Spaces:

TrustSafeAI
/

NeuralFuse

Running

App Files Files Community

hsiung commited on Oct 26, 2024

Commit

a767b82

1 Parent(s): ccf396a

initial commit

Browse files

Signed-off-by: Lei Hsiung <leihsiung.ray@gmail.com>

This view is limited to 50 files because it contains too many changes. See raw diff

Files changed (50) hide show

README.md +1 -1
index.html +65 -280
static/css/index.css +24 -1
static/images/favicon.svg +0 -37
static/images/favicon/android-chrome-192x192.png +0 -0
static/images/favicon/android-chrome-512x512.png +0 -0
static/images/favicon/apple-touch-icon.png +0 -0
static/images/favicon/favicon-16x16.png +0 -0
static/images/favicon/favicon-32x32.png +0 -0
static/images/favicon/favicon.ico +0 -0
static/images/favicon/site.webmanifest +1 -0
static/images/interpolate_end.jpg +0 -0
static/images/interpolate_start.jpg +0 -0
static/images/performance.png +0 -0
static/images/steve.webm +0 -3
static/images/teaser.png +0 -0
static/interpolation/stacked/000000.jpg +0 -0
static/interpolation/stacked/000001.jpg +0 -0
static/interpolation/stacked/000002.jpg +0 -0
static/interpolation/stacked/000003.jpg +0 -0
static/interpolation/stacked/000004.jpg +0 -0
static/interpolation/stacked/000005.jpg +0 -0
static/interpolation/stacked/000006.jpg +0 -0
static/interpolation/stacked/000007.jpg +0 -0
static/interpolation/stacked/000008.jpg +0 -0
static/interpolation/stacked/000009.jpg +0 -0
static/interpolation/stacked/000010.jpg +0 -0
static/interpolation/stacked/000011.jpg +0 -0
static/interpolation/stacked/000012.jpg +0 -0
static/interpolation/stacked/000013.jpg +0 -0
static/interpolation/stacked/000014.jpg +0 -0
static/interpolation/stacked/000015.jpg +0 -0
static/interpolation/stacked/000016.jpg +0 -0
static/interpolation/stacked/000017.jpg +0 -0
static/interpolation/stacked/000018.jpg +0 -0
static/interpolation/stacked/000019.jpg +0 -0
static/interpolation/stacked/000020.jpg +0 -0
static/interpolation/stacked/000021.jpg +0 -0
static/interpolation/stacked/000022.jpg +0 -0
static/interpolation/stacked/000023.jpg +0 -0
static/interpolation/stacked/000024.jpg +0 -0
static/interpolation/stacked/000025.jpg +0 -0
static/interpolation/stacked/000026.jpg +0 -0
static/interpolation/stacked/000027.jpg +0 -0
static/interpolation/stacked/000028.jpg +0 -0
static/interpolation/stacked/000029.jpg +0 -0
static/interpolation/stacked/000030.jpg +0 -0
static/interpolation/stacked/000031.jpg +0 -0
static/interpolation/stacked/000032.jpg +0 -0
static/interpolation/stacked/000033.jpg +0 -0

README.md CHANGED Viewed

@@ -1,5 +1,5 @@
 ---
-title: "Nerfies: Deformable Neural Radiance Fields"
 emoji: 🧠
 colorFrom: yellow
 colorTo: indigo

