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

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 4401–4425 of 5044 papers

TitleStatusHype
On the Impact of Quantization and Pruning of Self-Supervised Speech Models for Downstream Speech Recognition Tasks "In-the-Wild''—0
On the Impact of Word Error Rate on Acoustic-Linguistic Speech Emotion Recognition: An Update for the Deep Learning Era—0
On the Importance of Hyperparameters and Data Augmentation for Self-Supervised Learning—0
On the Memorization Properties of Contrastive Learning—0
On the Origin of Species of Self-Supervised Learning—0
On the Power of Foundation Models—0
On the Pros and Cons of Momentum Encoder in Self-Supervised Visual Representation Learning—0
On the Robustness of Arabic Speech Dialect Identification—0
On the Role of Corpus Ordering in Language Modeling—0
On the Sins of Image Synthesis Loss for Self-supervised Depth Estimation—0
On the social bias of speech self-supervised models—0
On the surprising similarities between supervised and self-supervised models—0
On the use of Performer and Agent Attention for Spoken Language Identification—0
On the Use of Self-Supervised Speech Representations in Spontaneous Speech Synthesis—0
On Vision Transformers for Classification Tasks in Side-Scan Sonar Imagery—0
On visual self-supervision and its effect on model robustness—0
Open Challenges and Opportunities in Federated Foundation Models Towards Biomedical Healthcare—0
Open Implementation and Study of BEST-RQ for Speech Processing—0
OpenMixup: Open Mixup Toolbox and Benchmark for Visual Representation Learning—0
Open-World Skill Discovery from Unsegmented Demonstrations—0
Opportunistic Osteoporosis Diagnosis via Texture-Preserving Self-Supervision, Mixture of Experts and Multi-Task Integration—0
Optimizing Audio Augmentations for Contrastive Learning of Health-Related Acoustic Signals—0
OPTiML: Dense Semantic Invariance Using Optimal Transport for Self-Supervised Medical Image Representation—0
OPTIMUS: Observing Persistent Transformations in Multi-temporal Unlabeled Satellite-data—0
Orienting Novel 3D Objects Using Self-Supervised Learning of Rotation Transforms—0
Show:102550
← PrevPage 177 of 202Next →
All datasetsDABSSTL-10CIFAR10cifar100ImageNet-100 (TEMI Split)TinyImageNetCIFAR-10CIFAR-100CREMA-DTiny ImageNet

Benchmark Results

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