RoPAWS: Robust Semi-supervised Representation Learning from Uncurated Data

Sangwoo Mo, Jong-Chyi Su, Chih-Yao Ma, Mido Assran, Ishan Misra +2 more
2/12/2026

No official code found. Best implementation: facebookresearch/suncet (494 stars, MIT, last commit 2023-04-28).

Abstract

Semi-supervised learning aims to train a model using limited labels. State-of-the-art semi-supervised methods for image classification such as PAWS rely on self-supervised representations learned with large-scale unlabeled but curated data. However, PAWS is often less effective when using real-world unlabeled data that is uncurated, e.g., contains out-of-class data. We propose RoPAWS, a robust extension of PAWS that can work with real-world unlabeled data. We first reinterpret PAWS as a generative classifier that models densities using kernel density estimation. From this probabilistic perspective, we calibrate its prediction based on the densities of labeled and unlabeled data, which leads to a simple closed-form solution from the Bayes' rule. We demonstrate that RoPAWS significantly improves PAWS for uncurated Semi-iNat by +5.3% and curated ImageNet by +0.4%.

View on arXivView PDF

Code Implementations(1)

facebookresearch/suncetCommunity100%
MIT

Code to reproduce the results in the FAIR research papers "Semi-Supervised Learning of Visual Features by Non-Parametrically Predicting View Assignments with Support Samples" https://arxiv.org/abs/2104.13963 and "Supervision Accelerates Pre-training in Contrastive Semi-Supervised Learning of Visual Representations" https://arxiv.org/abs/2006.10803

49464PythonAug 27, 20203 years agoMIT

Similar Papers

Self Adaptive Threshold Pseudo-labeling and Unreliable Sample Contrastive Loss for Semi-supervised Image Classification

86% match2024

Improving 3D Semi-supervised Learning by Effectively Utilizing All Unlabelled Data

86% match1 repo52026

Generalized Semi-Supervised Learning via Self-Supervised Feature Adaptation

85% match2026

OwMatch: Conditional Self-Labeling with Consistency for Open-World Semi-Supervised Learning

85% match1 repo62026

Exploring Beyond Logits: Hierarchical Dynamic Labeling Based on Embeddings for Semi-Supervised Classification

85% match2024

Pseudo-labelling meets Label Smoothing for Noisy Partial Label Learning

85% match1 repo42024

Cite this paper

@article{mo2026ropaws,
  title  = {RoPAWS: Robust Semi-supervised Representation Learning from Uncurated Data},
  author = {Sangwoo Mo and Jong-Chyi Su and Chih-Yao Ma and Mido Assran and Ishan Misra and Licheng Yu and Sean Bell},
  year   = {2026},
  eprint = {2302.14483},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/pdf/2302.14483},
  journal = {ICLR 2023 2023}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2302.14483.svg)](https://codeofpaper.com/paper/2302.14483)

Discussion