Excavate Condition-invariant Space by Intrinsic Encoder
As the human, we can recognize the places across a wide range of changing environmental conditions such as those caused by weathers, seasons, and day-night cycles. We excavate and memorize the stable semantic structure of different places and scenes. For example, we can recognize tree whether the ba...
Main Authors: | , , , |
---|---|
Format: | Report |
Language: | unknown |
Published: |
arXiv
2018
|
Subjects: | |
Online Access: | https://dx.doi.org/10.48550/arxiv.1806.11306 https://arxiv.org/abs/1806.11306 |
id |
ftdatacite:10.48550/arxiv.1806.11306 |
---|---|
record_format |
openpolar |
spelling |
ftdatacite:10.48550/arxiv.1806.11306 2023-05-15T17:24:39+02:00 Excavate Condition-invariant Space by Intrinsic Encoder Xu, Jian Wang, Chunheng Shi, Cunzhao Xiao, Baihua 2018 https://dx.doi.org/10.48550/arxiv.1806.11306 https://arxiv.org/abs/1806.11306 unknown arXiv arXiv.org perpetual, non-exclusive license http://arxiv.org/licenses/nonexclusive-distrib/1.0/ Computer Vision and Pattern Recognition cs.CV FOS Computer and information sciences Preprint Article article CreativeWork 2018 ftdatacite https://doi.org/10.48550/arxiv.1806.11306 2022-04-01T09:36:50Z As the human, we can recognize the places across a wide range of changing environmental conditions such as those caused by weathers, seasons, and day-night cycles. We excavate and memorize the stable semantic structure of different places and scenes. For example, we can recognize tree whether the bare tree in winter or lush tree in summer. Therefore, the intrinsic features that are corresponding to specific semantic contents and condition-invariant of appearance changes can be employed to improve the performance of long-term place recognition significantly. In this paper, we propose a novel intrinsic encoder that excavates the condition-invariant latent space of different places under drastic appearance changes. Our method excavates the space of intrinsic structure and semantic information by proposed self-supervised encoder loss. Different from previous learning based place recognition methods that need paired training data of each place with appearance changes, we employ the weakly-supervised strategy to utilize unpaired set-based training data of different environmental conditions. We conduct comprehensive experiments and show that our semi-supervised intrinsic encoder achieves remarkable performance for place recognition under drastic appearance changes. The proposed intrinsic encoder outperforms the state-of-the-art image-level place recognition methods on standard benchmark Nordland. : 10 pages, 5 figures Report Nordland Nordland Nordland 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 FOS Computer and information sciences |
spellingShingle |
Computer Vision and Pattern Recognition cs.CV FOS Computer and information sciences Xu, Jian Wang, Chunheng Shi, Cunzhao Xiao, Baihua Excavate Condition-invariant Space by Intrinsic Encoder |
topic_facet |
Computer Vision and Pattern Recognition cs.CV FOS Computer and information sciences |
description |
As the human, we can recognize the places across a wide range of changing environmental conditions such as those caused by weathers, seasons, and day-night cycles. We excavate and memorize the stable semantic structure of different places and scenes. For example, we can recognize tree whether the bare tree in winter or lush tree in summer. Therefore, the intrinsic features that are corresponding to specific semantic contents and condition-invariant of appearance changes can be employed to improve the performance of long-term place recognition significantly. In this paper, we propose a novel intrinsic encoder that excavates the condition-invariant latent space of different places under drastic appearance changes. Our method excavates the space of intrinsic structure and semantic information by proposed self-supervised encoder loss. Different from previous learning based place recognition methods that need paired training data of each place with appearance changes, we employ the weakly-supervised strategy to utilize unpaired set-based training data of different environmental conditions. We conduct comprehensive experiments and show that our semi-supervised intrinsic encoder achieves remarkable performance for place recognition under drastic appearance changes. The proposed intrinsic encoder outperforms the state-of-the-art image-level place recognition methods on standard benchmark Nordland. : 10 pages, 5 figures |
format |
Report |
author |
Xu, Jian Wang, Chunheng Shi, Cunzhao Xiao, Baihua |
author_facet |
Xu, Jian Wang, Chunheng Shi, Cunzhao Xiao, Baihua |
author_sort |
Xu, Jian |
title |
Excavate Condition-invariant Space by Intrinsic Encoder |
title_short |
Excavate Condition-invariant Space by Intrinsic Encoder |
title_full |
Excavate Condition-invariant Space by Intrinsic Encoder |
title_fullStr |
Excavate Condition-invariant Space by Intrinsic Encoder |
title_full_unstemmed |
Excavate Condition-invariant Space by Intrinsic Encoder |
title_sort |
excavate condition-invariant space by intrinsic encoder |
publisher |
arXiv |
publishDate |
2018 |
url |
https://dx.doi.org/10.48550/arxiv.1806.11306 https://arxiv.org/abs/1806.11306 |
genre |
Nordland Nordland Nordland |
genre_facet |
Nordland Nordland Nordland |
op_rights |
arXiv.org perpetual, non-exclusive license http://arxiv.org/licenses/nonexclusive-distrib/1.0/ |
op_doi |
https://doi.org/10.48550/arxiv.1806.11306 |
_version_ |
1766115761742413824 |