AI Paper Atlas

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

Self-Supervised Wasserstein Pseudo-Labeling for Semi-Supervised Image Classification

Fariborz Taherkhani, Ali Dabouei, Sobhan Soleymani, Jeremy Dawson, Nasser M. Nasrabadi

CVPR 2021 · Label-efficient and robust learning › Semi-supervised learning · approach: Confidence-based pseudo-label selection · 39 citations (OpenAlex)

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 SSWPL instead of FixMatchWRN-28-2 · CIFAR-10 (250 labels)test error (%): 5.07 ± 0.33 -> 4.11 ± 0.15Improved
Use SSWPL instead of FixMatchWRN-28-2 · CIFAR-10 (4000 labels)test error (%): 4.31 ± 0.15 -> 3.18 ± 0.09Improved
Use SSWPL instead of FixMatchWRN-28-2 · CIFAR-100 (2500 labels)test error (%): 2.64 ± 0.64 -> 2.71 ± 0.25Hurt
Use SSWPL instead of FixMatchWRN-28-2 · CIFAR-100 (10000 labels)test error (%): 2.36 ± 0.19 -> 2.27 ± 0.07Improved
Use SSWPL instead of FixMatchWRN-28-2 · SVHN (250 labels)test error (%): 2.64 ± 0.64 -> 6.16 ± 0.18Hurt
Use SSWPL instead of FixMatchWRN-28-2 · SVHN (1000 labels)test error (%): 2.36 ± 0.19 -> 2.27 ± 0.07Improved
Use SSWPL instead of FixMatchResNet-50 · ImageNet (10% labeled; top-1)top-1 error (%): 28.54±0.52% -> 26.46 ± 0.44%Improved
Use SSWPL instead of FixMatchResNet-50 · ImageNet (10% labeled; top-5)top-5 error (%): 10.87±0.28% -> 9.14±0.26%Improved
Replace Wasserstein-barycenter clustering with k-means (ablation)SSWPL · CIFAR-10 (250 labels)test error (%): 9.62 ± 0.47 -> 4.11 ± 0.15Improved
Replace Wasserstein-barycenter clustering with k-means (ablation)SSWPL · CIFAR-10 (4000 labels)test error (%): 7.74 ± 0.73 -> 3.18 ± 0.09Improved
Replace Wasserstein-barycenter clustering with k-means (ablation)SSWPL · CIFAR-100 (2500 labels)test error (%): 6.16 ± 0.18 -> 2.71 ± 0.25Improved
Replace Wasserstein-barycenter clustering with k-means (ablation)SSWPL · CIFAR-100 (10000 labels)test error (%): 4.59 ± 0.34 -> 2.27 ± 0.07Improved

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