國立虎尾科技大學 |

Towards The Deep Model : = Understanding Visual Recognition Through Computational Models.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Towards The Deep Model :/
其他題名:	Understanding Visual Recognition Through Computational Models.
作者:	Wang, Panqu.
面頁冊數:	1 online resource (186 pages)
附註:	Source: Dissertation Abstracts International, Volume: 78-08(E), Section: B.
標題:	Computer science. -
電子資源:	click for full text (PQDT)
ISBN:	9781369682212

Towards The Deep Model : = Understanding Visual Recognition Through Computational Models.
Wang, Panqu.

Towards The Deep Model :Understanding Visual Recognition Through Computational Models. - 1 online resource (186 pages)

Source: Dissertation Abstracts International, Volume: 78-08(E), Section: B.

Thesis (Ph.D.)--University of California, San Diego, 2017.

Includes bibliographical references

Understanding how visual recognition is achieved in the human brain is one of the most fundamental questions in vision research. In this thesis I seek to tackle this problem from a neurocomputational modeling perspective. More specifically, I build machine learning-based models to simulate and explain cognitive phenomena related to human visual recognition, and I improve computational models using brain-inspired principles to excel at computer vision tasks. I first describe how a neurocomputational model ("The Model", TM, (Cottrell & Hsiao, 2011)) can be applied to explain the modulation of visual experience on the performance of subordinate-level face and object recognition. Next, by introducing a mixture-of-experts structure in the model, I show that TM can be used to simulate the development of hemispheric lateralization of face processing. In addition, I extend TM to "The Deep Model" (TDM) by coupling it with deep learning techniques, and use TDM to explain the peripheral vision advantage in human scene recognition. Furthermore, I show the performance of these computational methods can be improved by introducing realistic constraints based on the human brain. By combining unsupervised feature learning principles with the Gnostic Fields theory of how the brain performs object recognition across the ventral visual pathway, I show a biologically-inspired model can develop realistic features of the early visual cortex, while performing well on object recognition datasets. By designing better encoding and decoding strategies in the deep neural network, I demonstrate that our system achieves the state-of-the-art performance on pixel-level semantic segmentation task on many popular computer vision benchmarks.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2018

Mode of access: World Wide Web

ISBN: 9781369682212Subjects--Topical Terms:

573171
Computer science.
Index Terms--Genre/Form:

554714
Electronic books.

Towards The Deep Model : = Understanding Visual Recognition Through Computational Models.
LDR:02960ntm a2200337K 4500 001 913672
005 20180622095235.5
006 m o u
007 cr mn||||a|a||
008 190606s2017 xx obm 000 0 eng d
020 $a 9781369682212
035 $a (MiAaPQ)AAI10258188
035 $a (MiAaPQ)ucsd:16277
035 $a AAI10258188
040 $a MiAaPQ $b eng $c MiAaPQ
100 1 $a Wang, Panqu. $3 1186603
245 1 0 $a Towards The Deep Model : $b Understanding Visual Recognition Through Computational Models.
264 0 $c 2017
300 $a 1 online resource (186 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertation Abstracts International, Volume: 78-08(E), Section: B.
500 $a Advisers: Garrison Cottrell; Nuno Vasconcelos.
502 $a Thesis (Ph.D.)--University of California, San Diego, 2017.
504 $a Includes bibliographical references
520 $a Understanding how visual recognition is achieved in the human brain is one of the most fundamental questions in vision research. In this thesis I seek to tackle this problem from a neurocomputational modeling perspective. More specifically, I build machine learning-based models to simulate and explain cognitive phenomena related to human visual recognition, and I improve computational models using brain-inspired principles to excel at computer vision tasks. I first describe how a neurocomputational model ("The Model", TM, (Cottrell & Hsiao, 2011)) can be applied to explain the modulation of visual experience on the performance of subordinate-level face and object recognition. Next, by introducing a mixture-of-experts structure in the model, I show that TM can be used to simulate the development of hemispheric lateralization of face processing. In addition, I extend TM to "The Deep Model" (TDM) by coupling it with deep learning techniques, and use TDM to explain the peripheral vision advantage in human scene recognition. Furthermore, I show the performance of these computational methods can be improved by introducing realistic constraints based on the human brain. By combining unsupervised feature learning principles with the Gnostic Fields theory of how the brain performs object recognition across the ventral visual pathway, I show a biologically-inspired model can develop realistic features of the early visual cortex, while performing well on object recognition datasets. By designing better encoding and decoding strategies in the deep neural network, I demonstrate that our system achieves the state-of-the-art performance on pixel-level semantic segmentation task on many popular computer vision benchmarks.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2018
538 $a Mode of access: World Wide Web
650 4 $a Computer science. $3 573171
650 4 $a Cognitive psychology. $3 556029
650 4 $a Electrical engineering. $3 596380
655 7 $a Electronic books. $2 local $3 554714
690 $a 0984
690 $a 0633
690 $a 0544
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a University of California, San Diego. $b Electrical Engineering (Signal and Image Proc). $3 1186555
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10258188 $z click for full text (PQDT)