AI Paper Atlas

Research map / Label-efficient and robust learning / Knowledge distillation

A Closer Look at Knowledge Distillation in Spiking Neural Network Training

Xu Liu, Na Xia, Jinxing Zhou, Jingyuan Xu, Dan Guo

AAAI 2026 · Label-efficient and robust learning › Knowledge distillation · approach: Rethinking distillation objectives · 2 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 softmax scaling of CAM and SAM instead of no scaling (ablation)SAMD · CIFAR-100 (ResNet-19, T=1)accuracy: 75.56 -> 79.11Improved
use softmax instead of L2-norm scaling (ablation)SAMD · CIFAR-100 (ResNet-19, T=1)accuracy: 76.48 -> 79.11Improved
use softmax instead of Z-score scaling (ablation)SAMD · CIFAR-100 (ResNet-19, T=1)accuracy: 74.78 -> 79.11Improved
add SAMD and NLD distillation (vs without either) (ablation)CKDSNN · CIFAR-100 (ResNet-19)accuracyImproved
replace gradient-based CAM-CAM distillation (e2KD, CATKD) with CAM-SAM (ablation)SAMD · CIFAR-100 (ResNet-19)accuracyImproved
use adaptive Gaussian noise instead of fixed-std noise (ablation)NLD · CIFAR-100 (ResNet-19, T=1)accuracyImproved
use CKDSNN instead of BKDSNNSEW-ResNet-34 SNN · ImageNet-1K (T=4)top-1 accuracy: 71.24 -> 73.05Improved
use CKDSNN instead of EnOFSNNResNet-20 SNN · CIFAR10-DVS (T=10)accuracy: 80.50 -> 81.55Improved
use CKDSNN instead of EnOFSNNResNet-19 SNN · CIFAR-100 (T=1)accuracy: 77.08 -> 79.11Improved
use CKDSNN instead of BKDSNNSNN energy · ImageNet-1K (ResNet34, T=4)fire rate (%): 15.0 -> 13.0Improved
increase time steps from 1 to 4CKDSNN ResNet-19 · CIFAR-100accuracy: 79.11 -> 83.88Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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