TensorFlow and PyTorch implementation of "Meta-Transfer Learning for Few-Shot Learning" (CVPR2019)
-
Updated
Dec 31, 2022 - Python
TensorFlow and PyTorch implementation of "Meta-Transfer Learning for Few-Shot Learning" (CVPR2019)
Tools for generating mini-ImageNet dataset and processing batches
Leaderboards for few-shot image classification on miniImageNet, tieredImageNet, FC100, and CIFAR-FS.
PyTorch implementation of “Negative Margin Matters: Understanding Margin in Few-shot Classification”
Source codes for "Improved Few-Shot Visual Classification" (CVPR 2020), "Enhancing Few-Shot Image Classification with Unlabelled Examples" (WACV 2022), and "Beyond Simple Meta-Learning: Multi-Purpose Models for Multi-Domain, Active and Continual Few-Shot Learning" (SSRN Electronic Journal)
Code of Empirical Bayes Transductive Meta-Learning with Synthetic Gradients
Source codes for "Improved Few-Shot Visual Classification" (CVPR 2020), "Enhancing Few-Shot Image Classification with Unlabelled Examples" (WACV 2022), and "Beyond Simple Meta-Learning: Multi-Purpose Models for Multi-Domain, Active and Continual Few-Shot Learning" (Neural Networks 2022 - in submission)
Pytorch implementation of Feature Generation for Long-Tail Classification by Rahul Vigneswaran, Marc T Law, Vineeth N Balasubramaniam and Makarand Tapaswi
mini-imagenet and tiny-imagent dataset transformation for traditional classification task and also for the format for few-shot learning / meta-learning tasks
Official implementation of POODLE: Improving Few-shot Learning via Penalizing Out-of-Distribution Samples (NeurIPS 2021)
Prototypical Networks for the task of few-shot image classification on Omniglot and mini-ImageNet.
Non-Euclidean implementations for few-shot image classification on the mini-ImageNet dataset
Self-supervised backbone pretraining on Mini-Imagenet
Add a description, image, and links to the mini-imagenet topic page so that developers can more easily learn about it.
To associate your repository with the mini-imagenet topic, visit your repo's landing page and select "manage topics."