- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 1
- Soundness
- 2
Read review
Paper summary
This paper proposes Residual-Adaptive Spiking Diffusion (RASD) to improve the generation quality of low-timestep spiking diffusion models. The method uses selective residual-potential inheritance to reuse information across consecutive denoising steps, while adjusting the inheritance ratio according to the denoising stage and network location. It also introduces residual-informed threshold adaptation, which uses historical activation information to estimate the activation range and adjust firing thresholds. Experiments on DDPM, Improved-DDPM, and DiT demonstrate improvements in generation quality with low timesteps.
Critical strengths
-
The motivation of reusing residual potentials across denoising steps is reasonable.
-
The method is evaluated on different diffusion architectures, including both U-Net-based models and DiT.
Critical weaknesses
-
TA-SpikingDiT has already explored reusing residual membrane potentials across denoising steps. RASD mainly extends this idea through selective inheritance and threshold adaptation. Therefore, the novelty of this work appears somewhat limited. Moreover, the improvements over TA-SpikingDiT on DiT are relatively small.
-
The contribution of threshold adaptation is not sufficiently demonstrated, as the paper lacks a clear component-wise ablation study.
-
The energy analysis only compares RASD with ANNs. Comparisons of inference latency and energy consumption with other spiking diffusion methods are missing.
Questions for authors
-
What are the actual inference latency and energy consumption of RASD compared with existing spiking diffusion methods?
-
How could RASD be implemented on neuromorphic hardware.