Search: onr:"swepub:oai:DiVA.org:hh-51299" >
SqueezerFaceNet :
SqueezerFaceNet : Reducing a Small Face Recognition CNN Even More Via Filter Pruning
-
- Alonso-Fernandez, Fernando, 1978- (author)
- Högskolan i Halmstad,Centrum för forskning om tillämpade intelligenta system (CAISR)
-
- Hernandez-Diaz, Kevin, 1992- (author)
- Högskolan i Halmstad,Centrum för forskning om tillämpade intelligenta system (CAISR)
-
- Buades Rubio, Jose Maria (author)
- Computer Graphics and Vision and AI Group, University of Balearic Islands, Palma, Spain
-
show more...
-
- Bigun, Josef, 1961- (author)
- Högskolan i Halmstad,Centrum för forskning om tillämpade intelligenta system (CAISR)
-
show less...
-
(creator_code:org_t)
- Cham : Springer, 2024
- 2024
- English.
-
In: Progress in Artificial Intelligence and Pattern Recognition. IWAIPR 2023.. - Cham : Springer. - 9783031495519 - 9783031495526 ; , s. 349-361
- Related links:
-
https://hh.diva-port... (primary) (Raw object)
-
show more...
-
https://urn.kb.se/re...
-
https://doi.org/10.1...
-
show less...
Abstract
Subject headings
Close
- The widespread use of mobile devices for various digital services has created a need for reliable and real-time person authentication. In this context, facial recognition technologies have emerged as a dependable method for verifying users due to the prevalence of cameras in mobile devices and their integration into everyday applications. The rapid advancement of deep Convolutional Neural Networks (CNNs) has led to numerous face verification architectures. However, these models are often large and impractical for mobile applications, reaching sizes of hundreds of megabytes with millions of parameters. We address this issue by developing SqueezerFaceNet, a light face recognition network which less than 1M parameters. This is achieved by applying a network pruning method based on Taylor scores, where filters with small importance scores are removed iteratively. Starting from an already small network (of 1.24M) based on SqueezeNet, we show that it can be further reduced (up to 40%) without an appreciable loss in performance. To the best of our knowledge, we are the first to evaluate network pruning methods for the task of face recognition. © 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.
Subject headings
- TEKNIK OCH TEKNOLOGIER -- Elektroteknik och elektronik -- Signalbehandling (hsv//swe)
- ENGINEERING AND TECHNOLOGY -- Electrical Engineering, Electronic Engineering, Information Engineering -- Signal Processing (hsv//eng)
Keyword
- Face recognition
- Mobile Biometrics
- CNN pruning
- Taylor scores
Publication and Content Type
- ref (subject category)
- kon (subject category)
Find in a library
To the university's database