Show/Hide Menu
Hide/Show Apps
anonymousUser
Logout
Türkçe
Türkçe
Search
Search
Login
Login
OpenMETU
OpenMETU
About
About
Açık Bilim Politikası
Açık Bilim Politikası
Frequently Asked Questions
Frequently Asked Questions
Browse
Browse
By Issue Date
By Issue Date
Authors
Authors
Titles
Titles
Subjects
Subjects
Communities & Collections
Communities & Collections
Contextual Object Detection Using Set-Based Classification
Download
index.pdf
Date
2012-01-01
Author
Cinbiş, Ramazan Gökberk
Sclaroff, Stan
Metadata
Show full item record
This work is licensed under a
Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License
.
Item Usage Stats
0
views
2
downloads
We propose a new model for object detection that is based on set representations of the contextual elements. In this formulation, relative spatial locations and relative scores between pairs of detections are considered as sets of unordered items. Directly training classification models on sets of unordered items, where each set can have varying cardinality can be difficult. In order to overcome this problem, we propose SetBoost, a discriminative learning algorithm for building set classifiers. The SetBoost classifiers are trained to rescore detected objects based on object-object and object-scene context. Our method is able to discover composite relationships, as well as intra-class and inter-class spatial relationships between objects. The experimental evidence shows that our set-based formulation performs comparable to or better than existing contextual methods on the SUN and the VOC 2007 benchmark datasets.
Subject Keywords
Average precision
,
Object class
,
Context model
,
Reference object
,
Contextual relationship
URI
https://hdl.handle.net/11511/56664
DOI
https://doi.org/10.1007/978-3-642-33783-3_4
Collections
Department of Computer Engineering, Conference / Seminar