Question on the Amount of Labeled Data Used to Train the ResNet Feature Extractor

Yikai-Wang / ICI-FSL

This repository contains the code for Instance Credibility Inference (ICI).

82 stars 22 forks source link

Question on the Amount of Labeled Data Used to Train the ResNet Feature Extractor #6

Closed cpphoo closed 4 years ago

cpphoo commented 4 years ago

Hi, thanks for your excellent work!

After reading your paper, I was wondering whether the ResNet backbone was trained on the labelled portion of the base dataset (i.e. 10% of examples in each base class for tieredImageNet or 40% of examples in each base class in MiniImageNet as reported in Ren et. al.) or 100% of the images from each base class in the dataset.

Yikai-Wang commented 4 years ago

We use 90% of examples in each base class in all experiments for training set, and the residual 10% are for validation set. Details can be found in https://github.com/Yikai-Wang/ICI-FSL/blob/f2537b7742159adfa68cc8646b9a20c570320443/datasets.py#L151-L161

cpphoo commented 4 years ago

Got it! Thanks for your prompt reply!