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 851–875 of 6661 papers

TitleStatusHype
SimC3D: A Simple Contrastive 3D Pretraining Framework Using RGB ImagesCode0
DAug: Diffusion-based Channel Augmentation for Radiology Image Retrieval and Classification—0
OCEAN: Open-World Contrastive Authorship IdentificationCode0
Rethinking Time Series Forecasting with LLMs via Nearest Neighbor Contrastive Learning—0
Revitalizing Reconstruction Models for Multi-class Anomaly Detection via Class-Aware Contrastive Learning—0
Enhancing Cross-Language Code Translation via Task-Specific Embedding Alignment in Retrieval-Augmented Generation—0
A Framework For Image Synthesis Using Supervised Contrastive Learning—0
HEAL: Hierarchical Embedding Alignment Loss for Improved Retrieval and Representation LearningCode1
Towards Zero-shot 3D Anomaly Localization—0
Florence-VL: Enhancing Vision-Language Models with Generative Vision Encoder and Depth-Breadth FusionCode3
Enhancing Whole Slide Image Classification through Supervised Contrastive Domain Adaptation—0
Dynamic Graph Representation with Contrastive Learning for Financial Market Prediction: Integrating Temporal Evolution and Static RelationsCode0
CLIP-PING: Boosting Lightweight Vision-Language Models with Proximus Intrinsic Neighbors Guidance—0
Language Model Meets Prototypes: Towards Interpretable Text Classification Models through Prototypical Networks—0
Tight PAC-Bayesian Risk Certificates for Contrastive LearningCode0
Cluster Specific Representation Learning—0
3D Interaction Geometric Pre-training for Molecular Relational LearningCode1
Stain-aware Domain Alignment for Imbalance Blood Cell ClassificationCode0
TREND: Unsupervised 3D Representation Learning via Temporal Forecasting for LiDAR Perception—0
Enhancing CLIP Conceptual Embedding through Knowledge Distillation—0
Memory-efficient Continual Learning with Neural Collapse Contrastive—0
Improving Language Transfer Capability of Decoder-only Architecture in Multilingual Neural Machine TranslationCode0
Low-Contrast-Enhanced Contrastive Learning for Semi-Supervised Endoscopic Image SegmentationCode0
CLERF: Contrastive LEaRning for Full Range Head Pose Estimation—0
BANER: Boundary-Aware LLMs for Few-Shot Named Entity RecognitionCode0
Show:102550
← PrevPage 35 of 267Next →
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