Contrastive Learning and Pre-trained model Papers&Codes

A list of Contrastive Learning and Pre-trained model Papers&Codes

Contrastive Learning

Title	Conference	Codes
SimCSE: Simple Contrastive Learning of Sentence Embeddings	EMNLP 2021	[Torch]
Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere	ICML 2020	[Torch]
SimCLS: A Simple Framework for Contrastive Learning of Abstractive Summarization	ACL 2021	github
ConSERT: A Contrastive Framework for Self-Supervised Sentence Representation Transfer	ACL 2021	github
Contrastive Learning for Many-to-many Multilingual Neural Machine Translation	ACL 2021	github
Distributed Representations of Words and Phrases and their Compositionality
An efficient framework for learning sentence representations	ICLR 2018

Title	Conference	Codes
MoCo - Momentum Contrast for Unsupervised Visual Representation Learning	CVPR20	Torch(official)
MoCo v2 - Improved Baselines with Momentum Contrastive Learning		Torch(official)
SimCLR - A Simple Framework for Contrastive Learning of Visual Representations	ICML20	TF(official), Torch
SimCLR v2 - Big Self-Supervised Models are Strong Semi-Supervised Learners	NIPS20	TF(official)
BYOL - Bootstrap your own latent: A new approach to self-supervised Learning		JAX(official), Torch
SwAV - Unsupervised Learning of Visual Features by Contrasting Cluster Assignments	NIPS20	Torch(official), Torch
SimSiam - Exploring Simple Siamese Representation Learning		Torch
Prototypical Contrastive Learning of Unsupervised Representations	ICLR2021	github

Title	Conference	Codes
[HCL] - Contrastive Learning With Hard Negative Samples	ICLR 2021	Link
A theoretical analysis of contrastive unsupervised representation learning	ICML 2019
Contrastive Conditional Transport for Representation Learning
Mining Better Samples for Contrastive Learning of Temporal Correspondence	CVPR 2020
Scaling Deep Contrastive Learning Batch Size
What Makes for Good Views for Contrastive Learning?
Contrastive Multiview Coding
Representation Learning with Contrastive Predictive Coding

Title	Conference	Codes	Note
Cross-Attention is All You Need: Adapting Pretrained Transformers for Machine Translation