- Rating
- 3
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
This paper introduces Spike-by-Spike Diffusion, which replaces stage-level execution with trajectory-level execution in SNN for Diffusion model. It makes each SNN step pass through all denoising stages and refines the output in the same inference process. It also designs an incremental scheduler to ensure the consistency in the accumulation of increments across stages. It further proposes a step-sensitive multi-threshold neuron and a two-stage calibration method to improve generation accuracy without modifying pretrained weights.Experimental results shows that this method offers advantages in both final generation quality and energy consumption.
Critical strengths
-
The trajectory-level SNN execution proposed by Spike-by-Spike Diffusion solves the problem of SNN diffusion models being unable to perform terminal image readout before the last timestep by making the complete diffusion trajectory the unit of temporal accumulation.
-
Based on the property that, in standard diffusion sampling, a single-stage latent variable update can be expressed in affine form, he designed an SNN-compatible incremental scheduler that allows latent increments to propagate during the denoising stage to support trajectory-level SNN execution. He also designed step-sensitive multi-threshold neurons and, through Layer–stage-based and temporal sensitivity calibration, improved the model’s generative accuracy during early SNN time steps.
Critical weaknesses
-
Layer–Stage Base Calibration requires running the SNN diffusion inference multiple times and then comparing the reconstruction errors to determine the coefficient ; Temporal Sensitivity Calibration uses CMA-ES search to find the thresholds for different diffusion stages. Since there are many parameters to calibrate, these two calibration methods may incur a high computational cost. Furthermore, the calibration datasets and the number of calibration samples are not not fully described.
-
As mentioned in Appendix B.5, during each global SNN step, all denoising phases must advance and retain a separate SNN state for each stage, while the parameters introduced by the two calibration methods must also be retained during the inference process. However, the paper does not quantify the size and precision of these retained states.
Questions for authors
-
How much additional overhead do layer–stage base calibration and temporal sensitivity calibration introduce?
-
What is the peak inference memory for the and configurations compared with stage-level execution? Could the authors clarify how they scale with and ?
-
In Table 1, why did the converted SNN perform slightly better than the ANN reference in multiple sets of FID/sFID tests? Is this statistically significant?
As no responses are found, I still tend to reject the submission.