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 1211–1220 of 6661 papers

Title	Date	Tasks	Status	Hype
VLCap: Vision-Language with Contrastive Learning for Coherent Video Paragraph Captioning	Jun 26, 2022	Contrastive LearningDiversity	CodeCode Available	1
Vision Transformer for Contrastive Clustering	Jun 26, 2022	ClusteringContrastive Learning	CodeCode Available	1
SLIC: Self-Supervised Learning with Iterative Clustering for Human Action Videos	Jun 25, 2022	Action ClassificationClustering	CodeCode Available	1
Language Models as Knowledge Embeddings	Jun 25, 2022	Contrastive LearningLink Prediction	CodeCode Available	1
Utilizing Expert Features for Contrastive Learning of Time-Series Representations	Jun 23, 2022	Contrastive LearningRepresentation Learning	CodeCode Available	1
Towards Galaxy Foundation Models with Hybrid Contrastive Learning	Jun 23, 2022	Contrastive Learning	CodeCode Available	1
CLAMP: Prompt-based Contrastive Learning for Connecting Language and Animal Pose	Jun 23, 2022	Animal Pose EstimationContrastive Learning	CodeCode Available	1
Panoramic Panoptic Segmentation: Insights Into Surrounding Parsing for Mobile Agents via Unsupervised Contrastive Learning	Jun 21, 2022	Contrastive LearningDomain Generalization	CodeCode Available	1
Robust Task Representations for Offline Meta-Reinforcement Learning via Contrastive Learning	Jun 21, 2022	Contrastive LearningMeta Reinforcement Learning	CodeCode Available	1
Conditioned and Composed Image Retrieval Combining and Partially Fine-Tuning CLIP-Based Features	Jun 19, 2022	Composed Image Retrieval (CoIR)Content-Based Image Retrieval	CodeCode Available	1

Show:10 25 50

← PrevPage 122 of 667Next →

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