FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4380881065> ?p ?o ?g. }

• W4380881065 abstract "With the rapid advances of deep learning-based computer vision (CV) technology, digital images are increasingly consumed, not by humans, but by downstream CV algorithms. However, capturing high-fidelity and high-resolution images is energy-intensive. It not only dominates the energy consumption of the sensor itself (i.e. in low-power edge devices), but also contributes to significant memory burdens and performance bottlenecks in the later storage, processing, and communication stages. In this paper, we systematically explore a new paradigm of in-sensor processing, termed learned compressive acquisition (LeCA). Targeting machine vision applications on the edge, the LeCA framework exploits the joint learning of a sensor autoencoder structure with the downstream CV algorithms to effectively compress the original image into low-dimensional features with adaptive bit depth. We employ column-parallel analog-domain processing directly inside the image sensor to perform the compressive encoding of the raw image, resulting in meaningful hardware savings, and energy efficiency improvements. Evaluated within a modern machine vision processing pipeline, LeCA achieves 4×, 6×, and 8× compression ratios prior to any digital compression, with minimal accuracy loss of 0.97%, 0.98%, and 2.01% on ImageNet, outperforming existing methods. Compared with the conventional full-resolution image sensor and the state-of-the-art compressive sensing sensor, our LeCA sensor is 6.3× and 2.2× more energy-efficient while reaching a 2× higher compression ratio." @default.
• W4380881065 created "2023-06-17" @default.
• W4380881065 creator A5010392575 @default.
• W4380881065 creator A5050566186 @default.
• W4380881065 creator A5051423351 @default.
• W4380881065 creator A5062801966 @default.
• W4380881065 creator A5070329670 @default.
• W4380881065 creator A5075420600 @default.
• W4380881065 creator A5076757325 @default.
• W4380881065 creator A5077984277 @default.
• W4380881065 date "2023-06-17" @default.
• W4380881065 modified "2023-10-18" @default.
• W4380881065 title "LeCA: In-Sensor Learned Compressive Acquisition for Efficient Machine Vision on the Edge" @default.
• W4380881065 cites W1483556273 @default.
• W4380881065 cites W1503479382 @default.
• W4380881065 cites W1980178290 @default.
• W4380881065 cites W1999455876 @default.
• W4380881065 cites W2012696426 @default.
• W4380881065 cites W2013987500 @default.
• W4380881065 cites W2021347102 @default.
• W4380881065 cites W2040903332 @default.
• W4380881065 cites W2049819383 @default.
• W4380881065 cites W2060709554 @default.
• W4380881065 cites W2064076387 @default.
• W4380881065 cites W2070993571 @default.
• W4380881065 cites W2097761689 @default.
• W4380881065 cites W2101004723 @default.
• W4380881065 cites W2108598243 @default.
• W4380881065 cites W2118216984 @default.
• W4380881065 cites W2122548617 @default.
• W4380881065 cites W2137100320 @default.
• W4380881065 cites W2138536318 @default.
• W4380881065 cites W2138674095 @default.
• W4380881065 cites W2145348019 @default.
• W4380881065 cites W2165637632 @default.
• W4380881065 cites W2194775991 @default.
• W4380881065 cites W2197399834 @default.
• W4380881065 cites W2486080740 @default.
• W4380881065 cites W2615178951 @default.
• W4380881065 cites W2774669597 @default.
• W4380881065 cites W2788231037 @default.
• W4380881065 cites W2790486801 @default.
• W4380881065 cites W2798309714 @default.
• W4380881065 cites W2899519551 @default.
• W4380881065 cites W2910901852 @default.
• W4380881065 cites W2935381027 @default.
• W4380881065 cites W2948978827 @default.
• W4380881065 cites W2962891349 @default.
• W4380881065 cites W2964057022 @default.
• W4380881065 cites W2972984303 @default.
• W4380881065 cites W2974134299 @default.
• W4380881065 cites W2975938667 @default.
• W4380881065 cites W2981090330 @default.
• W4380881065 cites W2981613960 @default.
• W4380881065 cites W2996765167 @default.
• W4380881065 cites W3015271406 @default.
• W4380881065 cites W3020338877 @default.
• W4380881065 cites W3043571714 @default.
• W4380881065 cites W3096649732 @default.
• W4380881065 cites W3096831136 @default.
• W4380881065 cites W3134599322 @default.
• W4380881065 cites W3134748538 @default.
• W4380881065 cites W3161891823 @default.
• W4380881065 cites W3174208823 @default.
• W4380881065 cites W3185169430 @default.
• W4380881065 cites W4220909387 @default.
• W4380881065 doi "https://doi.org/10.1145/3579371.3589089" @default.
• W4380881065 hasPublicationYear "2023" @default.
• W4380881065 type Work @default.
• W4380881065 citedByCount "0" @default.
• W4380881065 crossrefType "proceedings-article" @default.
• W4380881065 hasAuthorship W4380881065A5010392575 @default.
• W4380881065 hasAuthorship W4380881065A5050566186 @default.
• W4380881065 hasAuthorship W4380881065A5051423351 @default.
• W4380881065 hasAuthorship W4380881065A5062801966 @default.
• W4380881065 hasAuthorship W4380881065A5070329670 @default.
• W4380881065 hasAuthorship W4380881065A5075420600 @default.
• W4380881065 hasAuthorship W4380881065A5076757325 @default.
• W4380881065 hasAuthorship W4380881065A5077984277 @default.
• W4380881065 hasBestOaLocation W43808810651 @default.
• W4380881065 hasConcept C101738243 @default.
• W4380881065 hasConcept C104317675 @default.
• W4380881065 hasConcept C105795698 @default.
• W4380881065 hasConcept C108583219 @default.
• W4380881065 hasConcept C115961682 @default.
• W4380881065 hasConcept C119599485 @default.
• W4380881065 hasConcept C124851039 @default.
• W4380881065 hasConcept C127413603 @default.
• W4380881065 hasConcept C154945302 @default.
• W4380881065 hasConcept C162307627 @default.
• W4380881065 hasConcept C186370098 @default.
• W4380881065 hasConcept C199360897 @default.
• W4380881065 hasConcept C24590314 @default.
• W4380881065 hasConcept C2742236 @default.
• W4380881065 hasConcept C2780165032 @default.
• W4380881065 hasConcept C31258907 @default.
• W4380881065 hasConcept C31972630 @default.
• W4380881065 hasConcept C33923547 @default.
• W4380881065 hasConcept C41008148 @default.
• W4380881065 hasConcept C43521106 @default.

• next