SwePub
Sök i SwePub databas

  Utökad sökning

Träfflista för sökning "WFRF:(Baci Saimir) "

Sökning: WFRF:(Baci Saimir)

  • Resultat 1-2 av 2
Sortera/gruppera träfflistan
   
NumreringReferensOmslagsbildHitta
1.
  • Aksoy, Eren, 1982-, et al. (författare)
  • SalsaNet : Fast Road and Vehicle Segmentationin LiDAR Point Clouds for Autonomous Driving
  • 2020
  • Ingår i: IEEE Intelligent Vehicles Symposium. - Piscataway, N.J. : IEEE. ; , s. 926-932
  • Konferensbidrag (refereegranskat)abstract
    • In this paper, we introduce a deep encoder-decoder network, named SalsaNet, for efficient semantic segmentation of 3D LiDAR point clouds. SalsaNet segments the road, i.e. drivable free-space, and vehicles in the scene by employing the Bird-Eye-View (BEV) image projection of the point cloud. To overcome the lack of annotated point cloud data, in particular for the road segments, we introduce an auto-labeling process which transfers automatically generated labels from the camera to LiDAR. We also explore the role of imagelike projection of LiDAR data in semantic segmentation by comparing BEV with spherical-front-view projection and show that SalsaNet is projection-agnostic. We perform quantitative and qualitative evaluations on the KITTI dataset, which demonstrate that the proposed SalsaNet outperforms other state-of-the-art semantic segmentation networks in terms of accuracy and computation time. Our code and data are publicly available at https://gitlab.com/aksoyeren/salsanet.git. 
  •  
2.
  • Tzelepis, Georgios, et al. (författare)
  • Deep Neural Network Compression for Image Classification and Object Detection
  • 2019
  • Konferensbidrag (refereegranskat)abstract
    • Neural networks have been notorious for being computationally expensive. This is mainly because neural networks are often over-parametrized and most likely have redundant nodes or layers as they are getting deeper and wider. Their demand for hardware resources prohibits their extensive use in embedded devices and puts restrictions on tasks like real-time image classification or object detection. In this work, we propose a network-agnostic model compression method infused with a novel dynamical clustering approach to reduce the computational cost and memory footprint of deep neural networks. We evaluated our new compression method on five different state-of-the-art image classification and object detection networks. In classification networks, we pruned about 95% of network parameters. In advanced detection networks such as YOLOv3, our proposed compression method managed to reduce the model parameters up to 59.70% which yielded 110X less memory without sacrificing much in accuracy.
  •  
Skapa referenser, mejla, bekava och länka
  • Resultat 1-2 av 2
Typ av publikation
konferensbidrag (2)
Typ av innehåll
refereegranskat (2)
Författare/redaktör
Baci, Saimir (2)
Cavdar, Selcuk (2)
Aksoy, Eren, 1982- (1)
Tzelepis, Georgios (1)
Erdal Aksoy, Eren, 1 ... (1)
Asif, Ahraz (1)
Lärosäte
Högskolan i Halmstad (2)
Språk
Engelska (2)
Forskningsämne (UKÄ/SCB)
Teknik (2)

År

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.

 
pil uppåt Stäng

Kopiera och spara länken för att återkomma till aktuell vy