Conditioned Cooperative training for semi-supervised weapon detection
Copyright © 2023 Elsevier Ltd. All rights reserved..
Violent assaults and homicides occur daily, and the number of victims of mass shootings increases every year. However, this number can be reduced with the help of Closed Circuit Television (CCTV) and weapon detection models, as generic object detectors have become increasingly accurate with more data for training. We present a new semi-supervised learning methodology based on conditioned cooperative student-teacher training with optimal pseudo-label generation using a novel confidence threshold search method and improving both models by conditional knowledge transfer. Furthermore, a novel firearms image dataset of 458,599 images was collected using Instagram hashtags to evaluate our approach and compare the improvements obtained using a specific unsupervised dataset instead of a general one such as ImageNet. We compared our methodology with supervised, semi-supervised and self-supervised learning techniques, outperforming approaches such as YOLOv5 m (up to +19.86), YOLOv5l (up to +6.52) Unbiased Teacher (up to +10.5 AP), DETReg (up to +2.8 AP) and UP-DETR (up to +1.22 AP).
Medienart: |
E-Artikel |
---|
Erscheinungsjahr: |
2023 |
---|---|
Erschienen: |
2023 |
Enthalten in: |
Zur Gesamtaufnahme - volume:167 |
---|---|
Enthalten in: |
Neural networks : the official journal of the International Neural Network Society - 167(2023) vom: 15. Okt., Seite 489-501 |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Salazar González, Jose L [VerfasserIn] |
---|
Links: |
---|
Themen: |
Journal Article |
---|
Anmerkungen: |
Date Completed 23.10.2023 Date Revised 23.10.2023 published: Print-Electronic Citation Status MEDLINE |
---|
doi: |
10.1016/j.neunet.2023.08.043 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM361876947 |
---|
LEADER | 01000naa a22002652 4500 | ||
---|---|---|---|
001 | NLM361876947 | ||
003 | DE-627 | ||
005 | 20231226090057.0 | ||
007 | cr uuu---uuuuu | ||
008 | 231226s2023 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1016/j.neunet.2023.08.043 |2 doi | |
028 | 5 | 2 | |a pubmed24n1206.xml |
035 | |a (DE-627)NLM361876947 | ||
035 | |a (NLM)37690211 | ||
035 | |a (PII)S0893-6080(23)00462-8 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Salazar González, Jose L |e verfasserin |4 aut | |
245 | 1 | 0 | |a Conditioned Cooperative training for semi-supervised weapon detection |
264 | 1 | |c 2023 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a ƒaComputermedien |b c |2 rdamedia | ||
338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
500 | |a Date Completed 23.10.2023 | ||
500 | |a Date Revised 23.10.2023 | ||
500 | |a published: Print-Electronic | ||
500 | |a Citation Status MEDLINE | ||
520 | |a Copyright © 2023 Elsevier Ltd. All rights reserved. | ||
520 | |a Violent assaults and homicides occur daily, and the number of victims of mass shootings increases every year. However, this number can be reduced with the help of Closed Circuit Television (CCTV) and weapon detection models, as generic object detectors have become increasingly accurate with more data for training. We present a new semi-supervised learning methodology based on conditioned cooperative student-teacher training with optimal pseudo-label generation using a novel confidence threshold search method and improving both models by conditional knowledge transfer. Furthermore, a novel firearms image dataset of 458,599 images was collected using Instagram hashtags to evaluate our approach and compare the improvements obtained using a specific unsupervised dataset instead of a general one such as ImageNet. We compared our methodology with supervised, semi-supervised and self-supervised learning techniques, outperforming approaches such as YOLOv5 m (up to +19.86), YOLOv5l (up to +6.52) Unbiased Teacher (up to +10.5 AP), DETReg (up to +2.8 AP) and UP-DETR (up to +1.22 AP) | ||
650 | 4 | |a Journal Article | |
650 | 4 | |a Knowledge transfer | |
650 | 4 | |a Self-supervised learning | |
650 | 4 | |a Semi-supervised learning | |
650 | 4 | |a Supervised learning | |
650 | 4 | |a Weapon detection | |
700 | 1 | |a Álvarez-García, Juan A |e verfasserin |4 aut | |
700 | 1 | |a Rendón-Segador, Fernando J |e verfasserin |4 aut | |
700 | 1 | |a Carrara, Fabio |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t Neural networks : the official journal of the International Neural Network Society |d 1996 |g 167(2023) vom: 15. Okt., Seite 489-501 |w (DE-627)NLM087746824 |x 1879-2782 |7 nnns |
773 | 1 | 8 | |g volume:167 |g year:2023 |g day:15 |g month:10 |g pages:489-501 |
856 | 4 | 0 | |u http://dx.doi.org/10.1016/j.neunet.2023.08.043 |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d 167 |j 2023 |b 15 |c 10 |h 489-501 |