AI Paper Atlas

Research map / Architectures and efficiency / Spiking networks

DCT-SNN: Using DCT To Distribute Spatial Information Over Time for Low-Latency Spiking Neural Networks

Isha Garg, Sayeed Shafayet Chowdhury, Kaushik Roy

ICCV 2021 · Architectures and efficiency › Spiking networks · approach: Spiking transformers · 50 citations (OpenAlex)

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 changedWhereMeasuredEffect
use orthonormal transform instead of random transform for input encoding (ablation)DCT-SNN encoding, VGG5 · CIFAR-10accuracy (%): 64.7 -> 83.3Improved
use DCT matrix instead of random unranked orthonormal matrix (ablation)DCT-SNN encoding, VGG5 · CIFAR-10accuracy (%): 83.3 -> 83.5Improved
use data-dependent PCA bases instead of fixed DCT (ablation)DCT-SNN encoding, VGG5 · CIFAR-10accuracy (%): 83.5 -> 83.8No clear effect
reduce DCT block size from 16 to 4 (ablation)DCT-SNN · CIFAR-10accuracy (%)Improved
use block size 2 for DCT encoding (ablation)DCT-SNN · CIFAR-10accuracy (%)Hurt
add overlapping blocks with stride 2 to DCT-4 (ablation)DCT-SNN · CIFAR-10accuracy (%)Improved
increase timesteps from 32 to 48 (three cycles) (ablation)DCT-SNN DCT-4 · CIFAR-10accuracy (%): 88.41 -> 89.94Improved
use DCT-SNN encoding instead of Poisson pixel encodingSNN VGG9 · CIFAR-10accuracy (%): 88.9 (100) -> 89.94 (48)Mixed
use DCT-SNN encoding instead of Poisson-encoded DCT coefficientsSNN VGG9 · CIFAR-10accuracy (%): 88.2 (100) -> 89.94 (48)Improved
use DCT-SNN encoding instead of Poisson-encoded DCT coefficientsSNN VGG11 · CIFAR-100accuracy (%): 65.1 (125) -> 68.3 (48)Improved
initialize SNN from pretrained ANN instead of training from scratch (ablation)DCT-SNN VGG9 · CIFAR-10accuracy (%): 84.9 -> 89.94Improved
include all 16 frequencies at inference instead of only first 4 (ablation)DCT-SNN VGG9 · CIFAR-10accuracy (%): 73.9 -> 88.6Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy