StuffNet: Using 'Stuff' to Improve Object Detection

    WACV, 2017.

    Cited by: 7|Bibtex|Views11|Links
    EI

    Abstract:

    We propose a Convolutional Neural Network (CNN) based algorithm – StuffNet – for object detection. In addition to the standard convolutional features trained for region proposal and object detection [33], StuffNet uses convolutional features trained for segmentation of objects and u0027stuffu0027 (amorphous categories such as ground and w...More

    Code:

    Data:

    Your rating :
    0

     

    Tags
    Comments