Self-Supervised Learning
1749 papers with code • 10 benchmarks • 41 datasets
Self-Supervised Learning is proposed for utilizing unlabeled data with the success of supervised learning. Producing a dataset with good labels is expensive, while unlabeled data is being generated all the time. The motivation of Self-Supervised Learning is to make use of the large amount of unlabeled data. The main idea of Self-Supervised Learning is to generate the labels from unlabeled data, according to the structure or characteristics of the data itself, and then train on this unsupervised data in a supervised manner. Self-Supervised Learning is wildly used in representation learning to make a model learn the latent features of the data. This technique is often employed in computer vision, video processing and robot control.
Source: Self-supervised Point Set Local Descriptors for Point Cloud Registration
Image source: LeCun
Benchmarks
These leaderboards are used to track progress in Self-Supervised Learning
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Self-Supervised Learning models and implementationsDatasets
CIFAR-10
CIFAR-100
STL-10
Tiny ImageNet
2D-3D-S
NSynth
AVA
CATER
MotionSense
COCO 10% labeled data
Latest papers
Hypergraph Self-supervised Learning with Sampling-efficient Signals
coco-hut/se-hssl
•
•
Self-supervised learning (SSL) provides a promising alternative for representation learning on hypergraphs without costly labels.
Masked Autoencoders for Microscopy are Scalable Learners of Cellular Biology
recursionpharma/maes_microscopy
•
•
Featurizing microscopy images for use in biological research remains a significant challenge, especially for large-scale experiments spanning millions of images.
Multi-Task Multi-Modal Self-Supervised Learning for Facial Expression Recognition
To that end, we examine the performance of learning through different combinations of self-supervised tasks on the facial expression recognition downstream task.
How to build the best medical image segmentation algorithm using foundation models: a comprehensive empirical study with Segment Anything Model
mazurowski-lab/finetune-sam
•
•
Automated segmentation is a fundamental medical image analysis task, which enjoys significant advances due to the advent of deep learning.
Can We Break Free from Strong Data Augmentations in Self-Supervised Learning?
Self-supervised learning (SSL) has emerged as a promising solution for addressing the challenge of limited labeled data in deep neural networks (DNNs), offering scalability potential.
DEGNN: Dual Experts Graph Neural Network Handling Both Edge and Node Feature Noise
Leveraging these modified representations, DEGNN subsequently addresses downstream tasks, ensuring robustness against noise present in both edges and node features of real-world graphs.
An Experimental Comparison Of Multi-view Self-supervised Methods For Music Tagging
deezer/multi-view-ssl-benchmark
•
•
In this study, we expand the scope of pretext tasks applied to music by investigating and comparing the performance of new self-supervised methods for music tagging.
MMA-DFER: MultiModal Adaptation of unimodal models for Dynamic Facial Expression Recognition in-the-wild
Within the field of multimodal DFER, recent methods have focused on exploiting advances of self-supervised learning (SSL) for pre-training of strong multimodal encoders.
OmniSat: Self-Supervised Modality Fusion for Earth Observation
To demonstrate the advantages of combining modalities of different natures, we augment two existing datasets with new modalities.
Masked Image Modeling as a Framework for Self-Supervised Learning across Eye Movements
To make sense of their surroundings, intelligent systems must transform complex sensory inputs to structured codes that are reduced to task-relevant information such as object category.
