Disjoint Datasets in Multi-task Learning with Deep Neural Networks for Autonomous Driving

Introduction

My goal

Dataset and the model

Concept of CityScapes
Multi-task model with shared weights

Knowledge distillation

Two different training iteration in the “knowledge distillation” model

Results

Results of methods (X is Semseg and Y is Depth metrics)

--

--

--

Deep Learning and AI solutions from Budapest University of Technology and Economics. http://smartlab.tmit.bme.hu/

Love podcasts or audiobooks? Learn on the go with our new app.

Recommended from Medium

Install TensorFlow 2.0 GPU (CUDA), Keras, & Python 3.7 in Windows 10

Improve Image Recognition Models using Transfer Learning

Stage 2: Unravelling the Neural Structured Learning Paradigm

Algorithms to Detect Anomalies in Images

Transfer learning with keras

How to Create and Train a Multi-Task Transformer Model

Stop duplicating deep learning training datasets with Amazon EBS multi-attach

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store
SmartLab AI

SmartLab AI

Deep Learning and AI solutions from Budapest University of Technology and Economics. http://smartlab.tmit.bme.hu/

More from Medium

GFPGAN — Towards Real-World Blind Face Restoration with Generative Facial Prior

GANs [Generative Adversarial Networks]

Data augmentation using ACGAN

Universal Ai Diploma Week 5 Generative Adversarial Neural Network Instructions