國立虎尾科技大學 |

Predicting YOLO Misdetection Using Feature Map Activations.

Record Type:	Language materials, manuscript : Monograph/item
Title/Author:	Predicting YOLO Misdetection Using Feature Map Activations./
Author:	Ferdous, Md. Rezoan.
Description:	1 online resource (59 pages)
Notes:	Source: Masters Abstracts International, Volume: 85-12.
Contained By:	Masters Abstracts International85-12.
Subject:	Computer engineering. -
Online resource:	click for full text (PQDT)
ISBN:	9798383058480

Predicting YOLO Misdetection Using Feature Map Activations.
Ferdous, Md. Rezoan.

Predicting YOLO Misdetection Using Feature Map Activations. - 1 online resource (59 pages)

Source: Masters Abstracts International, Volume: 85-12.

Thesis (M.S.)--Southern Illinois University at Carbondale, 2024.

Includes bibliographical references

This research proposes a novel method to identify the YOLO object detection network failures. The proposed method employs a secondary neural network to predict misdetections (localization and classification error) based on the features extracted from the YOLO network. Moreover, to make the secondary network lightweight by selecting important features for a target class, a recursive feature elimination-based method is proposed. As a result, the computational cost is reduced without compromising the accuracy. Four of the most frequently occurring classes in the COCO dataset were taken into consideration when training the secondary network for the experimental evaluation. When a single class was taken into consideration, the proposed failure detection approach attained an accuracy of 89.79%; this is a 16% improvement in accuracy over the existing method. A 52% reduction in inference time and an accuracy of 88.90% were obtained with the feature selection approach. Additionally, the proposed failure detection framework was assessed by taking into account several classes at once, and excellent accuracy was noted.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2024

Mode of access: World Wide Web

ISBN: 9798383058480Subjects--Topical Terms:

569006
Computer engineering.
Subjects--Index Terms:

Detection network failuresIndex Terms--Genre/Form:

554714
Electronic books.

Predicting YOLO Misdetection Using Feature Map Activations.
LDR:02428ntm a22003737 4500 001 1150172
005 20241022111606.5
006 m o d
007 cr bn ---uuuuu
008 250605s2024 xx obm 000 0 eng d
020 $a 9798383058480
035 $a (MiAaPQ)AAI31145992
035 $a AAI31145992
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Ferdous, Md. Rezoan. $3 1476607
245 1 0 $a Predicting YOLO Misdetection Using Feature Map Activations.
264 0 $c 2024
300 $a 1 online resource (59 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: Masters Abstracts International, Volume: 85-12.
500 $a Advisor: Tragoudas, Spyros.
502 $a Thesis (M.S.)--Southern Illinois University at Carbondale, 2024.
504 $a Includes bibliographical references
520 $a This research proposes a novel method to identify the YOLO object detection network failures. The proposed method employs a secondary neural network to predict misdetections (localization and classification error) based on the features extracted from the YOLO network. Moreover, to make the secondary network lightweight by selecting important features for a target class, a recursive feature elimination-based method is proposed. As a result, the computational cost is reduced without compromising the accuracy. Four of the most frequently occurring classes in the COCO dataset were taken into consideration when training the secondary network for the experimental evaluation. When a single class was taken into consideration, the proposed failure detection approach attained an accuracy of 89.79%; this is a 16% improvement in accuracy over the existing method. A 52% reduction in inference time and an accuracy of 88.90% were obtained with the feature selection approach. Additionally, the proposed failure detection framework was assessed by taking into account several classes at once, and excellent accuracy was noted.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Computer engineering. $3 569006
653 $a Detection network failures
653 $a Map activations
653 $a Neural networks
653 $a Misdetections
655 7 $a Electronic books. $2 local $3 554714
690 $a 0464
690 $a 0800
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a Southern Illinois University at Carbondale. $b Electrical and Computer Engineering. $3 1192686
773 0 $t Masters Abstracts International $g 85-12.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31145992 $z click for full text (PQDT)