• Login
    View Item 
    •   Home
    • Research
    • Preprints
    • View Item
    •   Home
    • Research
    • Preprints
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Browse

    All of KAUSTCommunitiesIssue DateSubmit DateThis CollectionIssue DateSubmit Date

    My Account

    Login

    Quick Links

    Open Access PolicyORCID LibguidePlumX LibguideSubmit an Item

    Statistics

    Display statistics

    SALA: Soft Assignment Local Aggregation for 3D Semantic Segmentation

    • CSV
    • RefMan
    • EndNote
    • BibTex
    • RefWorks
    Thumbnail
    Name:
    Preprintfile1.pdf
    Size:
    6.589Mb
    Format:
    PDF
    Description:
    Pre-print
    Download
    Type
    Preprint
    Authors
    Itani, Hani
    Giancola, Silvio
    Thabet, Ali Kassem cc
    Ghanem, Bernard cc
    KAUST Department
    Non-Academic Projects
    Visual Computing Center (VCC)
    Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
    Electrical Engineering Program
    Date
    2020-12-29
    Permanent link to this record
    http://hdl.handle.net/10754/666820
    
    Metadata
    Show full item record
    Abstract
    We introduce the idea of using learnable neighbor-togrid soft assignment in grid-based aggregation functions for the task of 3D semantic segmentation. Previous methods in literature operate on a predefined geometric grid such as local volume partitions or irregular kernel points. These methods use geometric functions to assign local neighbors to their corresponding grid. Such geometric heuristics are potentially sub-optimal for the end task of semantic segmentation. Furthermore, they are applied uniformly throughout the depth of the network. A more general alternative would allow the network to learn its own neighbor-to-grid assignment function that best suits the end task. Since it is learnable, this mapping has the flexibility to be different per layer. This paper leverages learned neighbor-to-grid soft assignment to define an aggregation function that balances efficiency and performance. We demonstrate the efficacy of our method by reaching state-of-the-art (SOTA) performance on S3DIS with almost 10× less parameters than the current reigning method. We also demonstrate competitive performance on ScanNet and PartNet as compared with much larger SOTA models.
    Publisher
    arXiv
    arXiv
    arXiv:2012.14929
    Additional Links
    https://arxiv.org/pdf/2012.14929
    Collections
    Preprints; Electrical Engineering Program; Visual Computing Center (VCC); Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division

    entitlement

     
    DSpace software copyright © 2002-2021  DuraSpace
    Quick Guide | Contact Us | Send Feedback
    Open Repository is a service hosted by 
    Atmire NV
     

    Export search results

    The export option will allow you to export the current search results of the entered query to a file. Different formats are available for download. To export the items, click on the button corresponding with the preferred download format.

    By default, clicking on the export buttons will result in a download of the allowed maximum amount of items. For anonymous users the allowed maximum amount is 50 search results.

    To select a subset of the search results, click "Selective Export" button and make a selection of the items you want to export. The amount of items that can be exported at once is similarly restricted as the full export.

    After making a selection, click one of the export format buttons. The amount of items that will be exported is indicated in the bubble next to export format.