Comparer des méthodes

	Apprentissage visuel contrastif	Réseau d'attention sur graphe
Domaine	Apprentissage profond	Apprentissage profond
Famille	Machine learning	Machine learning
Année d'origine	2020	2018
Auteur d'origine	Chen, T. et al. (SimCLR); He, K. et al. (MoCo)	Veličković, P. et al.
Type	Self-supervised deep representation learning	Graph neural network (attention-based)
Source fondatrice	Chen, T., Kornblith, S., Norouzi, M. & Hinton, G. (2020). A Simple Framework for Contrastive Learning of Visual Representations. ICML.	Veličković, P. et al. (2018). Graph Attention Networks. ICLR.
Alias	Karşıtlık Öğrenmesi — Görsel (SimCLR / MoCo / BYOL), contrastive learning, self-supervised visual representation learning, SimCLR	Graf Dikkat Ağı (GAT), GAT, graph attention network, attention-based graph neural network
Apparentées	5	4
Résumé	Visual contrastive learning is a self-supervised deep-learning approach — popularised by frameworks such as SimCLR (Chen et al., 2020) and MoCo (He et al., 2020) — that learns rich image representations without labels by pulling different augmentations of the same image together and pushing different images apart. It turns a large pool of unlabelled images into a useful feature extractor.	The Graph Attention Network (GAT), introduced by Veličković and colleagues in 2018, is a graph neural network variant that learns how much importance to assign to each neighbouring node through a self-attention mechanism. On heterogeneous neighbourhoods and relational classification it produces results superior to graph convolutional networks (GCN).