Regularizing Binary Neural Networks via Ensembling for Efficient Person Re-identification

Basit Öğe Kaydı
dc.contributor.authorŞerbetçi, Ayşe
dc.contributor.authorAkgül, Yusuf Sinan
dc.date.accessioned2023-06-22T11:35:17Z
dc.date.available2023-06-22T11:35:17Z
dc.date.issued2023en_US
dc.departmentFakülteler, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümüen_US
dc.description.abstractThis study aims to leverage Binary Neural Networks (BNN) to learn binary hash codes for efficient person re-identification (ReID). BNNs, which use binary weights and activations, show promise in speeding up the inference time in deep models. However, BNNs typically suffer from performance degradation mainly due to the discontinuity of the binarization operation. Proxy functions have been proposed to calculate the gradients in the backward propagation, but they lead to the gradient mismatch problem. In this study, we propose to address the gradient mismatch problem by designing a multi-branch ensemble model consisting of many weak hash code learners. Specifically, our design aggregates the gradients from multiple branches, which allows a better approximation of the gradients and regularizes the network. Our model adds little computational cost to the baseline BNN since a vast amount of network parameters are shared between the weak learners. Combining the efficiency of the BNNs and hash code learning, we obtain an effective ensemble model which is efficient both in feature extraction and ranking phases. Our experiments demonstrate that the proposed model outperforms a single BNN by more than %20 using nearly the same amount of floating point operations. Moreover, the proposed model outperforms a conventional ensemble of BNN by more than %7 while being nearly 10x and 2x more efficient in terms of CPU consumption and memory footprint, respectively. We explore the performance of BNNs for efficient person ReID as one of the first systems available in the literature. Moreover, we adopt the proposed ensemble model for further validation of the image classification task and observe that our method effectively regularizes BNNs, providing robustness to hyperparameter selection and producing more consistent results under different settings.en_US
dc.identifier.doi10.1109/ACCESS.2023.3281737en_US
dc.identifier.scopus2-s2.0-85161080404en_US
dc.identifier.scopusqualityN/Aen_US
dc.identifier.urihttps://hdl.handle.net/11467/6663
dc.identifier.urihttps://doi.org/10.1109/ACCESS.2023.3281737
dc.identifier.wosWOS:001016809400001en_US
dc.identifier.wosqualityQ2en_US
dc.indekslendigikaynakWeb of Scienceen_US
dc.indekslendigikaynakScopusen_US
dc.language.isoenen_US
dc.publisherInstitute of Electrical and Electronics Engineers Inc.en_US
dc.relation.ispartofIEEE Accessen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.subjectBinary neural network; Codes; Computational modeling; Ensemble learning; Feature extraction; Hash retrieval; Network regularization; Neural networks; Person re-identification; Standards; Task analysis; Trainingen_US
dc.titleRegularizing Binary Neural Networks via Ensembling for Efficient Person Re-identificationen_US
dc.typeArticleen_US

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
Küçük Resim
İsim:
Regularizing_Binary_Neural_Networks_via_Ensembling_for_Efficient_Person_Re-Identification.pdf
Boyut:
1007.4 KB
Biçim:
Adobe Portable Document Format
Açıklama:
İndir
Lisans paketi
Listeleniyor 1 - 1 / 1
Küçük Resim Yok
İsim:
license.txt
Boyut:
1.56 KB
Biçim:
Item-specific license agreed upon to submission
Açıklama:
İndir

Koleksiyon

Scopus İndeksli Yayınlar Koleksiyonu
WoS İndeksli Yayınlar Koleksiyonu