arXiv AI

Hardware-Aware Learned Representation Compression for Distributed In-Sensor Vision

arXiv Computer Vision
4d ago

Adaptive AI: Energy Efficient Multi-exit TinyML on Intelligent Vision Systems at the Edge

The paper presents a novel multi‑exit computational scheme for TinyML on an ultra‑low‑power GAP9 SoC, adding confidence‑based gating points to a MobileNetV2 CNN for ImageNet‑100. By allowing inference to stop early, the approach cuts average MAC operations by 41 % (from 313 MMAC to 185 MMAC), reduces inference time by 29 % (49 ms to 35 ms), and saves 24 % in energy (2.1 mJ to 1.6 mJ per frame) with only a ~1 % drop in accuracy. Compared to a state‑of‑the‑art adaptive CNN on the same hardware, the method more than doubles computational efficiency, raising MAC/cycle from 8.1 to 17.2.

By Luca Crupi, Lorenzo Lamberti, Alessandro Giusti, Daniele Palossi
arXiv Computer Vision
4d ago

Joint Architecture-Token-Bitwidth Multi-Axis Optimization of Vision Transformers for Semiconductor IC Packaging

The paper introduces a holistic framework that jointly optimizes architecture, token, and bit-width for Vision Transformers (ViTs). It uses Neural Architecture Search (AutoFormer) to find compact backbones, token merging (ToMe) to reduce information processing, and fp16 mixed‑precision inference to accelerate operations. Experiments on ImageNet‑1K and a real‑world 3D X‑ray semiconductor defect dataset show over 10× improvements in throughput and reductions in parameters, FLOPs, and energy while preserving accuracy.

By Phat Nguyen, Xue Geng, Kaixin Xu, Wang Zhe, Xulei Yang, Ngai-Man Cheung