paper-with-me

Papers

RoPAWS: Robust Semi-supervised Representation Learning from Uncurated Data

2023-02-28 · Sangwoo Mo, Jong-Chyi Su, Chih-Yao Ma, Mido Assran, Ishan Misra, Licheng Yu, Sean Bell

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%.

📄 PDF Abstract BibTeX arXiv:2302.14483

Code (1)

facebookresearch/suncet 공식 구현 pytorch

Tasks

Density Estimationimage-classificationImage ClassificationRepresentation Learning

Similar Papers 제목 키워드 기반

Fix-A-Step: Semi-supervised Learning from Uncurated Unlabeled Data

2022-08-25 · Zhe Huang, Mary-Joy Sidhom, Benjamin S. Wessler, Michael C. Hughes

Semi-supervised learning (SSL) promises improved accuracy compared to training classifiers on small labeled datasets by also training on many unlabeled images. In real applications like medical imaging, unlabeled data wi…

Active Learning with Task-Driven Representations for Messy Pools

2025-10-29 · Kianoosh Ashouritaklimi, Tom Rainforth arxiv

Active learning has the potential to be especially useful for messy, uncurated pools where datapoints vary in relevance to the target task. However, state-of-the-art approaches to this problem currently rely on using fix…

Active Learning

Semi-Supervised Object Detection with Uncurated Unlabeled Data for Remote Sensing Images

2023-10-09 · Nanqing Liu, Xun Xu, Yingjie Gao, Heng-Chao Li

Annotating remote sensing images (RSIs) presents a notable challenge due to its labor-intensive nature. Semi-supervised object detection (SSOD) methods tackle this issue by generating pseudo-labels for the unlabeled data…

Objectobject-detectionObject DetectionSemi-Supervised Object Detection

Semi-supervised learning objectives as log-likelihoods in a generative model of data curation

2020-08-13 · Stoil Ganev, Laurence Aitchison

We currently do not have an understanding of semi-supervised learning (SSL) objectives such as pseudo-labelling and entropy minimization as log-likelihoods, which precludes the development of e.g. Bayesian SSL. Here, we …

Semi-Supervised Hierarchical Open-Set Classification

2026-01-23 · Erik Wallin, Fredrik Kahl, Lars Hammarstrand arxiv

Hierarchical open-set classification handles previously unseen classes by assigning them to the most appropriate high-level category in a class taxonomy. We extend this paradigm to the semi-supervised setting, enabling t…