 ---
+title: NeuralFuse
 emoji: 🧠
 colorFrom: yellow
 colorTo: indigo

index.html CHANGED Viewed

@@ -3,10 +3,10 @@
 <head>
   <meta charset="utf-8">
   <meta name="description"
-        content="Deformable Neural Radiance Fields creates free-viewpoint portraits (nerfies) from casually captured videos.">
-  <meta name="keywords" content="Nerfies, D-NeRF, NeRF">
   <meta name="viewport" content="width=device-width, initial-scale=1">
-  <title>Nerfies: Deformable Neural Radiance Fields</title>
   <link href="https://fonts.googleapis.com/css?family=Google+Sans|Noto+Sans|Castoro"
         rel="stylesheet">
@@ -18,7 +18,10 @@
   <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>
@@ -33,48 +36,35 @@
     <div class="container is-max-desktop">
       <div class="columns is-centered">
         <div class="column has-text-centered">
-          <h1 class="title is-1 publication-title">Nerfies: Deformable Neural Radiance Fields</h1>
           <div class="is-size-5 publication-authors">
             <span class="author-block">
-              <a href="https://keunhong.com" target="_blank">Keunhong Park</a><sup>1</sup>,</span>
             <span class="author-block">
-              <a href="https://utkarshsinha.com" target="_blank">Utkarsh Sinha</a><sup>2</sup>,</span>
             <span class="author-block">
-              <a href="https://jonbarron.info" target="_blank">Jonathan T. Barron</a><sup>2</sup>,
             </span>
             <span class="author-block">
-              <a href="http://sofienbouaziz.com" target="_blank">Sofien Bouaziz</a><sup>2</sup>,
             </span>
             <span class="author-block">
-              <a href="https://www.danbgoldman.com" target="_blank">Dan B Goldman</a><sup>2</sup>,
-            </span>
-            <span class="author-block">
-              <a href="https://homes.cs.washington.edu/~seitz/" target="_blank">Steven M. Seitz</a><sup>1,2</sup>,
-            </span>
-            <span class="author-block">
-              <a href="http://www.ricardomartinbrualla.com" target="_blank">Ricardo Martin-Brualla</a><sup>2</sup>
             </span>
           </div>
           <div class="is-size-5 publication-authors">
-            <span class="author-block"><sup>1</sup>University of Washington,</span>
-            <span class="author-block"><sup>2</sup>Google Research</span>
           </div>
           <div class="column has-text-centered">
             <div class="publication-links">
-              <!-- PDF Link. -->
-              <span class="link-block">
-                <a href="https://arxiv.org/pdf/2011.12948" target="_blank"
-                   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>
               <span class="link-block">
-                <a href="https://arxiv.org/abs/2011.12948" target="_blank"
                    class="external-link button is-normal is-rounded is-dark">
                   <span class="icon">
                       <i class="ai ai-arxiv"></i>
@@ -82,19 +72,9 @@
                   <span>arXiv</span>
                 </a>
               </span>
-              <!-- Video Link. -->
-              <span class="link-block">
-                <a href="https://www.youtube.com/watch?v=MrKrnHhk8IA" target="_blank"
-                   class="external-link button is-normal is-rounded is-dark">
-                  <span class="icon">
-                      <i class="fab fa-youtube"></i>
-                  </span>
-                  <span>Video</span>
-                </a>
-              </span>
               <!-- Code Link. -->
               <span class="link-block">
-                <a href="https://github.com/google/nerfies" target="_blank"
                    class="external-link button is-normal is-rounded is-dark">
                   <span class="icon">
                       <i class="fab fa-github"></i>
@@ -102,15 +82,6 @@
                   <span>Code</span>
                   </a>
               </span>
-              <!-- Dataset Link. -->
-              <span class="link-block">
-                <a href="https://github.com/google/nerfies/releases/tag/0.1" target="_blank"
-                   class="external-link button is-normal is-rounded is-dark">
-                  <span class="icon">
-                      <i class="far fa-images"></i>
-                  </span>
-                  <span>Data</span>
-                  </a>
             </div>
           </div>
@@ -123,78 +94,17 @@
 <section class="hero teaser">
   <div class="container is-max-desktop">
     <div class="hero-body">
-      <video id="teaser" autoplay muted loop playsinline height="100%">
-        <source src="./static/videos/teaser.mp4"
-                type="video/mp4">
-      </video>
       <h2 class="subtitle has-text-centered">
-        <span class="dnerf">Nerfies</span> turns selfie videos from your phone into
-        free-viewpoint
-        portraits.
       </h2>
     </div>
   </div>
 </section>
-<section class="hero is-light is-small">
-  <div class="hero-body">
-    <div class="container">
-      <div id="results-carousel" class="carousel results-carousel">
-        <div class="item item-steve">
-          <video poster="" id="steve" autoplay controls muted loop playsinline height="100%">
-            <source src="./static/videos/steve.mp4"
-                    type="video/mp4">
-          </video>
-        </div>
-        <div class="item item-chair-tp">
-          <video poster="" id="chair-tp" autoplay controls muted loop playsinline height="100%">
-            <source src="./static/videos/chair-tp.mp4"
-                    type="video/mp4">
-          </video>
-        </div>
-        <div class="item item-shiba">
-          <video poster="" id="shiba" autoplay controls muted loop playsinline height="100%">
-            <source src="./static/videos/shiba.mp4"
-                    type="video/mp4">
-          </video>
-        </div>
-        <div class="item item-fullbody">
-          <video poster="" id="fullbody" autoplay controls muted loop playsinline height="100%">
-            <source src="./static/videos/fullbody.mp4"
-                    type="video/mp4">
-          </video>
-        </div>
-        <div class="item item-blueshirt">
-          <video poster="" id="blueshirt" autoplay controls muted loop playsinline height="100%">
