Learning to segment on tiny datasets: a new shape model

08/07/2017
by   Maxime Tremblay, et al.
0

Current object segmentation algorithms are based on the hypothesis that one has access to a very large amount of data. In this paper, we aim to segment objects using only tiny datasets. To this extent, we propose a new automatic part-based object segmentation algorithm for non-deformable and semi-deformable objects in natural backgrounds. We have developed a novel shape descriptor which models the local boundaries of an object's part. This shape descriptor is used in a bag-of-words approach for object detection. Once the detection process is performed, we use the background and foreground likelihood given by our trained shape model, and the information from the image content, to define a dense CRF model. We use a mean field approximation to solve it and thus segment the object of interest. Performance evaluated on different datasets shows that our approach can sometimes achieve results near state-of-the-art techniques based on big data while requiring only a tiny training set.

READ FULL TEXT
research
04/27/2012

Background subtraction based on Local Shape

We present a novel approach to background subtraction that is based on t...
research
11/22/2022

Global-Local Aggregation with Deformable Point Sampling for Camouflaged Object Detection

The camouflaged object detection (COD) task aims to find and segment obj...
research
10/14/2022

MOVE: Unsupervised Movable Object Segmentation and Detection

We introduce MOVE, a novel method to segment objects without any form of...
research
03/06/2021

Simultaneously Localize, Segment and Rank the Camouflaged Objects

Camouflage is a key defence mechanism across species that is critical to...
research
07/12/2013

Speedy Object Detection based on Shape

This study is a part of design of an audio system for in-house object de...
research
02/02/2015

Discriminatively Trained And-Or Graph Models for Object Shape Detection

In this paper, we investigate a novel reconfigurable part-based model, n...
research
04/02/2018

Learning Descriptor Networks for 3D Shape Synthesis and Analysis

This paper proposes a 3D shape descriptor network, which is a deep convo...

Please sign up or login with your details

Forgot password? Click here to reset