AI Paper Atlas

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

Knowledge Distillation Meets Open-Set Semi-supervised Learning

Jing Yang, Xiatian Zhu, Adrian Bulat, Brais Martínez, Georgios Tzimiropoulos

IJCV 2024 · Label-efficient and robust learning › Knowledge distillation · approach: Rethinking distillation objectives · 28 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 MSE loss instead of KL loss (ablation)SRD · CIFAR-100 (WRN40-4 to WRN16-4)Top-1 accuracy (%): 79.04 -> 79.58Improved
use MSE loss instead of pMSE loss (ablation)SRD · CIFAR-100 (WRN40-4 to WRN16-4)Top-1 accuracy (%): 79.13 -> 79.58Improved
add SRD loss to regularizer R (ablation)SRD · CIFAR-100 (WRN40-4 to WRN16-4)Top-1 accuracy (%): 78.05 -> 79.58Improved
add regularizer R to SRD loss (ablation)SRD · CIFAR-100 (WRN40-4 to WRN16-4)Top-1 accuracy (%): 79.10 -> 79.58Improved
add logit-matching KD to SRD (ablation)SRD · CIFAR-100 (WRN40-4 to WRN16-4)Top-1 accuracy (%): 79.58 -> 79.63Improved
add open-set OOD detection to SRD (ablation)SRD · Open-set SSL (ResNet8x4)Top-1 accuracy (%): 76.24 -> 76.08No clear effect
add data-augmentation consistency to SRD (ablation)SRD · Open-set SSL (ResNet8x4)Top-1 accuracy (%): 76.24 -> 75.66Hurt
add data-augmentation consistency to KD (ablation)KD · Open-set SSL (ResNet8x4)Top-1 accuracy (%): 74.68 -> 72.82Hurt
add MixMatch to SRD (ablation)SRD · Open-set SSL (ResNet8x4)Top-1 accuracy (%): 76.24 -> 77.13Improved
add SSKD to SRD (ablation)SRD · Open-set SSL (ResNet8x4)Top-1 accuracy (%): 76.24 -> 76.38Improved
add unlabeled Tiny-ImageNet data (D+U vs D) (ablation)SRD · Open-set SSL (ResNet32x4 to ResNet8x4)Top-1 accuracy (%): 75.92 -> 76.24Improved
add unlabeled Tiny-ImageNet data (D+U vs D) (ablation)CRD (pseudo labels) · Open-set SSL (ResNet32x4 to ResNet8x4)Top-1 accuracy (%): 75.51 -> 73.84Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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