Pith. sign in

REVIEW 11 cited by

ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1911.09785 v2 pith:GGJVDBS4 submitted 2019-11-21 cs.LG cs.CVstat.ML

David Berthelot , Nicholas Carlini , Ekin D. Cubuk , Alex Kurakin , Kihyuk Sohn , Han Zhang , Colin Raffel This is my paper · ORCID
classification cs.LGcs.CVstat.ML
keywords distributionaccuracyaugmentationalignmentanchoringdataremixmatchalgorithm
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
abstract

We improve the recently-proposed "MixMatch" semi-supervised learning algorithm by introducing two new techniques: distribution alignment and augmentation anchoring. Distribution alignment encourages the marginal distribution of predictions on unlabeled data to be close to the marginal distribution of ground-truth labels. Augmentation anchoring feeds multiple strongly augmented versions of an input into the model and encourages each output to be close to the prediction for a weakly-augmented version of the same input. To produce strong augmentations, we propose a variant of AutoAugment which learns the augmentation policy while the model is being trained. Our new algorithm, dubbed ReMixMatch, is significantly more data-efficient than prior work, requiring between $5\times$ and $16\times$ less data to reach the same accuracy. For example, on CIFAR-10 with 250 labeled examples we reach $93.73\%$ accuracy (compared to MixMatch's accuracy of $93.58\%$ with $4{,}000$ examples) and a median accuracy of $84.92\%$ with just four labels per class. We make our code and data open-source at https://github.com/google-research/remixmatch.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 11 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training?

    cs.CV 2026-07 conditional novelty 6.0 of 10

    Jointly optimizing self-supervised and supervised losses often saves training time and helps in low-label settings, but pretrain-then-finetune remains better for several contrastive methods and specialized domains.

  2. Semi-MedRef: Semi-Supervised Medical Referring Image Segmentation with Cross-Modal Alignment

    cs.CV 2026-05 unverdicted novelty 6.0 of 10

    Semi-MedRef introduces T-PatchMix, PosAug, and ITCL within a teacher-student SSL setup to preserve image-text alignment under augmentation for medical referring segmentation on QaTa-COV19 and MosMedData+.

  3. JanusNet: Hierarchical Slice-Block Shuffle and Displacement for Semi-Supervised 3D Multi-Organ Segmentation

    cs.CV 2025-08 conditional novelty 6.0 of 10

    Slice-block shuffle plus confidence-guided displacement reports 72.67% average Dice on Synapse with 20% labels and 63.99% on AMOS with 5% labels.

  4. FixCLR: Negative-Class Contrastive Learning for Semi-Supervised Domain Generalization

    cs.CV 2025-06 conditional novelty 6.0 of 10

    A plug-and-play contrastive regularization term, FixCLR, repels different pseudo-classes across domains and improves semi-supervised domain generalization accuracy when combined with FixMatch-based methods.

  5. ZeroVO: Visual Odometry with Minimal Assumptions

    cs.CV 2025-06 conditional novelty 6.0 of 10

    A two-frame visual odometry model using estimated depth, language priors, and semi-supervised pseudo-label filtering achieves zero-shot metric-scale pose estimation across multiple driving datasets.

  6. Improving realistic semi-supervised learning with doubly robust estimation

    cs.LG 2025-02 conditional novelty 6.0 of 10

    Doubly robust estimation of the unlabeled class distribution improves pseudo-labeling methods for realistic long-tailed semi-supervised learning.

  7. RegMixMatch: Optimizing Mixup Utilization in Semi-Supervised Learning

    cs.LG 2024-12 conditional novelty 6.0 of 10

    RegMixMatch combines clean-plus-mixed training with class-aware Mixup for low-confidence unlabeled samples, achieving state-of-the-art semi-supervised image classification.

  8. P3Net: Progressive and Periodic Perturbation for Semi-Supervised Medical Image Segmentation

    eess.IV 2025-05 conditional novelty 5.0 of 10

    A progressive, periodic interpolation schedule and a boundary-focused loss improve semi-supervised medical image segmentation on four standard datasets.

  9. Glioma Multimodal MRI Analysis System for Tumor Layered Diagnosis via Multi-task Semi-supervised Learning

    eess.IV 2025-01 conditional novelty 5.0 of 10

    An integrated MRI analysis system jointly segments gliomas and predicts grade, IDH, 1p/19q, and MGMT status, with added robustness to missing MRI modalities.

  10. DyConfidMatch: Dynamic Thresholding and Re-sampling for 3D Semi-supervised Learning

    cs.CV 2024-11 conditional novelty 4.0 of 10

    DyConfidMatch sets per-class pseudo-label thresholds and re-sampling weights from class-level confidence, improving semi-supervised 3D classification and detection.

  11. Learning from Limited and Imperfect Data

    cs.LG 2025-07 unverdicted novelty 3.0 of 10

    A doctoral thesis compiling nine peer-reviewed papers on long-tailed image generation, long-tailed recognition, semi-supervised learning, and domain adaptation.

Pith tools