mlsanityData to 7 Oct 2026

SemiGPC: Distribution-Aware Label Refinement for Imbalanced Semi-Supervised Learning Using Gaussian Processes

arXiv 2311.01646 ↗First posted 3 Nov 2023cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

In this paper we introduce SemiGPC, a distribution-aware label refinement strategy based on Gaussian Processes where the predictions of the model are derived from the labels posterior distribution. Differently from other buffer-based semi-supervised methods such as CoMatch and SimMatch, our SemiGPC includes a normalization term that addresses imbalances in the global data distribution while maintaining local sensitivity. This explicit control allows SemiGPC to be more robust to confirmation bias especially under class imbalance. We show that SemiGPC improves performance when paired with different Semi-Supervised methods such as FixMatch, ReMixMatch, SimMatch and FreeMatch and different pre-training strategies including MSN and Dino. We also show that SemiGPC achieves state of the art results under different degrees of class imbalance on standard CIFAR10-LT/CIFAR100-LT especially in the low data-regime. Using SemiGPC also results in about 2% avg.accuracy increase compared to a new competitive baseline on the more challenging benchmarks SemiAves, SemiCUB, SemiFungi and Semi-iNat.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 23 of its 34 references that are in the map. First posted on arXiv 3 Nov 2023.

Builds on

23 of 34 references.

References · 23

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  2. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  3. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  4. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,080
  5. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,623
  6. 2022Masked Siamese Networks for Label-Efficient Learningcited by 301
  7. 2022FreeMatch: Self-adaptive Thresholding for Semi-supervised Learningcited by 232
  8. 2020CoMatch: Semi-supervised Learning with Contrastive Graph Regularizationcited by 167
  9. 2019Tensor Programs I: Wide Feedforward or Recurrent Neural Networks of Any Architecture are Gaussian Processescited by 148
  10. 2019Exact Gaussian Processes on a Million Data Pointscited by 118
  11. 2022SimMatch: Semi-supervised Learning with Similarity Matchingcited by 118
  12. 2022USB: A Unified Semi-supervised Learning Benchmark for Classificationcited by 95
11 more
  1. 2022Fast Finite Width Neural Tangent Kernelcited by 62
  2. 2021CoSSL: Co-Learning of Representation and Classifier for Imbalanced Semi-Supervised Learningcited by 41
  3. 2021A Realistic Evaluation of Semi-Supervised Learning for Fine-Grained Classificationcited by 36
  4. 2021Deep Neural Networks as Point Estimates for Deep Gaussian Processescited by 26
  5. 2022NP-Match: When Neural Processes meet Semi-Supervised Learningcited by 25
  6. 2021The Semi-Supervised iNaturalist-Aves Challenge at FGVC7 Workshopcited by 21
  7. 2021Dense Gaussian Processes for Few-Shot Segmentationcited by 17
  8. 2021The Semi-Supervised iNaturalist Challenge at the FGVC8 Workshopcited by 16
  9. 2021Meta-Learning with Neural Tangent Kernelscited by 15
  10. 2021Trust Your Robots! Predictive Uncertainty Estimation of Neural Networks with Sparse Gaussian Processescited by 12
  11. 2021Semi-Supervised Learning with Taxonomic Labelscited by 11

Built on by

Not cited yet.