CV papers since 2018

Log	Year	Title	Notes
x	2018	Unsupervised Feature Learning via Non-Parametric Instance Discrimination	Apparent similarity is learned not from the semantic annoataions, but from the visual data themselves. Instance-wise supervision.
	2019	EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
	2020	MoCo: Momentum Contrast for Unsupervised Visual Representation Learning	Dictionary Look-up,
x	2020	ViT: An Image Is Worth 16X16 Words Transformers For Image Recognition At Scale	Transformer on CV field
	2021	Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
	2021	CLIP: Learning Transferable Visual Models From Natural Language Supervision	OpenAI
x	2021	MAE: Masked Autoencoders Are Scalable Vision Learners	BERT on CV
	2021	DINO: Emerging Properties in Self-Supervised Vision Transformers
	2022	DALL-E 2: Hierarchical Text-Conditional Image Generation with CLIP Latents	OpenAI
	2023	SAM: Segment Anything

Constrastive Learning Collections

Year	Title	Notes
2018	Unsupervised Feature Learning via Non-Parametric Instance Discrimination	InstDisc, Memory bank
2018	Unsupervised Embedding Learning via Invariant and Spreading Instance Feature	InvaSpread,
2018	Representation Learning with Constrastive Predictive Coding	CPC,
2019	Constrastive Multiview Coding
2020	Moco: Momentum Contrast for Unsupervised Visual Representation Learning
2020	SimCLR: A Simple Farmework for Constrastive Learning of Visual Representations
2020	MoCov2: Improved Baselines with Momentum Constrastive Learning
2020	SimCLRv2: Big Self-supervised Models are Strong Semi-Supervised Learners
2021	SwAV: Unsupervised Learning of Visual Features by Constrasting Cluster Assignments
2020	BYOL: Bootstrap Your Own Latent A New Approach to Self-Supervised Learning	No negative samples, Understanding self-supervised and constrastive learning with “Bootstrap Your Own Latent(BYOL)”, and BYOL works even without batch statistics
2020	SimSiam: Exploring Simple Siamese Representation Learning
2021	MoCov3: An Empirical Study of Traning Self-Supervised Vision Transformers
2021	DINO: Emerging Properties in Self-Supervised Vision Transformers