- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes Low-Rank Temporal Batch Normalization (LRTB) for SNNs, which consists of two components. The first component improves cumulative variance estimation by considering both within-timestep variance and mean differences across timesteps. The second component uses a set of exponential basis functions to represent time-dependent normalization parameters, reducing the number of learnable affine parameters. Experiments on CIFAR10, CIFAR100, CIFAR10-DVS, and ImageNet show improvements over existing temporal normalization methods.
Critical strengths
-
The paper identifies a valid issue in the cumulative variance estimation of existing temporal normalization methods and provides a mathematically correct solution.
-
The proposed method achieves consistent performance improvements across different datasets and network architectures.
Critical weaknesses
-
Most experiments are conducted with only four timesteps and a temporal rank of three. Under this setting, the low-rank constraint is relatively weak.
-
Although the method reduces the number of learnable affine parameters, its practical computational benefits are not sufficiently demonstrated. The paper does not provide detailed comparisons of model size or inference latency.
-
The ImageNet results of TAB are taken from the original paper, but LRTB uses different experimental settings on ImageNet. This makes it difficult to determine whether the improvement comes from LRTB itself.
Questions for authors
-
How does LRTB perform with longer simulation horizons, such as T=10 or T=16?
-
What are the actual parameter savings of LRTB, and how does its inference latency compare with existing normalization methods?
-
How does LRTB perform on Spiking Transformer architectures?
4 comments
Thank you for the detailed response and additional experiments. I appreciate the new results at longer timesteps, the controlled ImageNet comparison, the Spikformer experiments, and the efficiency measurements.
However, I still have some reservations. Although the low-rank parameterization shows benefits at T=16, the accuracy improvement over TAB becomes relatively small as T increases. Moreover, the reduction in total model parameters is only 1.30%, and inference latency is still not reported. I also believe the methodological novelty remains somewhat limited, as the variance correction is based on a standard statistical formula and the low-rank parameterization is relatively straightforward.
Overall, the additional experiments strengthen the paper, but I do not think they sufficiently change my assessment of its contribution. Therefore, I will keep my original rating of 2.
Thank you for pointing this out. We have added inference-latency measurements using the same TAB and LRTB ResNet implementations at on an NVIDIA A100 80GB GPU, with FP32, batch size 64, and inputs. Each method was evaluated in a fresh process under torch.inference_mode(), with 100 warm-up iterations followed by 500 synchronized forward passes. LRTB reduces the mean inference latency from 529.76 ms/batch for TAB to 305.76 ms/batch, a 42.28% reduction, while reducing inference peak memory by 10.17%.
The smaller accuracy gain at may partly reflect model-performance saturation: both methods approach approximately 80% accuracy as the number of time steps increases, leaving less room for further improvement. Nevertheless, LRTB retains a positive gain while reducing temporal affine coefficients by 81.25%. We appreciate the reviewer’s careful assessment and the opportunity to clarify these practical efficiency results.
Thank you for the additional results and clarification. However, some of my previous concerns still remain, and I believe the methodological novelty is relatively limited. Therefore, I will keep my original rating unchanged.
Response to Reviewer RrLr
We thank the reviewer for recognizing the mathematical correctness of the cumulative variance estimator and the improvements across datasets and architectures. We have added horizon and rank experiments, parameter and computational profiling, a controlled ImageNet comparison, and Spikformer evaluations.
Q1. Longer horizons and the effectiveness of the low-rank constraint
We extended the N-Caltech101 evaluation to T=8 and T=16, keeping r=3.
The temporal affine coefficient reduction is 1−r/T relative to independent per-step coefficients; pp denotes percentage points.
With the same compact rank, LRTB outperforms TAB at every evaluated horizon. At T=16, the temporal affine coefficient reduction reaches 81.25%, directly addressing the concern that the original T=4,r=3 setting imposed only a mild low-rank constraint.
We also compared r=3 and r=4 at T=16. Both achieve 80.046%, so r=3 attains the same observed accuracy with 25% fewer temporal affine coefficients.
Q2. Computational efficiency
We profiled matched TAB and LRTB ResNet implementations at T=16 on an NVIDIA A100 80GB GPU, using FP32, batch size 64, and synthetic 3×32×32 inputs. Before measurement, we performed 100 untimed warm-up executions using the same inputs and procedure. We then repeated the corresponding training or inference step 500 times, recording the elapsed time and peak GPU memory for each repetition. These repetitions were used for computational profiling and were separate from the model-training epochs.
At T=16, LRTB reduces peak training memory by 41.60%, inference memory by 10.17%, while training iteration time increases by only 2.44%.
Normalization parameters decrease by 81.10%, corresponding to approximately 1.30% fewer total model parameters. These measurements quantify the actual parameter savings and demonstrate practical inference and memory benefits in the evaluated configuration. We will include the results and profiling setup in the revised manuscript.
C3. Fair comparison on ImageNet-1K
We compared TAB and LRTB on ImageNet-1K under exactly the same training and evaluation conditions, with the normalization method as the only difference. Both methods use ResNet-34 at T=4.
ImageNet-1K Top-1 accuracy (%)
Results are from one training run per method.
Under this controlled protocol, LRTB improves Top-1 accuracy by 1.32 percentage points. This comparison uses our rerun TAB baseline, providing more direct evidence of the normalization benefit than the original comparison against the published TAB result.
We will replace the original comparison with these matched results and include the complete training configuration in the revision.
Q3. Applicability to Spiking Transformer architectures
We additionally evaluated LRTB on Spikformer, comparing it with TAB on CIFAR-10 and CIFAR-100 under matched settings at T=4.
Top-1 accuracy (%)
Results are from one training run per configuration.
LRTB improves accuracy on both datasets, extending the empirical evidence beyond convolutional SNNs to the evaluated Spikformer architecture.
We will incorporate the horizon and rank experiments, computational profiling, controlled ImageNet results, and Spikformer comparisons into the revised manuscript.