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
Most implemented papers
Digging Into Self-Supervised Monocular Depth Estimation
Per-pixel ground-truth depth data is challenging to acquire at scale.
Neighbor2Neighbor: Self-Supervised Denoising from Single Noisy Images
TaoHuang2018/Neighbor2Neighbor
•
•
CVPR 2021
In this paper, we present a very simple yet effective method named Neighbor2Neighbor to train an effective image denoising model with only noisy images.
DeiT III: Revenge of the ViT
Our evaluations on Image classification (ImageNet-1k with and without pre-training on ImageNet-21k), transfer learning and semantic segmentation show that our procedure outperforms by a large margin previous fully supervised training recipes for ViT.
ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders
facebookresearch/convnext-v2
•
•
CVPR 2023
This co-design of self-supervised learning techniques and architectural improvement results in a new model family called ConvNeXt V2, which significantly improves the performance of pure ConvNets on various recognition benchmarks, including ImageNet classification, COCO detection, and ADE20K segmentation.
data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language
pytorch/fairseq
•
•
Preprint 2022
While the general idea of self-supervised learning is identical across modalities, the actual algorithms and objectives differ widely because they were developed with a single modality in mind.
Whitening for Self-Supervised Representation Learning
Most of the current self-supervised representation learning (SSL) methods are based on the contrastive loss and the instance-discrimination task, where augmented versions of the same image instance ("positives") are contrasted with instances extracted from other images ("negatives").
Bootstrap Your Own Latent - A New Approach to Self-Supervised Learning
open-mmlab/mmselfsup
•
•
NeurIPS 2020
From an augmented view of an image, we train the online network to predict the target network representation of the same image under a different augmented view.
An Empirical Study of Training Self-Supervised Vision Transformers
facebookresearch/moco-v3
•
•
ICCV 2021
In this work, we go back to basics and investigate the effects of several fundamental components for training self-supervised ViT.
Time-Contrastive Networks: Self-Supervised Learning from Video
While representations are learned from an unlabeled collection of task-related videos, robot behaviors such as pouring are learned by watching a single 3rd-person demonstration by a human.
Charting the Right Manifold: Manifold Mixup for Few-shot Learning
A recent regularization technique - Manifold Mixup focuses on learning a general-purpose representation, robust to small changes in the data distribution.
