- Rating
- 3
- Confidence
- 3
- Informativeness
- 3
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
This paper proposes Spiking Event-Consistent Attention (SECA) to improve the robustness of event-based spiking transformers. The method uses spatial proximity and event polarity to construct a bounded gate on query-key correlations, introducing two learned scalars per block. Models trained on clean data are evaluated under several event corruptions and across multiple backbones.
Critical strengths
-
The method is simple and addresses a meaningful problem. The bounded gate provides an interpretable way to incorporate event structure, and the improvement under strong polarity-flip noise is substantial. The component ablation also supports using both spatial and polarity information.
-
This paper provides detailed analysis. The authors compare genuine, shuffled, random, and misaligned priors, and show that much of the improvement remains after removing the gate at inference. This result is interesting because it suggests an effect on the learned parameters.
Critical weaknesses
-
The necessity of the structural gate at inference is unclear. Table 8 shows that disabling the gate in the same trained model yields a numerically higher PFN accuracy (89.028% vs 87.986%) without retraining. Although this slightly reduces clean accuracy, the robustness gain is largely retained, leaving the benefit of the additional inference-time modulation uncertain.
-
The polarity descriptor captures only relative ON/OFF imbalance, discarding absolute event counts and failing to distinguish meaningful activity from noise with similar polarity statistics.
-
The practical overhead of SECA is insufficiently evaluated. Adding only two learnable scalars per block establishes a small parameter overhead, but does not quantify computational or memory costs.
Questions for authors
see weaknesses
2 comments
I appreciate the authors' efforts in providing additional experiments and explanations, which have addressed most of my concerns. So I will maintain my original score as 3.
Dear Reviewer fYhQ,
Thank you for these helpful comments. We clarified the gate-removal evidence and the polarity descriptor's role, and added measured computational and memory costs across all three backbone families. We welcome further discussion.
Weakness 1: Necessity of the inference-time gate.
Active inference-time gating is not necessary to retain PFN robustness in this experiment. In Table 8, full SECA and gate-off share the same trained checkpoint without retraining. Gate-on has higher clean accuracy; gate-off has a numerically higher PFN mean over five paired corruption realizations. These summaries do not establish statistical superiority. Removing the gate preserves learned parameters and does not test training without the prior. The abstract, Sec. 4.6, and Appendix E.4 clarify our contribution: event-derived structure guides token interactions under clean-only training, with observed PFN robustness persisting beyond instantaneous inference-time modulation.
Table 8. Inference-time gate removal on DVS128-Gesture at ηPFN=0.10. PFN mean$\pm$SD over five paired corruption realizations; SECA views share one checkpoint.
Weakness 2: Polarity descriptor and absolute activity.
The descriptor summarizes relative ON/OFF imbalance, ρ=(a(0)−a(1))/(a(0)+a(1)+ϵ), with ϵ=10−6 (Appendix A). Absolute counts remain available at the feature-branch input through the original two-channel frames (Fig. 2). An empty region and a nonempty region with balanced polarities both give ρ=0, but different feature inputs; prior entries involving either token vanish, leaving its interactions without additional structural modulation. Polarity balance alone cannot distinguish signal from noise with matching statistics. Sec. 3.2 and Appendix B therefore define polarity/proximity as soft compatibility cues. Table 4 supports their utility in the evaluated setting: at ηPFN=0.10, accuracy is 68.403% for SSA, 78.819% for polarity-only modulation, and 88.542% for joint spatial–polarity modulation.
Weakness 3: Practical computational and memory costs.
Sec. 4.7 and Table R2 quantify costs beyond parameter count. Each pair uses the same L20 and all 288 clean DVS128-Gesture sequences (T=16, FP32, TF32 disabled), averaging five full passes after 50 warm-up forwards. CUDA-synchronized timing includes forward inference and spike reset, excluding data loading and host-to-device transfer. Dense MACs count only Conv/Linear/matrix products; memory is peak allocated GPU memory. SDT's separable spatial contractions add 0.403 G MACs per sequence. Spikformer and SDT-V3 retain their existing matrix products; their additional elementwise modulation is excluded from this count but included in measured runtime and peak memory.
Table R2. Inference cost on DVS128-Gesture. Entries: baseline / SECA.
For SDT, B=1 latency increases by about 1.7% (105.54 to 107.29 ms). At B=16, throughput decreases from 40.88 to 37.92 seq/s, corresponding to about 7.8% higher batch latency (Lbatch=1000B/R ms); peak memory increases by 6.57%. Spikformer/SDT-V3 add 0.16/0.02 MiB at B=16. Reversing Spikformer's execution order reverses its small timing difference, providing no evidence of acceleration. The measured overhead therefore depends on backbone and batch size. Table R2 and Table R3 (Appendix E.7) were profiled in separate sessions with different cuDNN settings and execution-order protocols; cuDNN TF32 is disabled in Table R2 and enabled in Table R3. Absolute timings are comparable only within each table.