Weighted Hausdorff Distance: A Loss Function For Object Localization

by   Javier Ribera, et al.

Recent advances in Convolutional Neural Networks (CNN) have achieved remarkable results in localizing objects in images. In these networks, the training procedure usually requires providing bounding boxes or the maximum number of expected objects. In this paper, we address the task of estimating object locations without annotated bounding boxes, which are typically hand-drawn and time consuming to label. We propose a loss function that can be used in any Fully Convolutional Network (FCN) to estimate object locations. This loss function is a modification of the Average Hausdorff Distance between two unordered sets of points. The proposed method does not require one to "guess" the maximum number of objects in the image, and has no notion of bounding boxes, region proposals, or sliding windows. We evaluate our method with three datasets designed to locate people's heads, pupil centers and plant centers. We report an average precision and recall of 94 datasets, and an average location error of 6 pixels in 256x256 images.


page 2

page 8

page 10

page 11


Weakly Supervised Object Localization on grocery shelves using simple FCN and Synthetic Dataset

We propose a weakly supervised method using two algorithms to predict ob...

OmniDetector: With Neural Networks to Bounding Boxes

We propose a person detector on omnidirectional images, an accurate meth...

Learning Objectness from Sonar Images for Class-Independent Object Detection

Detecting novel objects without class information is not trivial, as it ...

Learning a Fully Convolutional Network for Object Recognition using very few Data

In recent years, data-driven methods have shown great success for extrac...

A CNN Framenwork Based on Line Annotations for Detecting Nematodes in Microscopic Images

Plant parasitic nematodes cause damage to crop plants on a global scale....

RAPiD: Rotation-Aware People Detection in Overhead Fisheye Images

Recent methods for people detection in overhead, fisheye images either u...

ProNet: Learning to Propose Object-specific Boxes for Cascaded Neural Networks

This paper aims to classify and locate objects accurately and efficientl...

Code Repositories


A loss function (Weighted Hausdorff Distance) for object localization in PyTorch

view repo


Weighted Hausdorff Distance Loss: use it as point cloud similarity metric based loss for keras and tf. Useful in keypoint detection.

view repo


Custom Loss Functions in Keras

view repo


Tensorflow implementation for Weighted Hausdorff Distance: A Loss Function For Object Localization https://arxiv.org/abs/1806.07564

view repo


plaque detection using CNN

view repo

Please sign up or login with your details

Forgot password? Click here to reset