-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
279 changed files
with
3,502 additions
and
108 deletions.
There are no files selected for viewing
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,268 @@ | ||
<!DOCTYPE html> | ||
<html> | ||
|
||
<head> | ||
<!-- Required meta tags --> | ||
<meta charset="utf-8"> | ||
<meta name="description" content="Morphology-Aware Interactive Keypoint Esitmation"> | ||
<meta name="keywords" content="Morphology-Aware, InteractiveKeypointEstimation, Keypoint"> | ||
<meta name="viewport" content="width=device-width, initial-scale=1"> | ||
<title>Reversible Instance Normalization for Accurate Time-Series Forecasting against Distribution Shift</title> | ||
|
||
<!-- Bootstrap CSS --> | ||
<script async src="https://www.googletagmanager.com/gtag/js?id=G-PYVRSFMDRL"></script> | ||
<script> | ||
window.dataLayer = window.dataLayer || []; | ||
|
||
function gtag() { | ||
dataLayer.push(arguments); | ||
} | ||
|
||
gtag('js', new Date()); | ||
|
||
gtag('config', 'G-PYVRSFMDRL'); | ||
</script> | ||
|
||
<link href="https://fonts.googleapis.com/css?family=Google+Sans|Noto+Sans|Castoro" rel="stylesheet"> | ||
|
||
<link rel="stylesheet" href="./static/css/bulma.min.css"> | ||
<link rel="stylesheet" href="./static/css/bulma-carousel.min.css"> | ||
<link rel="stylesheet" href="./static/css/bulma-slider.min.css"> | ||
<link rel="stylesheet" href="./static/css/fontawesome.all.min.css"> | ||
<link rel="stylesheet" href="https://cdn.jsdelivr.net/gh/jpswalsh/academicons@1/css/academicons.min.css"> | ||
<link rel="stylesheet" href="./static/css/index.css"> | ||
<link rel="icon" href="./static/images/favicon.svg"> | ||
|
||
<script src="https://ajax.googleapis.com/ajax/libs/jquery/3.5.1/jquery.min.js"></script> | ||
<script defer src="./static/js/fontawesome.all.min.js"></script> | ||
<script src="./static/js/bulma-carousel.min.js"></script> | ||
<script src="./static/js/bulma-slider.min.js"></script> | ||
<script src="./static/js/index.js"></script> | ||
</head> | ||
|
||
<body> | ||
|
||
|
||
<section class="hero"> | ||
<div class="hero-body"> | ||
<div class="container is-max-desktop"> | ||
<div class="columns is-centered"> | ||
<div class="column has-text-centered"> | ||
<h1 class="title is-1 publication-title">Reversible Instance Normalization for Accurate Time-Series | ||
Forecasting against Distribution Shift</h1> | ||
<div class="is-size-5 publication-authors"> | ||
<span class="author-block"> | ||
<a href="https://www.linkedin.com/in/taesung-kim-142a53277">Taesung Kim*</a><sup>1</sup>, | ||
</span> | ||
<span class="author-block"> | ||
<a href="https://sites.google.com/view/jinhee-kim">Jinhee Kim*</a><sup>1</sup>, | ||
</span> | ||
<span class="author-block"> | ||
<a href="https://openreview.net/profile?id=~Yunwon_Tae1">Yunwon Tae</a><sup>2</sup>, | ||
</span> | ||
<span class="author-block"> | ||
<a href="https://cbokpark.github.io/">Cheonbok Park</a><sup>3</sup>, | ||
</span> | ||
<span class="author-block"> | ||
<a href="https://github.com/jangho87">Jang-Ho Choi</a><sup>4</sup>, | ||
</span> | ||
<span class="author-block"> | ||
<a href="https://sites.google.com/site/jaegulchoo/">Jaegul Choo</a><sup>1</sup> | ||
</span> | ||
</div> | ||
|
||
<div class="is-size-5 publication-authors"> | ||
<span class="author-block"><sup>1</sup>KAIST,</span> | ||
<span class="author-block"><sup>2</sup>VUNO,</span> | ||
<span class="author-block"><sup>3</sup>NAVER Corp.,</span> | ||
<span class="author-block"><sup>4</sup>ETRI</span> | ||
</div> | ||
<center> | ||
<p>*Both authors contributed equally.</p> | ||
</center> | ||
|
||
<div class="column has-text-centered"> | ||
<div class="publication-links"> | ||
<!-- PDF Link. --> | ||
<span class="link-block"> | ||
<a href="https://openreview.net/forum?id=cGDAkQo1C0p" | ||
class="external-link button is-normal is-rounded is-dark"> | ||
<span class="icon"> | ||
<i class="fas fa-file-pdf"></i> | ||
</span> | ||
<span>Paper</span> | ||
</a> | ||
</span> | ||
<!-- Code Link. --> | ||
<span class="link-block"> | ||
<a href="https://github.com/ts-kim/revin/" class="external-link button is-normal is-rounded is-dark"> | ||
<span class="icon"> | ||
<i class="fab fa-github"></i> | ||
</span> | ||
<span>Code</span> | ||
</a> | ||
</span> | ||
</div> | ||
</div> | ||
|
||
<center> | ||
<img src="./ICLR-logo.svg" class="figure-img img-fluid" alt="Responsive image" style="margin:0px 0px;"> | ||
</center> | ||
|
||
|
||
</div> | ||
</div> | ||
</div> | ||
</div> | ||
</section> | ||
|
||
|
||
|
||
<section class="hero teaser"></section> | ||
<div class="container is-max-desktop"> | ||
<div class="hero-body"> | ||
