AI Paper Atlas

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

SFKD: Spatial–Frequency Joint-Aware Heterogeneous Knowledge Distillation via Multi-Level Wavelet Spectral Interaction

Cuipeng Wang, Haipeng Wang

ECCV 2026 · Label-efficient and robust learning › Knowledge distillation · approach: Rethinking distillation objectives · 0 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 SFKD instead of FBTheterogeneous KD · CIFAR-100 heterogeneous, averageaccuracy gain: 8.38 -> 10.92Improved
use SFKD instead of FBTheterogeneous KD · ImageNet-1K heterogeneous, averageaccuracy gain: 2.31 -> 2.51Improved
use SFKD instead of FBTheterogeneous KD · CIFAR-100 heterogeneous, ViT-S -> MobileNetV2top-1 accuracy: 82.10 -> 79.97Hurt
use SFKD instead of FitNet feature projectionTransformer student · CIFAR-100 heterogeneous, ConvNeXt-T -> Swin-Ptop-1 accuracy: 24.06 -> 82.16Improved
use SFKD instead of FBThomogeneous KD · ImageNet-1K homogeneous, ResNet50 -> MobileNettop-1 accuracy: 73.45 -> 73.81Improved
add L1 low-frequency loss (ablation)SFKD · ImageNet-1K ablation, Swin-T -> ResNet18top-1 accuracy: 72.19 -> 72.54Improved
add L2 high-frequency loss (ablation)SFKD · ImageNet-1K ablation, Swin-T -> ResNet18top-1 accuracy: 72.32 -> 72.54Improved
add L3 reconstruction loss (ablation)SFKD · ImageNet-1K ablation, Swin-T -> ResNet18top-1 accuracy: 72.31 -> 72.54Improved
add L4 KL loss (ablation)SFKD · ImageNet-1K ablation, Swin-T -> ResNet18top-1 accuracy: 72.46 -> 72.54Improved
add LCR refinement stream (ablation)SFKD · ImageNet-1K ablation, Swin-T -> ResNet18 (refinement streams)top-1 accuracy: 71.24 -> 72.19Improved
add GTR refinement stream (ablation)SFKD · ImageNet-1K ablation, Swin-T -> ResNet18 (refinement streams)top-1 accuracy: 71.24 -> 72.46Improved
combine LCR and GTR streams (ablation)SFKD · ImageNet-1K ablation, Swin-T -> ResNet18 (refinement streams)top-1 accuracy: 72.46 -> 72.54Improved

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