12 mJ per Class On-Device Online Few-Shot Class-Incremental Learning
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914711099932672 |
|---|---|
| author | Wibowo, Yoga Esa Cioflan, Cristian Ingolfsson, Thorir Mar Hersche, Michael Zhao, Leo Rahimi, Abbas Benini, Luca |
| author_facet | Wibowo, Yoga Esa Cioflan, Cristian Ingolfsson, Thorir Mar Hersche, Michael Zhao, Leo Rahimi, Abbas Benini, Luca |
| contents | Few-Shot Class-Incremental Learning (FSCIL) enables machine learning systems to expand their inference capabilities to new classes using only a few labeled examples, without forgetting the previously learned classes. Classical backpropagation-based learning and its variants are often unsuitable for battery-powered, memory-constrained systems at the extreme edge. In this work, we introduce Online Few-Shot Class-Incremental Learning (O-FSCIL), based on a lightweight model consisting of a pretrained and metalearned feature extractor and an expandable explicit memory storing the class prototypes. The architecture is pretrained with a novel feature orthogonality regularization and metalearned with a multi-margin loss. For learning a new class, our approach extends the explicit memory with novel class prototypes, while the remaining architecture is kept frozen. This allows learning previously unseen classes based on only a few examples with one single pass (hence online). O-FSCIL obtains an average accuracy of 68.62% on the FSCIL CIFAR100 benchmark, achieving state-of-the-art results. Tailored for ultra-low-power platforms, we implement O-FSCIL on the 60 mW GAP9 microcontroller, demonstrating online learning capabilities within just 12 mJ per new class. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_07851 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | 12 mJ per Class On-Device Online Few-Shot Class-Incremental Learning Wibowo, Yoga Esa Cioflan, Cristian Ingolfsson, Thorir Mar Hersche, Michael Zhao, Leo Rahimi, Abbas Benini, Luca Machine Learning Computer Vision and Pattern Recognition Few-Shot Class-Incremental Learning (FSCIL) enables machine learning systems to expand their inference capabilities to new classes using only a few labeled examples, without forgetting the previously learned classes. Classical backpropagation-based learning and its variants are often unsuitable for battery-powered, memory-constrained systems at the extreme edge. In this work, we introduce Online Few-Shot Class-Incremental Learning (O-FSCIL), based on a lightweight model consisting of a pretrained and metalearned feature extractor and an expandable explicit memory storing the class prototypes. The architecture is pretrained with a novel feature orthogonality regularization and metalearned with a multi-margin loss. For learning a new class, our approach extends the explicit memory with novel class prototypes, while the remaining architecture is kept frozen. This allows learning previously unseen classes based on only a few examples with one single pass (hence online). O-FSCIL obtains an average accuracy of 68.62% on the FSCIL CIFAR100 benchmark, achieving state-of-the-art results. Tailored for ultra-low-power platforms, we implement O-FSCIL on the 60 mW GAP9 microcontroller, demonstrating online learning capabilities within just 12 mJ per new class. |
| title | 12 mJ per Class On-Device Online Few-Shot Class-Incremental Learning |
| topic | Machine Learning Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2403.07851 |