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

11/22/2016
by   Nikolay Savinov, et al.
0

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.

READ FULL TEXT

page 3

page 5

page 7

page 8

research
05/03/2018

SIPS: Unsupervised Succinct Interest Points

Detecting interest points is a key component of vision-based estimation ...
research
12/02/2019

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

We address a core problem of computer vision: Detection and description ...
research
02/07/2018

SCK: A sparse coding based key-point detector

All current popular hand-crafted key-point detectors such as Harris corn...
research
08/23/2023

Towards Privacy-Supporting Fall Detection via Deep Unsupervised RGB2Depth Adaptation

Fall detection is a vital task in health monitoring, as it allows the sy...
research
02/28/2023

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...
research
02/18/2021

Improved Point Transformation Methods For Self-Supervised Depth Prediction

Given stereo or egomotion image pairs, a popular and successful method f...
research
08/03/2021

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

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

Please sign up or login with your details

Forgot password? Click here to reset