​We just released our #NeurIPS2019 Multimodal Model-Agnostic Meta-Learning (MMAML) code for learning few-shot image classification, which extends MAML to multimodal task distributions (e.g. learning from multiple datasets). The code contains #PyTorch implementations of our model and two baselines (MAML and Multi-MAML) as well as the scripts to evaluate these models to five popular few-shot learning datasets: Omniglot, Mini-ImageNet, FC100 (CIFAR100), CUB-200-2011, and FGVC-Aircraft.

Code: https://github.com/shaohua0116/MMAML-Classification

Paper: https://arxiv.org/abs/1910.13616

#NeurIPS #MachineLearning #ML #code

🔗 shaohua0116/MMAML-Classification
An official PyTorch implementation of “Multimodal Model-Agnostic Meta-Learning via Task-Aware Modulation” (NeurIPS 2019) by Risto Vuorio*, Shao-Hua Sun*, Hexiang Hu, and Joseph J. Lim - shaohua0116...

​#NeurIPS2019_2019-12-09_19-49-34.xlsx

View an interactive version of this graph (experimental)

https://nodexlgraphgallery.org/Pages/Graph.aspx?graphID=218538

🔗 #NeurIPS2019_2019-12-09_19-49-34.xlsx
The graph represents a network of 4,349 Twitter users whose recent tweets contained "#NeurIPS2019", or who were replied to or mentioned in those tweets, taken from a data set limited to a maximum of 18,000 tweets. The network was obtained from Twitter on Tuesday, 10 December 2019 at 04:17 UTC. The tweets in the network were tweeted over the 9-day, 3-hour, 2-minute period from Sunday, 01 December 2019 at 00:42 UTC to Tuesday, 10 December 2019 at 03:45 UTC. Additional tweets that were mentioned in this data set were also collected from prior time periods. These tweets may expand the complete time period of the data. There is an edge for each "replies-to" relationship in a tweet, an edge for each "mentions" relationship in a tweet, and a self-loop edge for each tweet that is not a "replies-to" or "mentions". The graph is directed. The graph's vertices were grouped by cluster using the Clauset-Newman-Moore cluster algorithm. The graph was laid out using the Ha

​David Abel on Twitter

🔗 David Abel on Twitter
Just wrapped ! Notes here:

​Neural Ordinary Differential Equations for Semantic Segmentation of Individual Colon Glands
Hans Pinckaers, Geert Litjens : https://arxiv.org/abs/1910.10470
GitHub : https://github.com/DIAGNijmegen/neural-odes-segmentation
#MedNeurIPS #NeurIPS #NeurIPS2019

🔗 Neural Ordinary Differential Equations for Semantic Segmentation of Individual Colon Glands
Automated medical image segmentation plays a key role in quantitative research and diagnostics. Convolutional neural networks based on the U-Net architecture are the state-of-the-art. A key disadvantage is the hard-coding of the receptive field size, which requires architecture optimization for each segmentation task. Furthermore, increasing the receptive field results in an increasing number of weights. Recently, Neural Ordinary Differential Equations (NODE) have been proposed, a new type of continuous depth deep neural network. This framework allows for a dynamic receptive field at a fixed memory cost and a smaller amount of parameters. We show on a colon gland segmentation dataset (GlaS) that these NODEs can be used within the U-Net framework to improve segmentation results while reducing memory load and parameter counts.