SOTAVerified

Contrastive Learning

Contrastive Learning is a deep learning technique for unsupervised representation learning. The goal is to learn a representation of data such that similar instances are close together in the representation space, while dissimilar instances are far apart.

It has been shown to be effective in various computer vision and natural language processing tasks, including image retrieval, zero-shot learning, and cross-modal retrieval. In these tasks, the learned representations can be used as features for downstream tasks such as classification and clustering.

(Image credit: Schroff et al. 2015)

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 4801–4850 of 6661 papers

TitleStatusHype
VLCap: Vision-Language with Contrastive Learning for Coherent Video Paragraph CaptioningCode1
SLIC: Self-Supervised Learning with Iterative Clustering for Human Action VideosCode1
Self-supervised Context-aware Style Representation for Expressive Speech Synthesis—0
Language Models as Knowledge EmbeddingsCode1
Geometry Contrastive Learning on Heterogeneous GraphsCode0
Value-Consistent Representation Learning for Data-Efficient Reinforcement Learning—0
Graph Component Contrastive Learning for Concept Relatedness EstimationCode0
Contrastive Learning of Features between Images and LiDAR—0
Similarity-aware Positive Instance Sampling for Graph Contrastive Pre-training—0
CoSP: Co-supervised pretraining of pocket and ligand—0
Towards Galaxy Foundation Models with Hybrid Contrastive LearningCode1
Utilizing Expert Features for Contrastive Learning of Time-Series RepresentationsCode1
CLAMP: Prompt-based Contrastive Learning for Connecting Language and Animal PoseCode1
A Feature Memory Rearrangement Network for Visual Inspection of Textured Surface Defects Toward Edge Intelligent Manufacturing—0
Panoramic Panoptic Segmentation: Insights Into Surrounding Parsing for Mobile Agents via Unsupervised Contrastive LearningCode1
Probing Visual-Audio Representation for Video Highlight Detection via Hard-Pairs Guided Contrastive Learning—0
Enhancing Multi-view Stereo with Contrastive Matching and Weighted Focal LossCode2
Robust Task Representations for Offline Meta-Reinforcement Learning via Contrastive LearningCode1
Few-Max: Few-Shot Domain Adaptation for Unsupervised Contrastive Representation LearningCode0
Rethinking Audio-visual Synchronization for Active Speaker Detection—0
Visualizing and Understanding Contrastive LearningCode0
Self-Supervised Consistent Quantization for Fully Unsupervised Image Retrieval—0
C-SENN: Contrastive Self-Explaining Neural Network—0
Conditioned and Composed Image Retrieval Combining and Partially Fine-Tuning CLIP-Based FeaturesCode1
Self-Supervised Learning for Videos: A SurveyCode0
Evaluation of Contrastive Learning with Various Code Representations for Code Clone Detection—0
MET: Masked Encoding for Tabular DataCode1
DU-Net based Unsupervised Contrastive Learning for Cancer Segmentation in Histology Images—0
Learning Fair Representation via Distributional Contrastive DisentanglementCode1
VLMixer: Unpaired Vision-Language Pre-training via Cross-Modal CutMix—0
Beyond Supervised vs. Unsupervised: Representative Benchmarking and Analysis of Image Representation LearningCode0
NCAGC: A Neighborhood Contrast Framework for Attributed Graph ClusteringCode1
Volumetric Supervised Contrastive Learning for Seismic Semantic Segmentation—0
Let Invariant Rationale Discovery Inspire Graph Contrastive LearningCode1
Text-Aware End-to-end Mispronunciation Detection and DiagnosisCode1
Contrastive Learning as Goal-Conditioned Reinforcement Learning—0
Discrete Contrastive Diffusion for Cross-Modal Music and Image GenerationCode1
Label-enhanced Prototypical Network with Contrastive Learning for Multi-label Few-shot Aspect Category Detection—0
Towards a Solution to Bongard Problems: A Causal Approach—0
On Finite-Sample Identifiability of Contrastive Learning-Based Nonlinear Independent Component Analysis—0
Self-Supervised Representation Learning With MUlti-Segmental Informational Coding (MUSIC)—0
Contrastive Learning for Unsupervised Domain Adaptation of Time SeriesCode1
Transductive CLIP with Class-Conditional Contrastive Learning—0
GLIPv2: Unifying Localization and Vision-Language UnderstandingCode4
Is Self-Supervised Learning More Robust Than Supervised Learning?—0
ClamNet: Using contrastive learning with variable depth Unets for medical image segmentation—0
STNDT: Modeling Neural Population Activity with a Spatiotemporal Transformer—0
COSTA: Covariance-Preserving Feature Augmentation for Graph Contrastive LearningCode1
I'm Me, We're Us, and I'm Us: Tri-directional Contrastive Learning on HypergraphsCode1
An Empirical Study on Disentanglement of Negative-free Contrastive LearningCode1
Show:102550
← PrevPage 97 of 134Next →
All datasetsimagenet-1k10,000 People - Human Pose Recognition DataCIFAR-10STL-10

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ResNet50ImageNet Top-1 Accuracy73.6—Unverified
2ResNet50ImageNet Top-1 Accuracy73—Unverified
3ResNet50ImageNet Top-1 Accuracy71.1—Unverified
4ResNet50ImageNet Top-1 Accuracy69.3—Unverified
5ResNet50 (v2)ImageNet Top-1 Accuracy67.6—Unverified
6ResNet50 (v2)ImageNet Top-1 Accuracy63.8—Unverified
7ResNet50ImageNet Top-1 Accuracy63.6—Unverified
8ResNet50ImageNet Top-1 Accuracy61.5—Unverified
9ResNet50ImageNet Top-1 Accuracy61.5—Unverified
10ResNet50 (4×)ImageNet Top-1 Accuracy61.3—Unverified
#ModelMetricClaimedVerifiedStatus
110..5sec1—Unverified
#ModelMetricClaimedVerifiedStatus
1IPCL (ResNet18)Accuracy (Top-1)84.77—Unverified
#ModelMetricClaimedVerifiedStatus
1IPCL (ResNet18)Accuracy (Top-1)85.55—Unverified