Show/Hide Menu
Hide/Show Apps
anonymousUser
Logout
Türkçe
Türkçe
Search
Search
Login
Login
OpenMETU
OpenMETU
About
About
Open Science Policy
Open Science Policy
Frequently Asked Questions
Frequently Asked Questions
Browse
Browse
By Issue Date
By Issue Date
Authors
Authors
Titles
Titles
Subjects
Subjects
Communities & Collections
Communities & Collections
Object localization with reinforcement learning Pekiştirmeli öǧrenme ile nesne yeri saptama
Date
2018-07-05
Author
Halici, Eren
Alatan, Abdullah Aydın
Metadata
Show full item record
This work is licensed under a
Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License
.
Item Usage Stats
9
views
0
downloads
Reinforcement Learning, which has recently started to be used more and more in computer vision applications, is mostly utilized in solving object tracking and object localization problems. Most of the time, training these problems makes use of bounding box information; however, producing bounding box information requires meticulous human effort. In this work, a framework for solving the object localization problem without using bounding boxes is proposed. Instead of bounding boxes; a database of tightly cropped images and a database of uncropped scenes is required. The framework consists of two parts: A reinforcement learning agent that tries to produce tightly cropped images from uncropped scenes and a discriminator which aims to determine whether an image is generated by the reinforcement learning agent or it belongs to the distribution of the tightly cropped image database. The experiment results indicate that achieving a promising localization performance is possible without using explicit bounding box information.
Subject Keywords
Object localization
,
Reinforcement learning
,
Generative adversarial networks
URI
https://hdl.handle.net/11511/41144
DOI
https://doi.org/10.1109/siu.2018.8404567
Collections
Department of Electrical and Electronics Engineering, Conference / Seminar