SOTAVerified

Self-Supervised Learning

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

Papers

Showing 351400 of 5044 papers

TitleStatusHype
A Self-supervised Method for Entity AlignmentCode1
A Fast Knowledge Distillation Framework for Visual RecognitionCode1
3D Self-Supervised Methods for Medical ImagingCode1
Boundary-aware Self-supervised Learning for Video Scene SegmentationCode1
Deep fiber clustering: Anatomically informed fiber clustering with self-supervised deep learning for fast and effective tractography parcellationCode1
Broken Neural Scaling LawsCode1
Broaden Your Views for Self-Supervised Video LearningCode1
A Simple and Efficient Baseline for Data Attribution on ImagesCode1
Blockwise Self-Supervised Learning at ScaleCode1
A Simple Baseline for Low-Budget Active LearningCode1
A Self-Supervised Gait Encoding Approach with Locality-Awareness for 3D Skeleton Based Person Re-IdentificationCode1
A simple, efficient and scalable contrastive masked autoencoder for learning visual representationsCode1
Mitigating Memorization of Noisy Labels via Regularization between RepresentationsCode1
BirdSAT: Cross-View Contrastive Masked Autoencoders for Bird Species Classification and MappingCode1
Delving Deep into the Generalization of Vision Transformers under Distribution ShiftsCode1
BYOL for Audio: Self-Supervised Learning for General-Purpose Audio RepresentationCode1
Self-supervised Learning from a Multi-view PerspectiveCode1
EXAONEPath 1.0 Patch-level Foundation Model for PathologyCode1
BIOSCAN-5M: A Multimodal Dataset for Insect BiodiversityCode1
A Self-Correcting Sequential RecommenderCode1
Can a MISL Fly? Analysis and Ingredients for Mutual Information Skill LearningCode1
ASSET: Robust Backdoor Data Detection Across a Multiplicity of Deep Learning ParadigmsCode1
DeiT III: Revenge of the ViTCode1
Boosting Contrastive Self-Supervised Learning with False Negative CancellationCode1
COSMOS: Catching Out-of-Context Misinformation with Self-Supervised LearningCode1
Can Vision Transformers Learn without Natural Images?Code1
CASS: Cross Architectural Self-Supervision for Medical Image AnalysisCode1
CARLANE: A Lane Detection Benchmark for Unsupervised Domain Adaptation from Simulation to multiple Real-World DomainsCode1
A Study on Incorporating Whisper for Robust Speech AssessmentCode1
Causal Unsupervised Semantic SegmentationCode1
CCGL: Contrastive Cascade Graph LearningCode1
A Surface Geometry Model for LiDAR Depth CompletionCode1
Binning as a Pretext Task: Improving Self-Supervised Learning in Tabular DomainsCode1
Bootstrap your own latent: A new approach to self-supervised LearningCode1
Charting the Right Manifold: Manifold Mixup for Few-shot LearningCode1
Chasing Clouds: Differentiable Volumetric Rasterisation of Point Clouds as a Highly Efficient and Accurate Loss for Large-Scale Deformable 3D RegistrationCode1
Civil Rephrases Of Toxic Texts With Self-Supervised TransformersCode1
Contrastive Neural Processes for Self-Supervised LearningCode1
A Survey on Self-supervised Learning: Algorithms, Applications, and Future TrendsCode1
DeLoRes: Decorrelating Latent Spaces for Low-Resource Audio Representation LearningCode1
3rd Place: A Global and Local Dual Retrieval Solution to Facebook AI Image Similarity ChallengeCode1
CLIP meets DINO for Tuning Zero-Shot Classifier using Unlabeled Image CollectionsCode1
A Survey of World Models for Autonomous DrivingCode1
An Embarrassingly Simple Backdoor Attack on Self-supervised LearningCode1
Differentiable Raycasting for Self-supervised Occupancy ForecastingCode1
CLOOB: Modern Hopfield Networks with InfoLOOB Outperform CLIPCode1
A Survey on Deep Multi-modal Learning for Body Language Recognition and GenerationCode1
Bidirectional Learning for Domain Adaptation of Semantic SegmentationCode1
AgriCLIP: Adapting CLIP for Agriculture and Livestock via Domain-Specialized Cross-Model AlignmentCode1
Adversarial Self-Supervised Contrastive LearningCode1
Show:102550
← PrevPage 8 of 101Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Pretraining: NoneImages & Text57.5Unverified
2Pretraining: ShEDImages & Text54.3Unverified
3Pretraining: e-MixImages & Text48.9Unverified
#ModelMetricClaimedVerifiedStatus
1ResNet50Accuracy91.7Unverified
2ResNet18Accuracy91.02Unverified
3MV-MRAccuracy89.67Unverified
#ModelMetricClaimedVerifiedStatus
1ResNet50average top-1 classification accuracy93.89Unverified
2ResNet18average top-1 classification accuracy92.58Unverified
#ModelMetricClaimedVerifiedStatus
1ResNet50average top-1 classification accuracy72.51Unverified
2ResNet18average top-1 classification accuracy69.31Unverified
#ModelMetricClaimedVerifiedStatus
1CorInfomax (ResNet50)Top-1 Accuracy82.64Unverified
2CorInfomax (ResNet18)Top-1 Accuracy80.48Unverified
#ModelMetricClaimedVerifiedStatus
1ResNet50average top-1 classification accuracy51.84Unverified
2ResNet18average top-1 classification accuracy51.67Unverified
#ModelMetricClaimedVerifiedStatus
1CorInfomax (ResNet18)Top-1 Accuracy93.18Unverified
#ModelMetricClaimedVerifiedStatus
1CorInfomax (ResNet18)Top-1 Accuracy71.61Unverified
#ModelMetricClaimedVerifiedStatus
1Hybrid BYOL-S/CvTAccuracy67.2Unverified
#ModelMetricClaimedVerifiedStatus
1CorInfomax (ResNet50)Top-1 Accuracy54.86Unverified