Corpus ID: 6303574

Matching neural paths: transfer from recognition to correspondence search

  title={Matching neural paths: transfer from recognition to correspondence search},
  author={Nikolay Savinov and L. Ladicky and M. Pollefeys},
  • Nikolay Savinov, L. Ladicky, M. Pollefeys
  • Published 2017
  • Computer Science
  • ArXiv
  • Many machine learning tasks require finding per-part correspondences between objects. In this work we focus on low-level correspondences - a highly ambiguous matching problem. We propose to use a hierarchical semantic representation of the objects, coming from a convolutional neural network, to solve this ambiguity. Training it for low-level correspondence prediction directly might not be an option in some domains where the ground-truth correspondences are hard to obtain. We show how transfer… CONTINUE READING
    Neighbourhood Consensus Networks
    • 75
    • PDF
    D2-Net: A Trainable CNN for Joint Detection and Description of Local Features
    • 59
    • PDF
    D2-Net: A Trainable CNN for Joint Description and Detection of Local Features
    • 33
    R2D2: Repeatable and Reliable Detector and Descriptor
    • 44
    • PDF


    Publications referenced by this paper.
    Stereo Matching by Training a Convolutional Neural Network to Compare Image Patches
    • 755
    • Highly Influential
    • PDF
    Universal Correspondence Network
    • 171
    • PDF
    Do Convnets Learn Correspondence?
    • 225
    • PDF
    You Only Look Once: Unified, Real-Time Object Detection
    • 8,796
    • PDF
    DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
    • 3,555
    • PDF
    Very Deep Convolutional Networks for Large-Scale Image Recognition
    • 39,495
    • PDF
    CNN Features Off-the-Shelf: An Astounding Baseline for Recognition
    • 3,551
    • PDF
    Are we ready for autonomous driving? The KITTI vision benchmark suite
    • 4,716
    • PDF