Abstract
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.
Original language | English |
---|---|
Pages (from-to) | 925-930 |
Number of pages | 6 |
Journal | IEEE Transactions on Neural Networks and Learning Systems |
Volume | 32 |
Issue number | 2 |
Early online date | 2020 |
DOIs | |
Publication status | Published - 2021 |
Publication type | A1 Journal article-refereed |
Keywords
- Prototypes
- Training
- Neural networks
- Data visualization
- Learning systems
- Tensile stress
- Image edge detection
- Edge tensor processing unit (TPU)
- embedded deep learning (DL)
- few-shot learning
- weight imprinting (WI).
Publication forum classification
- Publication forum level 3