Diversity Helps: Unsupervised Few-shot Learning via Distribution Shift-based Data Augmentation

13 April 2020

Papers citing "Diversity Helps: Unsupervised Few-shot Learning via Distribution Shift-based Data Augmentation"

5 / 5 papers shown

Title
Rethinking Clustering-Based Pseudo-Labeling for Unsupervised Meta-Learning Xingping Dong Jianbing Shen Ling Shao 32 7 0 27 Sep 2022
Trainable Class Prototypes for Few-Shot Learning Jianyi Li Guizhong Liu VLM 22 2 0 21 Jun 2021
Contrastive Prototype Learning with Augmented Embeddings for Few-Shot Learning Yizhao Gao Nanyi Fei Guangzhen Liu Zhiwu Lu Tao Xiang Songfang Huang 61 35 0 23 Jan 2021
Self-Supervised Prototypical Transfer Learning for Few-Shot Classification Carlos Medina A. Devos Matthias Grossglauser SSL 26 50 0 19 Jun 2020
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks Chelsea Finn Pieter Abbeel Sergey Levine OOD 422 11,715 0 09 Mar 2017