Description
PyData SF 2016 Anusua Trivedi | Transfer Learning and Finetuning Deep Convolution Neural Network on Different Domain Specific Images
We propose a method to apply a pre-trained deep convolution neural network (DCNN) on images to improve prediction accuracy. We use a pre-trained DCNN on two very different domain specific datasets, and apply fine-tuning to transfer the learned features to the prediction. Our approach improves prediction accuracy on both domain-specific datasets, compared to state-of-the-art approaches.
In this talk, we propose prediction techniques using deep learning on different types of images datasets – medical images and fashion images.
We show how to build a generic deep learning model, which could be used with:
- A fluorescein angiographic eye image to predict Diabetic Retinopathy
- A fashion image to predict the clothing type in that image
We propose a method to apply a pre-trained deep convolution neural network (DCNN) on images to improve prediction accuracy. We use an ImageNet pre-trained DCNN and apply fine-tuning to transfer the learned features to the prediction.
We use this fine-tuned model on two very different domain specific datasets. Our approach improves prediction accuracy on both domain-specific datasets, compared to state-of-the-art Machine Learning approaches.