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 1651–1675 of 6661 papers

Title	Date	Tasks	Status	Hype	Score
CSP: Self-Supervised Contrastive Spatial Pre-Training for Geospatial-Visual Representations	May 1, 2023	Contrastive Learningimage-classification	CodeCode Available	1	5
Improving Composed Image Retrieval via Contrastive Learning with Scaling Positives and Negatives	Apr 17, 2024	Contrastive LearningImage Retrieval	CodeCode Available	1	5
Towards Cross-Table Masked Pretraining for Web Data Mining	Jul 10, 2023	Contrastive Learning	CodeCode Available	1	5
Improving Contrastive Learning by Visualizing Feature Transformation	Aug 6, 2021	Contrastive LearningData Augmentation	CodeCode Available	1	5
A Simple and Effective Self-Supervised Contrastive Learning Framework for Aspect Detection	Sep 18, 2020	Contrastive LearningTopic Models	CodeCode Available	1	5
Improving Contrastive Learning on Imbalanced Seed Data via Open-World Sampling	Nov 1, 2021	AttributeContrastive Learning	CodeCode Available	1	5
Improving Contrastive Learning of Sentence Embeddings from AI Feedback	May 3, 2023	Contrastive LearningData Augmentation	CodeCode Available	1	5
Pretext-Contrastive Learning: Toward Good Practices in Self-supervised Video Representation Leaning	Oct 29, 2020	Contrastive LearningData Augmentation	CodeCode Available	1	5
CL4CTR: A Contrastive Learning Framework for CTR Prediction	Dec 1, 2022	Click-Through Rate PredictionContrastive Learning	CodeCode Available	1	5
Improving Contrastive Learning on Imbalanced Data via Open-World Sampling	May 21, 2021	AttributeContrastive Learning	CodeCode Available	1	5
CURL: Contrastive Unsupervised Representation Learning for Reinforcement Learning	Jan 1, 2020	Contrastive Learningreinforcement-learning	CodeCode Available	1	5
CURL: Contrastive Unsupervised Representations for Reinforcement Learning	Apr 8, 2020	Atari GamesAtari Games 100k	CodeCode Available	1	5
CLAD: Robust Audio Deepfake Detection Against Manipulation Attacks with Contrastive Learning	Apr 24, 2024	Audio Deepfake DetectionContrastive Learning	CodeCode Available	1	5
Improving Hateful Meme Detection through Retrieval-Guided Contrastive Learning	Nov 14, 2023	Contrastive LearningHateful Meme Classification	CodeCode Available	1	5
Improving Text-to-Image Synthesis Using Contrastive Learning	Jul 6, 2021	Contrastive LearningImage Generation	CodeCode Available	1	5
Improving Word Translation via Two-Stage Contrastive Learning	Mar 15, 2022	Bilingual Lexicon InductionContrastive Learning	CodeCode Available	1	5
Data-Efficient Contrastive Self-supervised Learning: Most Beneficial Examples for Supervised Learning Contribute the Least	Feb 18, 2023	Contrastive LearningOpen-Ended Question Answering	CodeCode Available	1	5
A Simple Contrastive Learning Objective for Alleviating Neural Text Degeneration	May 5, 2022	Contrastive LearningDialogue Generation	CodeCode Available	1	5
Company-as-Tribe: Company Financial Risk Assessment on Tribe-Style Graph with Hierarchical Graph Neural Networks	Jan 31, 2023	Contrastive LearningGraph Learning	CodeCode Available	1	5
Improving Molecular Contrastive Learning via Faulty Negative Mitigation and Decomposed Fragment Contrast	Feb 18, 2022	Computational chemistryContrastive Learning	CodeCode Available	1	5
A simple, efficient and scalable contrastive masked autoencoder for learning visual representations	Oct 30, 2022	Contrastive LearningSelf-Supervised Learning	CodeCode Available	1	5
Improving Self-Supervised Learning by Characterizing Idealized Representations	Sep 13, 2022	Contrastive LearningSelf-Supervised Learning	CodeCode Available	1	5
CLAMP-ViT: Contrastive Data-Free Learning for Adaptive Post-Training Quantization of ViTs	Jul 7, 2024	Contrastive Learningobject-detection	CodeCode Available	1	5
Semi-supervised Crowd Counting via Density Agency	Sep 7, 2022	Contrastive LearningCrowd Counting	CodeCode Available	1	5
Leveraging Hidden Positives for Unsupervised Semantic Segmentation	Mar 27, 2023	Contrastive LearningSemantic Segmentation	CodeCode Available	1	5

Show:10 25 50

← PrevPage 67 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