atlas

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

Self-Decoupling and Ensemble Distillation for Efficient Segmentation

AAAI 2023 · Label-efficient and robust learning › Knowledge distillation · approach: Distillation with causal and adaptive guidance · 5 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
Add DPED to segmentation training (ablation)DeepLabV3-EfficientNet-B0 with SDES · CamVidmIoU: 67.56 -> 68.13Helped
Add DFED to segmentation training (ablation)DeepLabV3-EfficientNet-B0 with SDES · CamVidmIoU: 67.56 -> 68.37Helped
Add both DPED and DFED (ablation)DeepLabV3-EfficientNet-B0 with SDES · CamVidmIoU: 67.56 -> 68.74Helped
Use a random category split instead of the more-to-less subset split (ablation)SDES · CamVidmIoU: 68.74 -> 68.19Hurt
Vary the DPED loss weight α (ablation)SDES · CamVidmIoUMixed
Vary the DFED loss weight β (ablation)SDES · CamVidmIoUMixed
Vary the feature selection ratio γ (ablation)SDES · CamVidmIoUMixed
Vary the number of expert decoders N (ablation)SDES · CamVidmIoUMixed

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