Empowering On-Device Model Adaptation with an Edge AI Inference Accelerator
On-device model adaptation is essential to enable lifelong personalization on resource-constrained hardware, but compute, power, and memory limitations of such devices make end-to-end backpropagation impractical for modern deep neural networks. This work proposes a heterogeneous adaptation pipeline that repurposes a commercial edge AI inference accelerator, Hailo-8L, for frozen-backbone feature extraction during on-device training. The computational graph is partitioned so that the pre-trained backbone is quantized to INT8 and run on the accelerator, while only a lightweight FP32 classificatio
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 51%Hardware startup unveils inference accelerator →
- FuzzySimilar title/name (fuzzy) · 84%xorbitsai/inference →
“Fuzzy title match (0.92): “Empowering On-Device Model Adaptation with an Edge AI Infere” ≈ “xorbitsai/inference””
- LinkedLinked via arxiv author · 85%Mateusz Piechocki →
“Empowering On-Device Model Adaptation with an Edge AI Inference Accelerator”
- LinkedLinked via arxiv author · 85%Alessandro Capotondi →
“Empowering On-Device Model Adaptation with an Edge AI Inference Accelerator”
- LinkedLinked via arxiv author · 85%Marek Kraft →
“Empowering On-Device Model Adaptation with an Edge AI Inference Accelerator”