<img src="./figs/fig1.gif" class="figure-img img-fluid" alt="Responsive image" style="margin:20px 0px;"> | ||
</div> | ||
</div> | ||
</section> | ||
|
||
<section class="section"></section> | ||
<div class="container is-max-desktop"> | ||
<!-- Abstract. --> | ||
<div class="columns is-centered has-text-centered"> | ||
<div class="column is-four-fifths"> | ||
<h2 class="title is-3">Abstract</h2> | ||
<div class="content has-text-justified"> | ||
<p> | ||
Statistical properties such as mean and variance often change over time in time series, | ||
i.e., time-series data suffer from a distribution shift problem. This change in temporal | ||
distribution is one of the main challenges that prevent accurate time-series forecasting. | ||
To address this issue, we propose a simple yet effective normalization method called reversible | ||
instance normalization (RevIN), a generally applicable normalization-and-denormalization method with | ||
learnable affine transformation. The proposed method is symmetrically structured to remove and restore the | ||
statistical information of a time-series instance, leading to significant performance improvements in | ||
time-series forecasting, as shown in Fig. 1. We demonstrate the effectiveness of RevIN via extensive | ||
quantitative and qualitative analyses on various real-world datasets, addressing the distribution shift | ||
problem. | ||
</p> | ||
</div> | ||
</div> | ||
</div> | ||
<!--/ Abstract. --> | ||
</div> | ||
</section> | ||
|
||
<div class="container is-max-desktop"> | ||
<div class="columns is-centered"> | ||
<div class="column"> | ||
<div class="content"> | ||
<h2 class="title is-3">Poster</h2> | ||
<center> | ||
<figure class="figure"> | ||
<img src="./figs/RevIN_Poster_ICLR_2O22.jpg" class="figure-img img-fluid" alt="Responsive image" | ||
style="margin:20px;"> | ||
</figure> | ||
</center> | ||
</div> | ||
</div> | ||
</div> | ||
</div> | ||
</section> | ||
|
||
|
||
|
||
<section class="section"> | ||
<!-- Supplement matarials --> | ||
<div class="container is-max-desktop"> | ||
<div class="columns is-centered"> | ||
<div class="column"> | ||
<div class="content"> | ||
|
||
<h2 class="title is-3">Experimental Results</h2> | ||
<div class="content has-text-justified"> | ||
<p> | ||
RevIN can alleviate the distribution discrepancy problem by removing | ||
non-stationary information in the input layer and then restoring it in the output layer. The | ||
analysis is conducted on the ETT and ECL datasets using SCINet (Liu et al., 2021) as the baseline. | ||
</p> | ||
</div> | ||
|
||
<center> | ||
<figure class="figure"> | ||
<img src="./figs/fig3.PNG" class="figure-img img-fluid" alt="Responsive image" style="margin:20px;"> | ||
</figure> | ||
</center> | ||
|
||
<div class="content has-text-justified"> | ||
<p> | ||
These are prediction results on three variables in the Nasdaq data, | ||
Close, DTB6, and DE1, to verify the effectiveness | ||
of RevIN on obvious non-stationary time series. | ||
</p> | ||
</div> | ||
|
||
<center> | ||
<figure class="figure"> | ||
<img src="./figs/fig6.PNG" class="figure-img img-fluid" alt="Responsive image" style="margin:20px;"> | ||
</figure> | ||
</center> | ||
|
||
<div class="content has-text-justified"></div> | ||
<p> | ||
Additional multivariate time-series forecasting results. | ||
</p> | ||
</div> | ||
|
||
<center> | ||
<figure class="figure"> | ||
<img src="./figs/fig9.jpg" class="figure-img img-fluid" alt="Responsive image" style="margin:20px;"> | ||
</figure> | ||
</center> | ||
|
||
|
||
</div> | ||
</div> | ||
</div> | ||
</div> | ||
<!--/ Supplement matarials --> | ||
|
||
|
||
|
||
<section class="section" id="BibTeX"> | ||
<div class="container is-max-desktop content"> | ||
<h2 class="title">BibTeX</h2> | ||
<pre><code>@inproceedings{ | ||
kim2022reversible, | ||
title={Reversible Instance Normalization for Accurate Time-Series Forecasting against Distribution Shift}, | ||
author={Taesung Kim and | ||
Jinhee Kim and | ||
Yunwon Tae and | ||
Cheonbok Park and | ||
Jang-Ho Choi and | ||
Jaegul Choo}, | ||
booktitle={International Conference on Learning Representations}, | ||
year={2022}, | ||
url={https://openreview.net/forum?id=cGDAkQo1C0p} | ||
}</code></pre> | ||
</div> | ||
</section> | ||
|
||
|
||
<footer class="footer"> | ||
<div class="container"> | ||
<div class="columns is-centered"> | ||
<div class="column is-8"> | ||
<div class="content"> | ||
<p> | ||
The page template is based on <a href="https://github.com/nerfies/nerfies.github.io">Nerfies GitHub | ||
repository</a> source code. | ||
</p> | ||
</div> | ||
</div> | ||
</div> | ||
</div> | ||
</footer> | ||
|
||
</body> | ||
|
||
</html> |
Oops, something went wrong.