arXiv Artificial Intelligence

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

1 hour ago 15.09.2026 07:00 👁 2 views
Hardware-Aware Learned Representation Compression for Distributed In-Sensor Vision

Quick summary

arXiv:2609.13947v1 Announce Type: cross Abstract: In-sensor computing reduces the cost of transmitting high-resolution image data by performing early-stage processing near the sensor. However, the logic chip integrated with a CMOS image sensor (CIS) is tightly constrained in compute and memory, limiting conventional deep neural network partitioning. We present OASIS, a distributed in-sensor vision framework that uses a lightweight encoder to generate compact, task-relevant representations before off-chip transmission. The encoder is trained end-to-end using task, entropy, and reconstruction ob

Key takeaways

  • arXiv:2609.13947v1 Announce Type: cross Abstract: In-sensor computing reduces the cost of transmitting high-resolution image data by performing early-stage processing near the sensor.
  • However, the logic chip integrated with a CMOS image sensor (CIS) is tightly constrained in compute and memory, limiting conventional deep neural network partitioning.
  • We present OASIS, a distributed in-sensor vision framework that uses a lightweight encoder to generate compact, task-relevant representations before off-chip transmission.

Why it matters

“Hardware-Aware Learned Representation Compression for Distributed In-Sensor Vision” exposes the compute, energy and supply-chain layer behind model competition. Capacity shifts can influence model costs, service availability and the ability of smaller companies to compete.

Kaynak sitede devamını oku: arXiv Artificial Intelligence ↗