Improving Image co-segmentation via Deep Metric Learning
Deep Metric Learning (DML) is helpful in computer vision tasks. In this paper, we firstly introduce DML into image co-segmentation. We propose a novel Triplet loss for Image Segmentation, called IS-Triplet loss for short, and combine it with traditional image segmentation loss. Different from the ge...
Main Authors: | , |
---|---|
Format: | Article in Journal/Newspaper |
Language: | unknown |
Published: |
arXiv
2021
|
Subjects: | |
Online Access: | https://dx.doi.org/10.48550/arxiv.2103.10670 https://arxiv.org/abs/2103.10670 |
id |
ftdatacite:10.48550/arxiv.2103.10670 |
---|---|
record_format |
openpolar |
spelling |
ftdatacite:10.48550/arxiv.2103.10670 2023-05-15T16:01:30+02:00 Improving Image co-segmentation via Deep Metric Learning Li, Zhengwen Liu, Xiabi 2021 https://dx.doi.org/10.48550/arxiv.2103.10670 https://arxiv.org/abs/2103.10670 unknown arXiv arXiv.org perpetual, non-exclusive license http://arxiv.org/licenses/nonexclusive-distrib/1.0/ Computer Vision and Pattern Recognition cs.CV Artificial Intelligence cs.AI FOS Computer and information sciences Article CreativeWork article Preprint 2021 ftdatacite https://doi.org/10.48550/arxiv.2103.10670 2022-03-10T14:33:44Z Deep Metric Learning (DML) is helpful in computer vision tasks. In this paper, we firstly introduce DML into image co-segmentation. We propose a novel Triplet loss for Image Segmentation, called IS-Triplet loss for short, and combine it with traditional image segmentation loss. Different from the general DML task which learns the metric between pictures, we treat each pixel as a sample, and use their embedded features in high-dimensional space to form triples, then we tend to force the distance between pixels of different categories greater than of the same category by optimizing IS-Triplet loss so that the pixels from different categories are easier to be distinguished in the high-dimensional feature space. We further present an efficient triple sampling strategy to make a feasible computation of IS-Triplet loss. Finally, the IS-Triplet loss is combined with 3 traditional image segmentation losses to perform image segmentation. We apply the proposed approach to image co-segmentation and test it on the SBCoseg dataset and the Internet dataset. The experimental result shows that our approach can effectively improve the discrimination of pixels' categories in high-dimensional space and thus help traditional loss achieve better performance of image segmentation with fewer training epochs. : 11 pages, 5 figures Article in Journal/Newspaper DML DataCite Metadata Store (German National Library of Science and Technology) |
institution |
Open Polar |
collection |
DataCite Metadata Store (German National Library of Science and Technology) |
op_collection_id |
ftdatacite |
language |
unknown |
topic |
Computer Vision and Pattern Recognition cs.CV Artificial Intelligence cs.AI FOS Computer and information sciences |
spellingShingle |
Computer Vision and Pattern Recognition cs.CV Artificial Intelligence cs.AI FOS Computer and information sciences Li, Zhengwen Liu, Xiabi Improving Image co-segmentation via Deep Metric Learning |
topic_facet |
Computer Vision and Pattern Recognition cs.CV Artificial Intelligence cs.AI FOS Computer and information sciences |
description |
Deep Metric Learning (DML) is helpful in computer vision tasks. In this paper, we firstly introduce DML into image co-segmentation. We propose a novel Triplet loss for Image Segmentation, called IS-Triplet loss for short, and combine it with traditional image segmentation loss. Different from the general DML task which learns the metric between pictures, we treat each pixel as a sample, and use their embedded features in high-dimensional space to form triples, then we tend to force the distance between pixels of different categories greater than of the same category by optimizing IS-Triplet loss so that the pixels from different categories are easier to be distinguished in the high-dimensional feature space. We further present an efficient triple sampling strategy to make a feasible computation of IS-Triplet loss. Finally, the IS-Triplet loss is combined with 3 traditional image segmentation losses to perform image segmentation. We apply the proposed approach to image co-segmentation and test it on the SBCoseg dataset and the Internet dataset. The experimental result shows that our approach can effectively improve the discrimination of pixels' categories in high-dimensional space and thus help traditional loss achieve better performance of image segmentation with fewer training epochs. : 11 pages, 5 figures |
format |
Article in Journal/Newspaper |
author |
Li, Zhengwen Liu, Xiabi |
author_facet |
Li, Zhengwen Liu, Xiabi |
author_sort |
Li, Zhengwen |
title |
Improving Image co-segmentation via Deep Metric Learning |
title_short |
Improving Image co-segmentation via Deep Metric Learning |
title_full |
Improving Image co-segmentation via Deep Metric Learning |
title_fullStr |
Improving Image co-segmentation via Deep Metric Learning |
title_full_unstemmed |
Improving Image co-segmentation via Deep Metric Learning |
title_sort |
improving image co-segmentation via deep metric learning |
publisher |
arXiv |
publishDate |
2021 |
url |
https://dx.doi.org/10.48550/arxiv.2103.10670 https://arxiv.org/abs/2103.10670 |
genre |
DML |
genre_facet |
DML |
op_rights |
arXiv.org perpetual, non-exclusive license http://arxiv.org/licenses/nonexclusive-distrib/1.0/ |
op_doi |
https://doi.org/10.48550/arxiv.2103.10670 |
_version_ |
1766397325840744448 |