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 2251–2300 of 5044 papers

TitleStatusHype
Contrastive General Graph Matching with Adaptive Augmentation Sampling—0
Preserving Node Distinctness in Graph Autoencoders via Similarity Distillation—0
Self-Supervised Embeddings for Detecting Individual Symptoms of Depression—0
Speaker-Independent Acoustic-to-Articulatory Inversion through Multi-Channel Attention DiscriminatorCode0
Investigating Self-Supervised Methods for Label-Efficient Learning—0
AND: Audio Network Dissection for Interpreting Deep Acoustic Models—0
Cross-domain Transfer of Valence Preferences via a Meta-optimization ApproachCode0
The Hidden Pitfalls of the Cosine Similarity Loss—0
Suppressing Uncertainties in Degradation Estimation for Blind Super-Resolution—0
BrainMAE: A Region-aware Self-supervised Learning Framework for Brain Signals—0
KEHRL: Learning Knowledge-Enhanced Language Representations with Hierarchical Reinforcement LearningCode0
UDHF2-Net: Uncertainty-diffusion-model-based High-Frequency TransFormer Network for Remotely Sensed Imagery Interpretation—0
Self-Supervised Alignment Learning for Medical Image Segmentation—0
Speech Analysis of Language Varieties in ItalyCode0
An Adapter-Based Unified Model for Multiple Spoken Language Processing Tasks—0
Towards evolution of Deep Neural Networks through contrastive Self-Supervised learning—0
SSAD: Self-supervised Auxiliary Detection Framework for Panoramic X-ray based Dental Disease DiagnosisCode0
Liveness Detection in Computer Vision: Transformer-based Self-Supervised Learning for Face Anti-Spoofing—0
MixDiff: Mixing Natural and Synthetic Images for Robust Self-Supervised RepresentationsCode0
Scale-Translation Equivariant Network for Oceanic Internal Solitary Wave LocalizationCode0
Semantic Graph Consistency: Going Beyond Patches for Regularizing Self-Supervised Vision Transformers—0
Deep self-supervised learning with visualisation for automatic gesture recognitionCode0
A dual task learning approach to fine-tune a multilingual semantic speech encoder for Spoken Language Understanding—0
DistillNeRF: Perceiving 3D Scenes from Single-Glance Images by Distilling Neural Fields and Foundation Model Features—0
How Should We Extract Discrete Audio Tokens from Self-Supervised Models?—0
Occam's Razor for Self Supervised Learning: What is Sufficient to Learn Good Representations?—0
A Comprehensive Survey of Foundation Models in Medicine—0
Inclusive ASR for Disfluent Speech: Cascaded Large-Scale Self-Supervised Learning with Targeted Fine-Tuning and Data Augmentation—0
Self-Supervised and Few-Shot Learning for Robust Bioaerosol Monitoring—0
POWN: Prototypical Open-World Node ClassificationCode0
SSTFB: Leveraging self-supervised pretext learning and temporal self-attention with feature branching for real-time video polyp segmentation—0
Shelf-Supervised Cross-Modal Pre-Training for 3D Object DetectionCode0
Towards an Improved Understanding and Utilization of Maximum Manifold Capacity Representations—0
T-JEPA: A Joint-Embedding Predictive Architecture for Trajectory Similarity Computation—0
You Don't Need Domain-Specific Data Augmentations When Scaling Self-Supervised Learning—0
An Image is Worth More Than 16x16 Patches: Exploring Transformers on Individual Pixels—0
LASER: Learning by Aligning Self-supervised Representations of Speech for Improving Content-related TasksCode0
SCDNet: Self-supervised Learning Feature-based Speaker Change Detection—0
SimSAM: Simple Siamese Representations Based Semantic Affinity Matrix for Unsupervised Image SegmentationCode0
GraphFM: A Comprehensive Benchmark for Graph Foundation ModelCode0
Self-supervised Learning of Neural Implicit Feature Fields for Camera Pose Refinement—0
GenDistiller: Distilling Pre-trained Language Models based on an Autoregressive Generative Model—0
From Chaos to Clarity: 3DGS in the Dark—0
Exploring Self-Supervised Multi-view Contrastive Learning for Speech Emotion Recognition with Limited Annotations—0
Emotional Conversation: Empowering Talking Faces with Cohesive Expression, Gaze and Pose Generation—0
It is Never Too Late to Mend: Separate Learning for Multimedia RecommendationCode0
A deep cut into Split Federated Self-supervised LearningCode0
ML-SUPERB 2.0: Benchmarking Multilingual Speech Models Across Modeling Constraints, Languages, and Datasets—0
Object-level Scene Deocclusion—0
Visual Representation Learning with Stochastic Frame Prediction—0
Show:102550
← PrevPage 46 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