AI Paper Atlas

Research map / Label-efficient and robust learning / Semi-supervised learning

Trash To Treasure: Harvesting OOD Data With Cross-Modal Matching for Open-Set Semi-Supervised Learning

Junkai Huang, Chaowei Fang, Weikai Chen, Zhenhua Chai, Xiaolin Wei, Pengxu Wei, Liang Lin, Guanbin Li

ICCV 2021 · Label-efficient and robust learning › Semi-supervised learning · approach: Safe and realistic semi-supervised learning · 49 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 rotation-recognition self-supervision using all unlabeled data including OOD (ablation)Supervised · CIFAR-ID-50 (TIN OOD, 2500 labels)accuracy (%): 53.18 -> 59.82Improved
add rotation-recognition self-supervision using all unlabeled data including OOD (ablation)UDA · CIFAR-ID-50 (TIN OOD, 2500 labels)accuracy (%): 64.78 -> 70.10Improved
add rotation-recognition self-supervision to UDA (ablation)UDA · CIFAR-10 (TIN OOD, 250 labels)accuracy (%): 88.83 -> 90.69Improved
add cross-modal matching filtering to UDA+SS (ablation)UDA+SS · CIFAR-ID-50 (TIN OOD, 2500 labels)accuracy (%): 70.10 -> 73.19Improved
add cross-modal matching filtering to UDA+SS (ablation)UDA+SS · CIFAR-10 (TIN OOD, 250 labels)accuracy (%): 90.69 -> 91.52Improved
add entropy minimization on unlabeled data for the matching head (ablation)UDA+SS+CMF · CIFAR-ID-50 (TIN OOD, 2500 labels)accuracy (%): 72.38 -> 73.19Improved
add warm-up stage on all data (ablation)UDA+SS+CMF · CIFAR-10 (TIN OOD, 250 labels)accuracy (%): 89.45 -> 91.52Improved
add warm-up stage on all data (ablation)UDA+SS+CMF · CIFAR-ID-50 (TIN OOD, 2500 labels)accuracy (%): 71.81 -> 73.19Improved
use cross-modal matching instead of confidence-based thresholding (ablation)UDA+SS · CIFAR-10 (TIN OOD, 250 labels)accuracy (%): 90.81 -> 91.52Improved
use cross-modal matching instead of confidence-based thresholding (ablation)UDA+SS · CIFAR-ID-50 (TIN OOD, 2500 labels)accuracy (%): 71.16 -> 73.19Improved
add MTCF to UDAUDA · CIFAR-ID-50 intra-dataset OOD (2000 labels)accuracy (%): 66.02 -> 60.06Hurt
add MTCF to UDAUDA · CIFAR-ID-50 with TIN OOD (2500 labels)accuracy (%): 66.65 -> 67.30Improved

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