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 4376–4400 of 6661 papers

TitleStatusHype
BEV-DG: Cross-Modal Learning under Bird's-Eye View for Domain Generalization of 3D Semantic Segmentation—0
Leveraging multi-view data without annotations for prostate MRI segmentation: A contrastive approach—0
Generating Faithful Text From a Knowledge Graph with Noisy Reference Text—0
Counterfactual Cross-modality Reasoning for Weakly Supervised Video Moment LocalizationCode0
CSPM: A Contrastive Spatiotemporal Preference Model for CTR Prediction in On-Demand Food Delivery Services—0
Induction Network: Audio-Visual Modality Gap-Bridging for Self-Supervised Sound Source LocalizationCode0
Cross-view Semantic Alignment for Livestreaming Product RecognitionCode0
Slot Induction via Pre-trained Language Model Probing and Multi-level Contrastive LearningCode0
A Bi-directional Multi-hop Inference Model for Joint Dialog Sentiment Classification and Act Recognition—0
Exploring Transformers for Open-world Instance Segmentation—0
Revisiting Disentanglement and Fusion on Modality and Context in Conversational Multimodal Emotion Recognition—0
Expression Prompt Collaboration Transformer for Universal Referring Video Object SegmentationCode0
Multi-Label Self-Supervised Learning with Scene Images—0
Hierarchical Contrastive Learning with Multiple Augmentation for Sequential Recommendation—0
Exploring Visual Pre-training for Robot Manipulation: Datasets, Models and Methods—0
A Hybrid CNN-Transformer Architecture with Frequency Domain Contrastive Learning for Image Deraining—0
Local Structure-aware Graph Contrastive Representation Learning—0
Towards General Text Embeddings with Multi-stage Contrastive Learning—0
All-in-one Multi-degradation Image Restoration Network via Hierarchical Degradation Representation—0
Bootstrapping Contrastive Learning Enhanced Music Cold-Start Matching—0
Semi-supervised Contrastive Regression for Estimation of Eye Gaze—0
Efficient Labelling of Affective Video Datasets via Few-Shot & Multi-Task Contrastive LearningCode0
Adapting to Change: Robust Counterfactual Explanations in Dynamic Data LandscapesCode0
Learning Referring Video Object Segmentation from Weak Annotation—0
From Fake to Hyperpartisan News Detection Using Domain Adaptation—0
Show:102550
← PrevPage 176 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