Computer Vision
 
Edit

Semi-Supervised Image Classification

124 papers with code • 58 benchmarks • 13 datasets

Semi-supervised image classification leverages unlabelled data as well as labelled data to increase classification performance.

You may want to read some blog posts to get an overview before reading the papers and checking the leaderboards:

( Image credit: Self-Supervised Semi-Supervised Learning )

Libraries

Use these libraries to find Semi-Supervised Image Classification models and implementations
facebookresearch/vissl
7 papers
3,228
lightly-ai/lightly
7 papers
2,742
Westlake-AI/openmixup
7 papers
568
vturrisi/solo-learn
6 papers
1,355
See all 16 libraries.

Datasets

Subtasks

Most implemented papers

Most implemented Social Latest No code

Unsupervised Data Augmentation for Consistency Training

google-research/uda • • NeurIPS 2020

In this work, we present a new perspective on how to effectively noise unlabeled examples and argue that the quality of noising, specifically those produced by advanced data augmentation methods, plays a crucial role in semi-supervised learning.

20
Paper
Code

Unsupervised Learning of Visual Features by Contrasting Cluster Assignments

facebookresearch/swav • • NeurIPS 2020

In addition, we also propose a new data augmentation strategy, multi-crop, that uses a mix of views with different resolutions in place of two full-resolution views, without increasing the memory or compute requirements much.

16
Paper
Code

Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning

takerum/vat_tf • • 13 Apr 2017

In our experiments, we applied VAT to supervised and semi-supervised learning tasks on multiple benchmark datasets.

13
Paper
Code

Semi-Supervised Learning with Ladder Networks

arasmus/ladder • NeurIPS 2015

We combine supervised learning with unsupervised learning in deep neural networks.

10
Paper
Code

Meta Pseudo Labels

google-research/google-research • • CVPR 2021

We present Meta Pseudo Labels, a semi-supervised learning method that achieves a new state-of-the-art top-1 accuracy of 90. 2% on ImageNet, which is 1. 6% better than the existing state-of-the-art.

9
Paper
Code

Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results

CuriousAI/mean-teacher • • NeurIPS 2017

Without changing the network architecture, Mean Teacher achieves an error rate of 4. 35% on SVHN with 250 labels, outperforming Temporal Ensembling trained with 1000 labels.

8
Paper
Code

Big Self-Supervised Models are Strong Semi-Supervised Learners

google-research/simclr • • NeurIPS 2020

The proposed semi-supervised learning algorithm can be summarized in three steps: unsupervised pretraining of a big ResNet model using SimCLRv2, supervised fine-tuning on a few labeled examples, and distillation with unlabeled examples for refining and transferring the task-specific knowledge.

8
Paper
Code

Temporal Ensembling for Semi-Supervised Learning

smlaine2/tempens • 7 Oct 2016

In this paper, we present a simple and efficient method for training deep neural networks in a semi-supervised setting where only a small portion of training data is labeled.

7
Paper
Code

Semi-Supervised Learning with Context-Conditional Generative Adversarial Networks

edenton/cc-gan • 19 Nov 2016

We introduce a simple semi-supervised learning approach for images based on in-painting using an adversarial loss.

7
Paper
Code

Self-Supervised Learning of Pretext-Invariant Representations

facebookresearch/vissl • • CVPR 2020

The goal of self-supervised learning from images is to construct image representations that are semantically meaningful via pretext tasks that do not require semantic annotations for a large training set of images.

7
Paper
Code
Contact us on: hello@paperswithcode.com . Papers With Code is a free resource with all data licensed under CC-BY-SA.
Terms Data policy Cookies policy