RoPAWS: Robust Semi-supervised Representation Learning from Uncurated Data
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%.
Code (1)
Tasks
Density Estimationimage-classificationImage ClassificationRepresentation LearningSimilar Papers 제목 키워드 기반
Fix-A-Step: Semi-supervised Learning from Uncurated Unlabeled Data
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
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 LearningSemi-Supervised Object Detection with Uncurated Unlabeled Data for Remote Sensing Images
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 DetectionSemi-supervised learning objectives as log-likelihoods in a generative model of data curation
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
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…