Metraipolis › archive › dc_cb7cf8f2ff27

Hardware-Aware Learned Representation Compression for Distributed In-Sensor Vision — arXiv:2609.13947

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.13947
License (as archived)
CC0-1.0
Archived
2026-10-15T22:50:48.412Z
SHA-256 of the archived text
6342e04370c76b4c4cc46793a397e71bee4479dd1ef8ea509748f2464240be12
Stable URL of this page
https://metraipolis.com/documento/dc_cb7cf8f2ff27

How to cite

Hardware-Aware Learned Representation Compression for Distributed In-Sensor Vision — arXiv:2609.13947 — arXiv (en), https://arxiv.org/abs/2609.13947 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cb7cf8f2ff27 (Metraipolis archive dc_cb7cf8f2ff27, sha256 6342e04370c76b4c4cc46793a397e71bee4479dd1ef8ea509748f2464240be12)
BibTeX
@misc{dccb7cf8f2ff27,
  title = {Hardware-Aware Learned Representation Compression for Distributed In-Sensor Vision — arXiv:2609.13947},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.13947},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cb7cf8f2ff27; sha256 6342e04370c76b4c4cc46793a397e71bee4479dd1ef8ea509748f2464240be12},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.13947. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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 objectives, while the decoder is used only during training. OASIS supports two complementary deployment paths. The first applies 4-bit quantization and Huffman coding while preserving the spatial structure required by classification and dense-prediction tasks. The second uses Sobol-based hyperdimensional computing (HDC) to transform the encoder latent into a fixed-dimensional binary hypervector for associative-memory classification. For the SwinViT-based VWW model, mapping a $3\times3\times8$ latent to a 64-dimensional hypervector provides an additional $1.77\times$ communication reduction with less than one percentage point of accuracy loss relative to the 128-dimensional configuration, yielding an overall $18{,}816\times$ reduction compared with raw 8-bit image transmission. We implement the digital near-sensor pipeline on an AMD Xilinx Zynq UltraScale+ FPGA and characterize it using direct board-level power measurements and Vivado post-implementation analysis, together with circuit-simulated CIS models and a 7-nm ASIC projection. Across visual wake-word classification, hand tracking, and eye tracking, OASIS reduces total system energy by approximately $2\times$-$4.5\times$ while maintaining competitive accuracy, demonstrating a practical hardware-algorithm co-design path for communication-efficient in-sensor vision.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-15 in cs.AI).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Hardware Architecture (cs.AR).
Pagina del lavoro: https://arxiv.org/abs/2609.13947 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-15T22:29:03.591Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).