Hypersphere-Based Weight Imprinting for Few-Shot Learning on Embedded Devices

Nikolaos Passalis, Alexandros Iosifidis, Moncef Gabbouj, Anastasios Tefas

Tutkimustuotos: ArtikkeliScientificvertaisarvioitu

4 Sitaatiot (Scopus)

Abstrakti

Weight imprinting (WI) was recently introduced as a way to perform gradient descent-free few-shot learning. Due to this, WI was almost immediately adapted for performing few-shot learning on embedded neural network accelerators that do not support back-propagation, e.g., edge tensor processing units. However, WI suffers from many limitations, e.g., it cannot handle novel categories with multimodal distributions and special care should be given to avoid overfitting the learned embeddings on the training classes since this can have a devastating effect on classification accuracy (for the novel categories). In this article, we propose a novel hypersphere-based WI approach that is capable of training neural networks in a regularized, imprinting-aware way effectively overcoming the aforementioned limitations. The effectiveness of the proposed method is demonstrated using extensive experiments on three image data sets.
AlkuperäiskieliEnglanti
Sivut925-930
Sivumäärä6
JulkaisuIEEE Transactions on Neural Networks and Learning Systems
Vuosikerta32
Numero2
Varhainen verkossa julkaisun päivämäärä2020
DOI - pysyväislinkit
TilaJulkaistu - 2021
OKM-julkaisutyyppiA1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä

Julkaisufoorumi-taso

  • Jufo-taso 3

Sormenjälki

Sukella tutkimusaiheisiin 'Hypersphere-Based Weight Imprinting for Few-Shot Learning on Embedded Devices'. Ne muodostavat yhdessä ainutlaatuisen sormenjäljen.

Siteeraa tätä