Matches in SemOpenAlex for { <https://semopenalex.org/work/W4383469019> ?p ?o ?g. }
Showing items 1 to 49 of
49
with 100 items per page.
- W4383469019 abstract "Autonomous vehicles and Advanced Driving Assistance Systems (ADAS) have the potential to radically change the way we travel. Many such vehicles currently rely on segmentation and object detection algorithms to detect and track objects around its surrounding. The data collected from the vehicles are often sent to cloud servers to facilitate continual/life-long learning of these algorithms. Considering the bandwidth constraints, the data is compressed before sending it to servers, where it is typically decompressed for training and analysis. In this work, we propose the use of a learning-based compression Codec to reduce the overhead in latency incurred for the decompression operation in the standard pipeline. We demonstrate that the learned compressed representation can also be used to perform tasks like semantic segmentation in addition to decompression to obtain the images. We experimentally validate the proposed pipeline on the Cityscapes dataset, where we achieve a compression factor up to $66 times$ while preserving the information required to perform segmentation with a dice coefficient of $0.84$ as compared to $0.88$ achieved using decompressed images while reducing the overall compute by $11%$." @default.
- W4383469019 created "2023-07-07" @default.
- W4383469019 creator A5023217610 @default.
- W4383469019 creator A5036761636 @default.
- W4383469019 creator A5092418454 @default.
- W4383469019 date "2023-07-04" @default.
- W4383469019 modified "2023-09-27" @default.
- W4383469019 title "Exploiting Richness of Learned Compressed Representation of Images for Semantic Segmentation" @default.
- W4383469019 doi "https://doi.org/10.48550/arxiv.2307.01524" @default.
- W4383469019 hasPublicationYear "2023" @default.
- W4383469019 type Work @default.
- W4383469019 citedByCount "0" @default.
- W4383469019 crossrefType "posted-content" @default.
- W4383469019 hasAuthorship W4383469019A5023217610 @default.
- W4383469019 hasAuthorship W4383469019A5036761636 @default.
- W4383469019 hasAuthorship W4383469019A5092418454 @default.
- W4383469019 hasBestOaLocation W43834690191 @default.
- W4383469019 hasConcept C124504099 @default.
- W4383469019 hasConcept C131979681 @default.
- W4383469019 hasConcept C154945302 @default.
- W4383469019 hasConcept C199360897 @default.
- W4383469019 hasConcept C31972630 @default.
- W4383469019 hasConcept C41008148 @default.
- W4383469019 hasConcept C43521106 @default.
- W4383469019 hasConcept C89600930 @default.
- W4383469019 hasConceptScore W4383469019C124504099 @default.
- W4383469019 hasConceptScore W4383469019C131979681 @default.
- W4383469019 hasConceptScore W4383469019C154945302 @default.
- W4383469019 hasConceptScore W4383469019C199360897 @default.
- W4383469019 hasConceptScore W4383469019C31972630 @default.
- W4383469019 hasConceptScore W4383469019C41008148 @default.
- W4383469019 hasConceptScore W4383469019C43521106 @default.
- W4383469019 hasConceptScore W4383469019C89600930 @default.
- W4383469019 hasLocation W43834690191 @default.
- W4383469019 hasOpenAccess W4383469019 @default.
- W4383469019 hasPrimaryLocation W43834690191 @default.
- W4383469019 hasRelatedWork W1669643531 @default.
- W4383469019 hasRelatedWork W2005437358 @default.
- W4383469019 hasRelatedWork W2008656436 @default.
- W4383469019 hasRelatedWork W2023558673 @default.
- W4383469019 hasRelatedWork W2039154422 @default.
- W4383469019 hasRelatedWork W2134924024 @default.
- W4383469019 hasRelatedWork W2517104666 @default.
- W4383469019 hasRelatedWork W2979718872 @default.
- W4383469019 hasRelatedWork W3158534694 @default.
- W4383469019 hasRelatedWork W4283033898 @default.
- W4383469019 isParatext "false" @default.
- W4383469019 isRetracted "false" @default.
- W4383469019 workType "article" @default.