Self-Supervised Learning
1731 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 with no code
OPTiML: Dense Semantic Invariance Using Optimal Transport for Self-Supervised Medical Image Representation
In response to these constraints, we introduce a novel SSL framework OPTiML, employing optimal transport (OT), to capture the dense semantic invariance and fine-grained details, thereby enhancing the overall effectiveness of SSL in medical image representation learning.
Learning to Solve the Constrained Most Probable Explanation Task in Probabilistic Graphical Models
Given an assignment $\mathbf{x}$ to all variables in $\mathbf{X}$ (evidence) and a real number $q$, the constrained most-probable explanation (CMPE) task seeks to find an assignment $\mathbf{y}$ to all variables in $\mathbf{Y}$ such that $f(\mathbf{x}, \mathbf{y})$ is maximized and $g(\mathbf{x}, \mathbf{y})\leq q$.
Spatial Context-based Self-Supervised Learning for Handwritten Text Recognition
Handwritten Text Recognition (HTR) is a relevant problem in computer vision, and implies unique challenges owing to its inherent variability and the rich contextualization required for its interpretation.
Deep Pattern Network for Click-Through Rate Prediction
These patterns harbor substantial potential to significantly enhance CTR prediction performance.
When are Foundation Models Effective? Understanding the Suitability for Pixel-Level Classification Using Multispectral Imagery
This work aims to enhance the understanding of the status and suitability of foundation models for pixel-level classification using multispectral imagery at moderate resolution, through comparisons with traditional machine learning (ML) and regular-size deep learning models.
Pretraining Billion-scale Geospatial Foundational Models on Frontier
Although large FMs have demonstrated significant impact in natural language processing and computer vision, efforts toward FMs for geospatial applications have been restricted to smaller size models, as pretraining larger models requires very large computing resources equipped with state-of-the-art hardware accelerators.
Integration of Self-Supervised BYOL in Semi-Supervised Medical Image Recognition
Image recognition techniques heavily rely on abundant labeled data, particularly in medical contexts.
Self-Supervised Learning Featuring Small-Scale Image Dataset for Treatable Retinal Diseases Classification
The proposed SSL model achieves the state-of-art accuracy of 98. 84% using only 4, 000 training images.
Label-free Anomaly Detection in Aerial Agricultural Images with Masked Image Modeling
Hence, this is posed as an anomaly detection task in agricultural images.
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.
