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 5901–5950 of 6661 papers

TitleStatusHype
NuwaTS: a Foundation Model Mending Every Incomplete Time Series—0
NV-Retriever: Improving text embedding models with effective hard-negative mining—0
NYCU_TWD@LT-EDI-ACL2022: Ensemble Models with VADER and Contrastive Learning for Detecting Signs of Depression from Social Media—0
O1 Embedder: Let Retrievers Think Before Action—0
Object2Scene: Putting Objects in Context for Open-Vocabulary 3D Detection—0
Self-Supervised Object Goal Navigation with In-Situ Finetuning—0
OCCO: LVM-guided Infrared and Visible Image Fusion Framework based on Object-aware and Contextual COntrastive Learning—0
OCL: Ordinal Contrastive Learning for Imputating Features with Progressive Labels—0
OCTCube-M: A 3D multimodal optical coherence tomography foundation model for retinal and systemic diseases with cross-cohort and cross-device validation—0
OFAR: A Multimodal Evidence Retrieval Framework for Illegal Live-streaming Identification—0
OmniSage: Large Scale, Multi-Entity Heterogeneous Graph Representation Learning—0
On Bottleneck Features for Text-Dependent Speaker Verification Using X-vectors—0
On Class Separability Pitfalls In Audio-Text Contrastive Zero-Shot Learning—0
One-Bit Active Query With Contrastive Pairs—0
On Finite-Sample Identifiability of Contrastive Learning-Based Nonlinear Independent Component Analysis—0
On Learning Universal Representations Across Languages—0
Metric Compatible Training for Online Backfilling in Large-Scale Retrieval—0
Online Continual Learning with Contrastive Vision Transformer—0
Online Object Representations with Contrastive Learning—0
Online pre-training with long-form videos—0
On Mutual Information in Contrastive Learning for Visual Representations—0
On Negative Sampling for Audio-Visual Contrastive Learning from Movies—0
On Negative Sampling for Contrastive Audio-Text Retrieval—0
On Self-Supervised Image Representations for GAN Evaluation—0
On Task-personalized Multimodal Few-shot Learning for Visually-rich Document Entity Retrieval—0
On the Adversarial Robustness of Graph Contrastive Learning Methods—0
On the Comparison between Multi-modal and Single-modal Contrastive Learning—0
On the Difficulty of Defending Contrastive Learning against Backdoor Attacks—0
On the Effectiveness of Sampled Softmax Loss for Item Recommendation—0
On the Effect of Data-Augmentation on Local Embedding Properties in the Contrastive Learning of Music Audio Representations—0
On the Importance of Contrastive Loss in Multimodal Learning—0
On the Informativeness of Supervision Signals—0
On the Marginal Benefit of Active Learning: Does Self-Supervision Eat Its Cake?—0
On the Memorization Properties of Contrastive Learning—0
On the Provable Advantage of Unsupervised Pretraining—0
On the Robustness of Aspect-based Sentiment Analysis: Rethinking Model, Data, and Training—0
On the Robustness of Pretraining and Self-Supervision for a Deep Learning-based Analysis of Diabetic Retinopathy—0
On the Sequence Evaluation based on Stochastic Processes—0
On the Sweet Spot of Contrastive Views for Knowledge-enhanced Recommendation—0
A Generalization Theory of Cross-Modality Distillation with Contrastive Learning—0
On Training Targets and Activation Functions for Deep Representation Learning in Text-Dependent Speaker Verification—0
OOD Aware Supervised Contrastive Learning—0
OPEn: An Open-ended Physics Environment for Learning Without a Task—0
Open-Set Multivariate Time-Series Anomaly Detection—0
Open-Set Object Detection Using Classification-free Object Proposal and Instance-level Contrastive Learning—0
OpenTuringBench: An Open-Model-based Benchmark and Framework for Machine-Generated Text Detection and Attribution—0
Open-Vocabulary 3D Detection via Image-level Class and Debiased Cross-modal Contrastive Learning—0
Open-Vocabulary Object Detection with Meta Prompt Representation and Instance Contrastive Optimization—0
Open-World Test-Time Training: Self-Training with Contrast Learning—0
Optimal Sample Complexity of Contrastive Learning—0
Show:102550
← PrevPage 119 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