Projects

Knowledge Graph Driven AutoML

This project aims at an automatic pipeline of training models to recognize everything in images. The topics include:

  • Neual Architecture Search,

  • Semi-Supervised Learning,

  • Visual Knowledge Graph,

  • Few-shot Learning,

  • Instance Recognition.

Architecture Design

 
 
  • X. Wang, S. Zhang, Z. Yu, L. Feng and W. Zhang.
    Scale-equalizing pyramid convolution for object detection.
    Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2020.

    Pyramid convolution (a kind of 3D convolution) to extract multiscale features as a better alternative design of Feature Pyramid Networks (FPN).

Weakly Supervised Learning

 

Instance Retrieval

 
 
 







Locations of visitors to this page

profile counter Stats

Copyright © 2019 Wei Zhang