Research map / Architectures and efficiency / Spiking networks
TDSNNs: Competitive Topographic Deep Spiking Neural Networks for Visual Cortex Modeling
Deming Zhou, Yuetong Fang, Zhaorui Wang, Renjing Xu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add short-timescale spike synchrony loss L_S (beta>0) to long-timescale loss (ablation) | TSResnet18 · ImageNet | top-1 accuracy (%): 58.21 -> 58.34 | Improved |
| add short-timescale spike synchrony loss L_S (ablation) | TSResnet18 · V1-like layer smoothness | smoothness: 0.755 -> 0.7674 | Improved |
| add topographic STC loss to spiking ResNet18 | SResnet18 · ImageNet | top-1 accuracy drop: no drop vs 3% drop for TopoNet | No clear effect |
| set STC weights alpha=10, beta=90 (ablation) | TSResnet18 · ImageNet | top-1 accuracy (%): max 58.72% | Improved |
| add topography via STC (alpha=beta=0.5) | SResnet18 · CIFAR100 | accuracy (%): 73.01 -> 73.97 | Improved |
| add topography to Spikformer | Spikformer · ImageNet | accuracy | No clear effect |
| add topography to spiking ResNet18 | SResnet18 · Robustness (Gaussian noise) | accuracy (%): 24.5% -> 25.8% | Improved |
| add topography to spiking ResNet18 | SResnet18 · Robustness (PGD) | accuracy (%): 9.97% -> 10.7% | Improved |
| add topography to spiking ResNet18 | SResnet18 · Robustness (random pixel masking) | accuracy (%): 20.8% -> 21.0% | No clear effect |
| add topography to SNN (TDSNN vs SNN) | SNN ResNet18 · BrainScore V1 | BrainScore: 0.6823 -> 0.6845 | Improved |
| add topography to SNN (TDSNN vs SNN) | SNN ResNet18 · BrainScore V4 | BrainScore: 0.3970 -> 0.3886 | Hurt |
Closest papers by meaning
- TopoNets: High performing vision and language models with brain-like topography (ICLR 2025 · similarity 0.88)
- Unveiling the Spatial-temporal Effective Receptive Fields of Spiking Neural Networks (NeurIPS 2025 · similarity 0.88)
- Long-Range Feedback Spiking Network Captures Dynamic and Static Representations of the Visual Cortex under Movie Stimuli (NeurIPS 2024 · similarity 0.87)
- STAA-SNN: Spatial-Temporal Attention Aggregator for Spiking Neural Networks (CVPR 2025 · similarity 0.87)
- FSTA-SNN:Frequency-Based Spatial-Temporal Attention Module for Spiking Neural Networks (AAAI 2025 · similarity 0.87)
- Flexible Context-Driven Sensory Processing in Dynamical Vision Models (NeurIPS 2024 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
