Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387559897> ?p ?o ?g. }
Showing items 1 to 73 of
73
with 100 items per page.
- W4387559897 abstract "IoT devices are increasingly the source of data for machine learning (ML) applications running on edge servers. Data transmissions from devices to servers are often over local wireless networks whose bandwidth is not just limited but, more importantly, variable. Furthermore, in cyber-physical systems interacting with the physical environment, image offloading is also commonly subject to timing constraints. It is, therefore, important to develop an adaptive approach that maximizes the inference performance of ML applications under timing constraints and the resource constraints of IoT devices. In this paper, we use image classification as our target application and propose progressive neural compression (PNC) as an efficient solution to this problem. Although neural compression has been used to compress images for different ML applications, existing solutions often produce fixed-size outputs that are unsuitable for timing-constrained offloading over variable bandwidth. To address this limitation, we train a multi-objective rateless autoencoder that optimizes for multiple compression rates via stochastic taildrop to create a compression solution that produces features ordered according to their importance to inference performance. Features are then transmitted in that order based on available bandwidth, with classification ultimately performed using the (sub)set of features received by the deadline. We demonstrate the benefits of PNC over state-of-the-art neural compression approaches and traditional compression methods on a testbed comprising an IoT device and an edge server connected over a wireless network with varying bandwidth." @default.
- W4387559897 created "2023-10-12" @default.
- W4387559897 creator A5034805517 @default.
- W4387559897 creator A5044400826 @default.
- W4387559897 creator A5045611682 @default.
- W4387559897 creator A5058007175 @default.
- W4387559897 creator A5070918610 @default.
- W4387559897 creator A5082041084 @default.
- W4387559897 date "2023-10-08" @default.
- W4387559897 modified "2023-10-18" @default.
- W4387559897 title "Progressive Neural Compression for Adaptive Image Offloading under Timing Constraints" @default.
- W4387559897 doi "https://doi.org/10.48550/arxiv.2310.05306" @default.
- W4387559897 hasPublicationYear "2023" @default.
- W4387559897 type Work @default.
- W4387559897 citedByCount "0" @default.
- W4387559897 crossrefType "posted-content" @default.
- W4387559897 hasAuthorship W4387559897A5034805517 @default.
- W4387559897 hasAuthorship W4387559897A5044400826 @default.
- W4387559897 hasAuthorship W4387559897A5045611682 @default.
- W4387559897 hasAuthorship W4387559897A5058007175 @default.
- W4387559897 hasAuthorship W4387559897A5070918610 @default.
- W4387559897 hasAuthorship W4387559897A5082041084 @default.
- W4387559897 hasBestOaLocation W43875598971 @default.
- W4387559897 hasConcept C101738243 @default.
- W4387559897 hasConcept C111919701 @default.
- W4387559897 hasConcept C115961682 @default.
- W4387559897 hasConcept C120314980 @default.
- W4387559897 hasConcept C13481523 @default.
- W4387559897 hasConcept C138236772 @default.
- W4387559897 hasConcept C154945302 @default.
- W4387559897 hasConcept C2776257435 @default.
- W4387559897 hasConcept C31258907 @default.
- W4387559897 hasConcept C31395832 @default.
- W4387559897 hasConcept C41008148 @default.
- W4387559897 hasConcept C50644808 @default.
- W4387559897 hasConcept C78548338 @default.
- W4387559897 hasConcept C79403827 @default.
- W4387559897 hasConcept C79974875 @default.
- W4387559897 hasConcept C93996380 @default.
- W4387559897 hasConcept C9417928 @default.
- W4387559897 hasConceptScore W4387559897C101738243 @default.
- W4387559897 hasConceptScore W4387559897C111919701 @default.
- W4387559897 hasConceptScore W4387559897C115961682 @default.
- W4387559897 hasConceptScore W4387559897C120314980 @default.
- W4387559897 hasConceptScore W4387559897C13481523 @default.
- W4387559897 hasConceptScore W4387559897C138236772 @default.
- W4387559897 hasConceptScore W4387559897C154945302 @default.
- W4387559897 hasConceptScore W4387559897C2776257435 @default.
- W4387559897 hasConceptScore W4387559897C31258907 @default.
- W4387559897 hasConceptScore W4387559897C31395832 @default.
- W4387559897 hasConceptScore W4387559897C41008148 @default.
- W4387559897 hasConceptScore W4387559897C50644808 @default.
- W4387559897 hasConceptScore W4387559897C78548338 @default.
- W4387559897 hasConceptScore W4387559897C79403827 @default.
- W4387559897 hasConceptScore W4387559897C79974875 @default.
- W4387559897 hasConceptScore W4387559897C93996380 @default.
- W4387559897 hasConceptScore W4387559897C9417928 @default.
- W4387559897 hasLocation W43875598971 @default.
- W4387559897 hasOpenAccess W4387559897 @default.
- W4387559897 hasPrimaryLocation W43875598971 @default.
- W4387559897 hasRelatedWork W2076202163 @default.
- W4387559897 hasRelatedWork W2096442341 @default.
- W4387559897 hasRelatedWork W2161981399 @default.
- W4387559897 hasRelatedWork W2387043686 @default.
- W4387559897 hasRelatedWork W2595043295 @default.
- W4387559897 hasRelatedWork W2751842002 @default.
- W4387559897 hasRelatedWork W3165542721 @default.
- W4387559897 hasRelatedWork W4211022243 @default.
- W4387559897 hasRelatedWork W4243608781 @default.
- W4387559897 hasRelatedWork W4378191574 @default.
- W4387559897 isParatext "false" @default.
- W4387559897 isRetracted "false" @default.
- W4387559897 workType "article" @default.