AI Paper Atlas

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

SiNGER: A Clearer Voice Distills Vision Transformers Further

Geunhyeok Yu, Sunjae Jeong, Yoonyoung Choi, Jaeseung Kim, Hyoseok Hwang

ICLR 2026 · Label-efficient and robust learning › Knowledge distillation · approach: Few-shot and metric distillation · 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
add outlier suppression loss (ablation)SiNGER ViT-L->ViT-T with nullspace init · NYUd-v2RMSE: 1.1943 -> 1.1870Improved
add information preservation loss to outlier loss (ablation)SiNGER ViT-L->ViT-T · NYUd-v2RMSE: 1.1870 -> 1.1690Improved
add information preservation loss to outlier loss (ablation)SiNGER ViT-L->ViT-T · ImageNet-1K valaccuracy (%): 11.04 -> 11.57Improved
add information preservation loss (ablation)SiNGER · teacher vs refined teacher feature distanceGram/feature distance: 14.22 -> 7.25Improved
add information preservation loss (ablation)SiNGER · teacher vs student feature distancedistance: 72.36 -> 41.71Improved
use nullspace initialization instead of random (ablation)SiNGER adapter · NYUd-v2 (ablation setup)RMSE: 1.3048 -> 1.1943Improved
use nullspace initialization instead of random (ablation)SiNGER adapter · alignment to null basisE_safe: 0.2532 -> 0.8337Improved
increase LoRA rank r from 16 to 64 (ablation)SiNGER · NYUd-v2RMSE: 1.4395 -> 1.6485Hurt
lower LoRA rank r from 16 to 8 (ablation)SiNGER · NYUd-v2RMSE: 1.4395 -> 1.4545Hurt
change quantile threshold alpha from 0.95 to 0.90 (ablation)SiNGER · NYUd-v2RMSE: 1.4395 -> 1.5989Hurt
change quantile threshold alpha from 0.95 to 0.99 (ablation)SiNGER · NYUd-v2RMSE: 1.4395 -> 1.5321Hurt
add intermediate layer 11 to distillation layers 17 and 23 (ablation)SiNGER ViT-L->ViT-T · NYUd-v2RMSE: 0.9406 -> 0.9624Hurt

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