DeepAI AI Chat
Log In Sign Up

Quad-networks: unsupervised learning to rank for interest point detection

by   Nikolay Savinov, et al.
Toshiba Corp.
ETH Zurich

Several machine learning tasks require to represent the data using only a sparse set of interest points. An ideal detector is able to find the corresponding interest points even if the data undergo a transformation typical for a given domain. Since the task is of high practical interest in computer vision, many hand-crafted solutions were proposed. In this paper, we ask a fundamental question: can we learn such detectors from scratch? Since it is often unclear what points are "interesting", human labelling cannot be used to find a truly unbiased solution. Therefore, the task requires an unsupervised formulation. We are the first to propose such a formulation: training a neural network to rank points in a transformation-invariant manner. Interest points are then extracted from the top/bottom quantiles of this ranking. We validate our approach on two tasks: standard RGB image interest point detection and challenging cross-modal interest point detection between RGB and depth images. We quantitatively show that our unsupervised method performs better or on-par with baselines.


page 3

page 5

page 7

page 8


SIPS: Unsupervised Succinct Interest Points

Detecting interest points is a key component of vision-based estimation ...

Reinforced Feature Points: Optimizing Feature Detection and Description for a High-Level Task

We address a core problem of computer vision: Detection and description ...

SCK: A sparse coding based key-point detector

All current popular hand-crafted key-point detectors such as Harris corn...

RGB-D Grasp Detection via Depth Guided Learning with Cross-modal Attention

Planar grasp detection is one of the most fundamental tasks to robotic m...

Improved Point Transformation Methods For Self-Supervised Depth Prediction

Given stereo or egomotion image pairs, a popular and successful method f...

Cross-Modal Analysis of Human Detection for Robotics: An Industrial Case Study

Advances in sensing and learning algorithms have led to increasingly mat...

3D Interest Point Detection via Discriminative Learning

The task of detecting the interest points in 3D meshes has typically bee...