G2MF-WA: Geometric Multi-Model Fitting with Weakly Annotated Data

01/20/2020
by   Chao Zhang, et al.
7

In this paper we attempt to address the problem of geometric multi-model fitting with resorting to a few weakly annotated (WA) data points, which has been sparsely studied so far. In weak annotating, most of the manual annotations are supposed to be correct yet inevitably mixed with incorrect ones. The WA data can be naturally obtained in an interactive way for specific tasks, for example, in the case of homography estimation, one can easily annotate points on the same plane/object with a single label by observing the image. Motivated by this, we propose a novel method to make full use of the WA data to boost the multi-model fitting performance. Specifically, a graph for model proposal sampling is first constructed using the WA data, given the prior that the WA data annotated with the same weak label has a high probability of being assigned to the same model. By incorporating this prior knowledge into the calculation of edge probabilities, vertices (i.e., data points) lie on/near the latent model are likely to connect together and further form a subset/cluster for effective proposals generation. With the proposals generated, the α-expansion is adopted for labeling, and our method in return updates the proposals. This works in an iterative way. Extensive experiments validate our method and show that the proposed method produces noticeably better results than state-of-the-art techniques in most cases.

READ FULL TEXT

page 2

page 7

page 8

page 9

page 10

research
05/26/2017

Effective Sampling: Fast Segmentation Using Robust Geometric Model Fitting

Identifying the underlying models in a set of data points contaminated b...
research
03/25/2016

Mode-Seeking on Hypergraphs for Robust Geometric Model Fitting

In this paper, we propose a novel geometric model fitting method, called...
research
02/13/2020

Hypergraph Optimization for Multi-structural Geometric Model Fitting

Recently, some hypergraph-based methods have been proposed to deal with ...
research
07/11/2016

Hypergraph Modelling for Geometric Model Fitting

In this paper, we propose a novel hypergraph based method (called HF) to...
research
03/10/2022

Label-efficient Hybrid-supervised Learning for Medical Image Segmentation

Due to the lack of expertise for medical image annotation, the investiga...
research
06/05/2019

Progressive-X: Efficient, Anytime, Multi-Model Fitting Algorithm

The Progressive-X algorithm, Prog-X in short, is proposed for geometric ...

Please sign up or login with your details

Forgot password? Click here to reset