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 951–1000 of 5044 papers

TitleStatusHype
Domain-Adaptive Self-Supervised Pre-Training for Face & Body Detection in DrawingsCode1
Representing Part-Whole Hierarchies in Foundation Models by Learning Localizability Composability and Decomposability from Anatomy via Self SupervisionCode1
CrossTransformers: spatially-aware few-shot transferCode1
ReSSL: Relational Self-Supervised Learning with Weak AugmentationCode1
AV2AV: Direct Audio-Visual Speech to Audio-Visual Speech Translation with Unified Audio-Visual Speech RepresentationCode1
Rethinking Goal-conditioned Supervised Learning and Its Connection to Offline RLCode1
Crossway Diffusion: Improving Diffusion-based Visuomotor Policy via Self-supervised LearningCode1
Crowdsourced 3D Mapping: A Combined Multi-View Geometry and Self-Supervised Learning ApproachCode1
2nd Place Solution to Facebook AI Image Similarity Challenge Matching TrackCode1
Revisiting pre-trained remote sensing model benchmarks: resizing and normalization mattersCode1
CSP: Self-Supervised Contrastive Spatial Pre-Training for Geospatial-Visual RepresentationsCode1
Revisiting Weakly Supervised Pre-Training of Visual Perception ModelsCode1
A vector quantized masked autoencoder for speech emotion recognitionCode1
Enhancing Vision-Language Model with Unmasked Token AlignmentCode1
Systematic comparison of semi-supervised and self-supervised learning for medical image classificationCode1
Robustness via Retrying: Closed-Loop Robotic Manipulation with Self-Supervised LearningCode1
Object Segmentation Without Labels with Large-Scale Generative ModelsCode1
Enhancing Intrinsic Adversarial Robustness via Feature Pyramid DecoderCode1
AVF-MAE++: Scaling Affective Video Facial Masked Autoencoders via Efficient Audio-Visual Self-Supervised LearningCode1
SSR: An Efficient and Robust Framework for Learning with Unknown Label NoiseCode1
CutPaste: Self-Supervised Learning for Anomaly Detection and LocalizationCode1
CUTS: A Deep Learning and Topological Framework for Multigranular Unsupervised Medical Image SegmentationCode1
CVF-SID: Cyclic multi-Variate Function for Self-Supervised Image Denoising by Disentangling Noise from ImageCode1
SS-SFDA : Self-Supervised Source-Free Domain Adaptation for Road Segmentation in Hazardous EnvironmentsCode1
eProduct: A Million-Scale Visual Search Benchmark to Address Product Recognition ChallengesCode1
D2C: Diffusion-Decoding Models for Few-Shot Conditional GenerationCode1
Bidirectional Learning for Domain Adaptation of Semantic SegmentationCode1
D2C: Diffusion-Denoising Models for Few-shot Conditional GenerationCode1
End-to-end Multi-modal Video Temporal GroundingCode1
DailyMAE: Towards Pretraining Masked Autoencoders in One DayCode1
DAS-N2N: Machine learning Distributed Acoustic Sensing (DAS) signal denoising without clean dataCode1
data2vec: A General Framework for Self-supervised Learning in Speech, Vision and LanguageCode1
data2vec-aqc: Search for the right Teaching Assistant in the Teacher-Student training setupCode1
Backdoor Defense via Decoupling the Training ProcessCode1
Data Augmentation for Object Detection via Differentiable Neural RenderingCode1
scASDC: Attention Enhanced Structural Deep Clustering for Single-cell RNA-seq DataCode1
End-to-end Multiple Instance Learning with Gradient AccumulationCode1
SCD: Self-Contrastive Decorrelation for Sentence EmbeddingsCode1
Empowering Collaborative Filtering with Principled Adversarial Contrastive LossCode1
Scene Consistency Representation Learning for Video Scene SegmentationCode1
BadEncoder: Backdoor Attacks to Pre-trained Encoders in Self-Supervised LearningCode1
AnatoMask: Enhancing Medical Image Segmentation with Reconstruction-guided Self-maskingCode1
Data-Efficient Contrastive Self-supervised Learning: Most Beneficial Examples for Supervised Learning Contribute the LeastCode1
BADGR: An Autonomous Self-Supervised Learning-Based Navigation SystemCode1
Data-Efficient Reinforcement Learning with Self-Predictive RepresentationsCode1
Bag of Instances Aggregation Boosts Self-supervised DistillationCode1
Anatomical Invariance Modeling and Semantic Alignment for Self-supervised Learning in 3D Medical Image AnalysisCode1
SEED: Self-supervised Distillation For Visual RepresentationCode1
Anatomy-aware Self-supervised Learning for Anomaly Detection in Chest RadiographsCode1
EnCodecMAE: Leveraging neural codecs for universal audio representation learningCode1
Show:102550
← PrevPage 20 of 101Next →
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