Late Breaking Results: Less Sense Makes More Sense: In-Sensor Compressive Learning for Efficient Machine Vision

Integrating deep learning and image sensors has significantly transformed machine vision applications. Yet, conventional highresolution image acquisition schemes enabled by imagers are energyinefficient for deep learning, as they involve excessive data quantization and transmission overhead. To addr...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2025 62nd ACM/IEEE Design Automation Conference (DAC) s. 1 - 2
Hlavní autoři: Liang, Yiwen, Cao, Weidong
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 22.06.2025
Témata:
Data compression
Deep learning
Design automation
Energy conservation
Feature extraction
Image coding
Image sensors
Machine vision
Optimization
Quantization (signal)
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Integrating deep learning and image sensors has significantly transformed machine vision applications. Yet, conventional highresolution image acquisition schemes enabled by imagers are energyinefficient for deep learning, as they involve excessive data quantization and transmission overhead. To address this challenge, we propose a lightweight in-sensor compressive learning framework that integrates a compressive learning-based encoder within image sensors for taskspecific feature extraction. Our framework encodes raw images into adaptive low-dimensional representations using only a 1-bit encoder by joint optimization with downstream machine vision tasks. It achieves 10 \times data compression, a minimum of 1.6% accuracy loss in the task, and 3.93 \times energy savings at the sensor-end, outperforming prior arts.
DOI:10.1109/DAC63849.2025.11132931