| CARVIEW |
Select Language
HTTP/2 200
x-frame-options: SAMEORIGIN
server: Google Frontend
via: 1.1 google, 1.1 varnish, 1.1 varnish, 1.1 varnish
last-modified: Wed, 05 Dec 2018 01:10:54 GMT
x-cloud-trace-context: fe2906ba7ee9997c19577a900694893c
cache-control: max-age=3600
content-type: text/html; charset=utf-8
content-security-policy: frame-ancestors 'none'
accept-ranges: bytes
age: 160970
date: Wed, 31 Dec 2025 22:43:40 GMT
x-served-by: cache-lga21983-LGA, cache-lga21942-LGA, cache-bom-vanm7210042-BOM
x-cache: MISS, HIT, MISS
x-timer: S1767221020.391207,VS0,VE221
content-length: 45741
[1812.01285] Rare Event Detection using Disentangled Representation Learning
Skip to main content
We gratefully acknowledge support from the Simons Foundation, member institutions, and all contributors.
Donate
Computer Science > Computer Vision and Pattern Recognition
arXiv:1812.01285 (cs)
[Submitted on 4 Dec 2018]
Title:Rare Event Detection using Disentangled Representation Learning
View a PDF of the paper titled Rare Event Detection using Disentangled Representation Learning, by Ryuhei Hamaguchi and 2 other authors
View PDF
Abstract:This paper presents a novel method for rare event detection from an image pair with class-imbalanced datasets. A straightforward approach for event detection tasks is to train a detection network from a large-scale dataset in an end-to-end manner. However, in many applications such as building change detection on satellite images, few positive samples are available for the training. Moreover, scene image pairs contain many trivial events, such as in illumination changes or background motions. These many trivial events and the class imbalance problem lead to false alarms for rare event detection. In order to overcome these difficulties, we propose a novel method to learn disentangled representations from only low-cost negative samples. The proposed method disentangles different aspects in a pair of observations: variant and invariant factors that represent trivial events and image contents, respectively. The effectiveness of the proposed approach is verified by the quantitative evaluations on four change detection datasets, and the qualitative analysis shows that the proposed method can acquire the representations that disentangle rare events from trivial ones.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV) |
| Cite as: | arXiv:1812.01285 [cs.CV] |
| (or arXiv:1812.01285v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.1812.01285
arXiv-issued DOI via DataCite
|
Full-text links:
Access Paper:
- View PDF
- TeX Source
View a PDF of the paper titled Rare Event Detection using Disentangled Representation Learning, by Ryuhei Hamaguchi and 2 other authors
References & Citations
export BibTeX citation
Loading...
Bibliographic and Citation Tools
Bibliographic Explorer (What is the Explorer?)
Connected Papers (What is Connected Papers?)
Litmaps (What is Litmaps?)
scite Smart Citations (What are Smart Citations?)
Code, Data and Media Associated with this Article
alphaXiv (What is alphaXiv?)
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub (What is DagsHub?)
Gotit.pub (What is GotitPub?)
Hugging Face (What is Huggingface?)
Papers with Code (What is Papers with Code?)
ScienceCast (What is ScienceCast?)
Demos
Recommenders and Search Tools
Influence Flower (What are Influence Flowers?)
CORE Recommender (What is CORE?)
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.