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 Added Most Hyped Most Active Needs Verification Most Verified

Showing 1426–1450 of 6661 papers

Title	Date	Tasks	Status	Hype
Max-Margin Contrastive Learning	Dec 21, 2021	Contrastive LearningRepresentation Learning	CodeCode Available	1
Contrast and Generation Make BART a Good Dialogue Emotion Recognizer	Dec 21, 2021	Contrastive LearningDecoder	CodeCode Available	1
Data Efficient Language-supervised Zero-shot Recognition with Optimal Transport Distillation	Dec 17, 2021	Contrastive LearningKnowledge Distillation	CodeCode Available	1
Contrastive Vision-Language Pre-training with Limited Resources	Dec 17, 2021	Contrastive Learning	CodeCode Available	1
Contrastive Spatio-Temporal Pretext Learning for Self-supervised Video Representation	Dec 16, 2021	Contrastive LearningRepresentation Learning	CodeCode Available	1
Unsupervised Dense Information Retrieval with Contrastive Learning	Dec 16, 2021	Contrastive LearningCross-Lingual Transfer	CodeCode Available	1
CLIP-Lite: Information Efficient Visual Representation Learning with Language Supervision	Dec 14, 2021	Contrastive LearningRepresentation Learning	CodeCode Available	1
Learning to Retrieve Passages without Supervision	Dec 14, 2021	Contrastive LearningOpen-Domain Question Answering	CodeCode Available	1
CT4Rec: Simple yet Effective Consistency Training for Sequential Recommendation	Dec 13, 2021	Click-Through Rate PredictionContrastive Learning	CodeCode Available	1
Semantically Contrastive Learning for Low-light Image Enhancement	Dec 13, 2021	Contrastive LearningImage Enhancement	CodeCode Available	1
Self-Supervised Modality-Aware Multiple Granularity Pre-Training for RGB-Infrared Person Re-Identification	Dec 12, 2021	Contrastive LearningCross-Modality Person Re-identification	CodeCode Available	1
Learning Representations with Contrastive Self-Supervised Learning for Histopathology Applications	Dec 10, 2021	BenchmarkingContrastive Learning	CodeCode Available	1
DistilCSE: Effective Knowledge Distillation For Contrastive Sentence Embeddings	Dec 10, 2021	Contrastive LearningKnowledge Distillation	CodeCode Available	1
KGE-CL: Contrastive Learning of Tensor Decomposition Based Knowledge Graph Embeddings	Dec 9, 2021	Contrastive LearningGraph Embedding	CodeCode Available	1
Exploring the Equivalence of Siamese Self-Supervised Learning via A Unified Gradient Framework	Dec 9, 2021	Contrastive LearningLinear evaluation	CodeCode Available	1
SimIPU: Simple 2D Image and 3D Point Cloud Unsupervised Pre-Training for Spatial-Aware Visual Representations	Dec 9, 2021	Contrastive LearningUnsupervised Pre-training	CodeCode Available	1
Contrastive Learning with Large Memory Bank and Negative Embedding Subtraction for Accurate Copy Detection	Dec 8, 2021	Contrastive LearningCopy Detection	CodeCode Available	1
TCGL: Temporal Contrastive Graph for Self-supervised Video Representation Learning	Dec 7, 2021	Action RecognitionContrastive Learning	CodeCode Available	1
Contrastive Learning from Extremely Augmented Skeleton Sequences for Self-supervised Action Recognition	Dec 7, 2021	Action RecognitionContrastive Learning	CodeCode Available	1
Joint Learning of Localized Representations from Medical Images and Reports	Dec 6, 2021	Contrastive Learningimage-classification	CodeCode Available	1
Separated Contrastive Learning for Organ-at-Risk and Gross-Tumor-Volume Segmentation with Limited Annotation	Dec 6, 2021	Contrastive Learning	CodeCode Available	1
Anomaly Detection in IR Images of PV Modules using Supervised Contrastive Learning	Dec 6, 2021	Anomaly DetectionContrastive Learning	CodeCode Available	1
VarCLR: Variable Semantic Representation Pre-training via Contrastive Learning	Dec 5, 2021	Contrastive LearningLearning Semantic Representations	CodeCode Available	1
Transferring Unconditional to Conditional GANs with Hyper-Modulation	Dec 4, 2021	Conditional Image GenerationContrastive Learning	CodeCode Available	1
Contrastive Cross-domain Recommendation in Matching	Dec 2, 2021	Contrastive LearningRepresentation Learning	CodeCode Available	1

Show:10 25 50

← PrevPage 58 of 267Next →

All datasets imagenet-1k 10,000 People - Human Pose Recognition Data CIFAR-10 STL-10

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	ResNet50	ImageNet Top-1 Accuracy	73.6	—	Unverified
2	ResNet50	ImageNet Top-1 Accuracy	73	—	Unverified
3	ResNet50	ImageNet Top-1 Accuracy	71.1	—	Unverified
4	ResNet50	ImageNet Top-1 Accuracy	69.3	—	Unverified
5	ResNet50 (v2)	ImageNet Top-1 Accuracy	67.6	—	Unverified
6	ResNet50 (v2)	ImageNet Top-1 Accuracy	63.8	—	Unverified
7	ResNet50	ImageNet Top-1 Accuracy	63.6	—	Unverified
8	ResNet50	ImageNet Top-1 Accuracy	61.5	—	Unverified
9	ResNet50	ImageNet Top-1 Accuracy	61.5	—	Unverified
10	ResNet50 (4×)	ImageNet Top-1 Accuracy	61.3	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	1	0..5sec	1	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	IPCL (ResNet18)	Accuracy (Top-1)	84.77	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	IPCL (ResNet18)	Accuracy (Top-1)	85.55	—	Unverified