Learning with Proxy Supervision for End-To-End Visual Learning

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F17%3A00315382" target="_blank" >RIV/68407700:21230/17:00315382 - isvavai.cz</a>

Result on the web

<a href="https://www.semanticscholar.org/paper/Learning-with-proxy-supervision-for-end-to-end-vis-Cermak-Angelova/0a572c16e635312f118d1a53f0ff6446402d3c32" target="_blank" >https://www.semanticscholar.org/paper/Learning-with-proxy-supervision-for-end-to-end-vis-Cermak-Angelova/0a572c16e635312f118d1a53f0ff6446402d3c32</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/IVS.2017.7995690" target="_blank" >10.1109/IVS.2017.7995690</a>

Result language

angličtina

Original language name

Learning with Proxy Supervision for End-To-End Visual Learning

Original language description

Learning with deep neural networks forms the state-of-The-Art in many tasks such as image classification, image detection, speech recognition, text analysis. We here set out to gain understanding in learning in an 'end-To-end' manner for an autonomous vehicle, which refers to directly learning the decision which will result from the perception of the scene. For example, we consider learning a binary 'stop'/'go' decision, with respect to pedestrians, given the input image. In this work we propose to use additional information, referred to as 'proxy supervision', for improved learning and study its effects on the overall performance. We show that the proxy labels significantly improve the robustness of learning, while achieving as good, or better, accuracy than in the original task of binary classification.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

—

Continuities

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Publication year

2017

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

Proceedings of IEEE Intelligent Vehicles Symposium

ISBN

978-1-5090-4804-5

ISSN

1931-0587

e-ISSN

—

Number of pages

6

Pages from-to

1-6

Publisher name

IEEE (Institute of Electrical and Electronics Engineers)

Place of publication

—

Event location

Redondo Beach

Event date

Jun 11, 2017

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

000425212700001