Open-World Semi-Supervised Learning
11 papers with code • 3 benchmarks • 2 datasets
Benchmarks
These leaderboards are used to track progress in Open-World Semi-Supervised Learning
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
CIFAR-10
CIFAR-100
Most implemented papers
Parametric Classification for Generalized Category Discovery: A Baseline Study
Generalized Category Discovery (GCD) aims to discover novel categories in unlabelled datasets using knowledge learned from labelled samples.
Open-World Semi-Supervised Learning
snap-stanford/orca
•
•
ICLR 2022
Here, we introduce a novel open-world semi-supervised learning setting that formalizes the notion that novel classes may appear in the unlabeled test data.
Generalized Category Discovery
sgvaze/generalized-category-discovery
•
•
CVPR 2022
Here, the unlabelled images may come from labelled classes or from novel ones.
Towards Realistic Semi-Supervised Learning
We also highlight the flexibility of our approach in solving novel class discovery task, demonstrate its stability in dealing with imbalanced data, and complement our approach with a technique to estimate the number of novel classes
OpenLDN: Learning to Discover Novel Classes for Open-World Semi-Supervised Learning
In the open-world SSL problem, the objective is to recognize samples of known classes, and simultaneously detect and cluster samples belonging to novel classes present in unlabeled data.
Bridging the Gap: Learning Pace Synchronization for Open-World Semi-Supervised Learning
In open-world semi-supervised learning, a machine learning model is tasked with uncovering novel categories from unlabeled data while maintaining performance on seen categories from labeled data.
Discover and Align Taxonomic Context Priors for Open-world Semi-Supervised Learning
rain305f/tida
•
•
It allows us to discover multi-granularity semantic concepts as taxonomic context priors (i. e., sub-class, target-class, and super-class), and then collaboratively leverage them to enhance representation learning and improve the quality of pseudo labels.
Discover and Align Taxonomic Context Priors for Open-world Semi-Supervised Learning
rain305f/tida
•
•
NeurIPS 2023
It allows us to discover multi-granularity semantic concepts as taxonomic context priors (i. e., sub-class, target-class, and super-class), and then collaboratively leverage them to enhance representation learning and improve the quality of pseudo labels.
A Graph-Theoretic Framework for Understanding Open-World Semi-Supervised Learning
deeplearning-wisc/sorl
•
•
NeurIPS 2023
Open-world semi-supervised learning aims at inferring both known and novel classes in unlabeled data, by harnessing prior knowledge from a labeled set with known classes.
Open-World Semi-Supervised Learning for Node Classification
Open-world semi-supervised learning (Open-world SSL) for node classification, that classifies unlabeled nodes into seen classes or multiple novel classes, is a practical but under-explored problem in the graph community.
