, making it difficult to fully assess the relative advantages of the proposed method.
- The experiment was conducted only on the two low-resolution datasets, CIFAR-10 and CIFAR-100, and used artificially constructed category-conditioned label noise. The authors should conduct tests on higher-resolution datasets, such as ImageNet, to make their experimental results more convincing.
Questions for authors
- The zero-condition branch has no explicit unconditional training objective. How can it serve as a reliable screening reference?
- The author in Equation (12) acknowledges that the embedding mixture and output mixture in nonlinear networks are not equivalent. Furthermore, the training mainly uses soft mixed conditions, while generation uses one-hot conditions. The connection between the two still needs to be explained.