Abstract | ||
---|---|---|
This paper presents a method to quantitatively evaluate information contributions of individual bottom-up and top-down computing processes in object recognition. Our objective is to start a discovery on how to schedule bottom-up and top-down processes. (1) We identify two bottom-up processes and one top-down process in hierarchical models, termed α, β and γ channels respectively ; (2) We formulate the three channels under an unified Bayesian framework; (3) We use a blocking control strategy to isolate the three channels to separately train them and individually measure their information contributions in typical recognition tasks; (4) Based on the evaluated results, we integrate the three channels to detect objects with performance improvements obtained. Our experiments are performed in both low-middle level tasks, such as detecting edges/bars and junctions, and high level tasks, such as detecting human faces and cars, together with a group of human study designed to compare computer and human perception. |
Year | DOI | Venue |
---|---|---|
2009 | 10.1109/ICCV.2009.5459386 | ICCV |
Keywords | DocType | Volume |
blocking control strategy,low-middle level tasks,top-down processes,α channel,information contribution evaluation,γ channel,hierarchical models,bottom-up processes,object detection,object recognition,β channel,top down processing,pediatrics,top down,study design,bottom up,feature extraction,testing,human perception | Conference | 2009 |
Issue | ISSN | ISBN |
1 | 1550-5499 E-ISBN : 978-1-4244-4419-9 | 978-1-4244-4419-9 |
Citations | PageRank | References |
1 | 0.35 | 12 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Xiong Yang | 1 | 15 | 1.54 |
Tianfu Wu | 2 | 331 | 26.72 |
Song-Chun Zhu | 3 | 6580 | 741.75 |