Research

Low-Power Edge-AI capabilities are essential for on- device extended reality (XR) applications to support the vision of Metaverse. A critical requirement for emerging AI applications is personalization and adaptability without requiring retraining. Few-shot learning using embedding- based computations present an attractive method for the same. However, quantization-based optimizations to map such computations are yet to be explored. In this work, we present a fully binarized distance computing (BinDC) framework to perform distance computations for few-shot learning using only accumulation and logic operations (XOR/XNOR). The proposed method leads to marginal loss in accuracy of ≈ 4% (for 4-bits). This leads to savings in memory (≈ 8×), energy (≈ 2.5-3×), power (≈ 2×) and latency (≈ 1.1-1.5×) compared to a floating-point cosine distance computation when using CPU-based computations performed on an embedded platform. We further demonstrate realization utilizing RRAM (resistive random access memory) based IMC (in-memory computing) to further im- prove EDP (energy delay product) (≈ 1000×) in comparison to the embedded CPU-based realization.