Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

semi-supervised-image-classification

Open-World Semi-Supervised Learning

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in semi-supervised-image-classification

Trend

Dataset

Best Model

Actions

CIFAR-10

ImageNet-100

CIFAR-100

Libraries

Use these libraries to find semi-supervised-image-classification models and implementations

Datasets

CIFAR-10

CIFAR-100

Subtasks

No subtasks available.

Most implemented papers

Parametric Classification for Generalized Category Discovery: A Baseline Study

Xiaojuan Qi, Bingchen Zhao, Xin Wen•Sun Nov 20 2022

This study investigates the failure of parametric classifiers, verifies the effectiveness of previous design choices when high-quality supervision is available, and identifies unreliable pseudo-labels as a key problem.

128

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

Paper Graph

Generalized Category Discovery

Andrew Zisserman, A. Vedaldi, S. Vaze, Kai Han•Thu Jan 06 2022

This paper establishes strong baselines by taking state-of-the-art algorithms from novel category discovery and adapting them for this task, and introduces a simple yet effective semi-supervised k-means method to cluster the unlabelled data into seen and unseen classes automatically, substantially outperforming the baselines.

273 0

Paper Graph

Open-World Semi-Supervised Learning

J. Leskovec, Kaidi Cao, Maria Brbic•Fri Feb 05 2021

ORCA, an end-to-end deep learning approach that introduces uncertainty adaptive margin mechanism to circumvent the bias towards seen classes caused by learning discriminative features for seen classes faster than for the novel classes, reduces the gap between intra-class variance of seen with respect to novel classes.

234 0

Paper Graph

OpenLDN: Learning to Discover Novel Classes for Open-World Semi-Supervised Learning

Navid Kardan, M. Shah, F. Khan, Salman H. Khan, Mamshad Nayeem Rizve•Mon Jul 04 2022

This work introduces OpenLDN that utilizes a pairwise similarity loss to discover novel classes that outperforms the current state-of-the-art methods on multiple popular classification benchmarks while providing a better accuracy/training time trade-off.

68 0

Paper Graph

Towards Realistic Semi-Supervised Learning

Navid Kardan, M. Shah, Mamshad Nayeem Rizve•Mon Jul 04 2022

A novel pseudo-label based approach to tackle SSL in open-world setting that utilizes sample uncertainty and incorporate prior knowledge about class distribution to generate reliable class-distribution-aware pseudo-labels for unlabeled data belonging to both known and unknown classes.

61 0

Paper Graph

A Graph-Theoretic Framework for Understanding Open-World Semi-Supervised Learning

Yiyou Sun, Zhenmei Shi, Yixuan Li•Sun Nov 05 2023

This paper formalizes a graph-theoretic framework tailored for the open-world setting, where the clustering can be theoretically characterized by graph factorization, and applies the algorithm called Spectral Open-world Representation Learning (SORL), which can match or outperform several strong baselines on common benchmark datasets.

31 0

Paper Graph

Open-World Semi-Supervised Learning for Node Classification

Jing Zhang, Cuiping Li, Yanling Wang, Lingxi Zhang, Lixin Liu, Yuxiao Dong, Hong Chen, Hongzhi Yin•Sun Mar 17 2024

This paper proposes an IMbalance-A ware method named OpenIMA for Open-world semi-supervised node classification, which trains the node classification model from scratch via contrastive learning with bias-reduced pseudo labels.

4 0

Paper Graph

Robust Semi-Supervised Learning for Self-learning Open-World Classes

Wenjuan Xi, Xin Song, Weili Guo, Yang Yang•Thu Nov 30 2023

This paper proposes an open-world SSL method for Self-learning Open-world Classes (SSOC), which can explicitly self-learn multiple unknown classes and designs a pairwise similarity loss in addition to the entropy loss to effectively discover novel classes.

16 0

Paper Graph

Adding a benchmark result helps the community track progress.

Open-World Semi-Supervised Learning | State-of-the-Art