12 mJ per Class On-Device Online Few-Shot Class-Incremental Learning
CoRR(2024)
摘要
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
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.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要