-            <source src="./static/videos/blueshirt.mp4"
-                    type="video/mp4">
-          </video>
-        </div>
-        <div class="item item-mask">
-          <video poster="" id="mask" autoplay controls muted loop playsinline height="100%">
-            <source src="./static/videos/mask.mp4"
-                    type="video/mp4">
-          </video>
-        </div>
-        <div class="item item-coffee">
-          <video poster="" id="coffee" autoplay controls muted loop playsinline height="100%">
-            <source src="./static/videos/coffee.mp4"
-                    type="video/mp4">
-          </video>
-        </div>
-        <div class="item item-toby">
-          <video poster="" id="toby" autoplay controls muted loop playsinline height="100%">
-            <source src="./static/videos/toby2.mp4"
-                    type="video/mp4">
-          </video>
-        </div>
-      </div>
-    </div>
-  </div>
-</section>
 <section class="section">
   <div class="container is-max-desktop">
     <!-- Abstract. -->
@@ -203,185 +113,68 @@
         <h2 class="title is-3">Abstract</h2>
         <div class="content has-text-justified">
           <p>
-            We present the first method capable of photorealistically reconstructing a non-rigidly
-            deforming scene using photos/videos captured casually from mobile phones.
-          </p>
-          <p>
-            Our approach augments neural radiance fields
-            (NeRF) by optimizing an
-            additional continuous volumetric deformation field that warps each observed point into a
-            canonical 5D NeRF.
-            We observe that these NeRF-like deformation fields are prone to local minima, and
-            propose a coarse-to-fine optimization method for coordinate-based models that allows for
-            more robust optimization.
-            By adapting principles from geometry processing and physical simulation to NeRF-like
-            models, we propose an elastic regularization of the deformation field that further
-            improves robustness.
           </p>
           <p>
-            We show that <span class="dnerf">Nerfies</span> can turn casually captured selfie
-            photos/videos into deformable NeRF
-            models that allow for photorealistic renderings of the subject from arbitrary
-            viewpoints, which we dub <i>"nerfies"</i>. We evaluate our method by collecting data
-            using a
-            rig with two mobile phones that take time-synchronized photos, yielding train/validation
-            images of the same pose at different viewpoints. We show that our method faithfully
-            reconstructs non-rigidly deforming scenes and reproduces unseen views with high
-            fidelity.
           </p>
         </div>
       </div>
     </div>
     <!--/ Abstract. -->
-    <!-- Paper video. -->
-    <div class="columns is-centered has-text-centered">
-      <div class="column is-four-fifths">
-        <h2 class="title is-3">Video</h2>
-        <div class="publication-video">
-          <iframe src="https://www.youtube.com/embed/MrKrnHhk8IA?rel=0&amp;showinfo=0"
-                  frameborder="0" allow="autoplay; encrypted-media" allowfullscreen></iframe>
-        </div>
-      </div>
-    </div>
-    <!--/ Paper video. -->
   </div>
 </section>
 <section class="section">
   <div class="container is-max-desktop">
-    <div class="columns is-centered">
-      <!-- Visual Effects. -->
-      <div class="column">
-        <div class="content">
-          <h2 class="title is-3">Visual Effects</h2>
-          <p>
-            Using <i>nerfies</i> you can create fun visual effects. This Dolly zoom effect
-            would be impossible without nerfies since it would require going through a wall.
-          </p>
-          <video id="dollyzoom" autoplay controls muted loop playsinline height="100%">
-            <source src="./static/videos/dollyzoom-stacked.mp4"
-                    type="video/mp4">
-          </video>
-        </div>
-      </div>
-      <!--/ Visual Effects. -->
-      <!-- Matting. -->
-      <div class="column">
-        <h2 class="title is-3">Matting</h2>
-        <div class="columns is-centered">
-          <div class="column content">
-            <p>
-              As a byproduct of our method, we can also solve the matting problem by ignoring
-              samples that fall outside of a bounding box during rendering.
-            </p>
-            <video id="matting-video" controls playsinline height="100%">
-              <source src="./static/videos/matting.mp4"
-                      type="video/mp4">
-            </video>
-          </div>
-        </div>
-      </div>
-    </div>
-    <!--/ Matting. -->
-    <!-- Animation. -->
     <div class="columns is-centered">
       <div class="column is-full-width">
-        <h2 class="title is-3">Animation</h2>
-        <!-- Interpolating. -->
-        <h3 class="title is-4">Interpolating states</h3>
-        <div class="content has-text-justified">
-          <p>
-            We can also animate the scene by interpolating the deformation latent codes of two input
-            frames. Use the slider here to linearly interpolate between the left frame and the right
-            frame.
           </p>
         </div>
-        <div class="columns is-vcentered interpolation-panel">
-          <div class="column is-3 has-text-centered">
-            <img src="./static/images/interpolate_start.jpg"
-                 class="interpolation-image"
-                 alt="Interpolate start reference image."/>
-            <p>Start Frame</p>
-          </div>
-          <div class="column interpolation-video-column">
-            <div id="interpolation-image-wrapper">
-              Loading...
-            </div>
-            <input class="slider is-fullwidth is-large is-info"
-                   id="interpolation-slider"
-                   step="1" min="0" max="100" value="0" type="range">
-          </div>
-          <div class="column is-3 has-text-centered">
-            <img src="./static/images/interpolate_end.jpg"
-                 class="interpolation-image"
-                 alt="Interpolation end reference image."/>
-            <p class="is-bold">End Frame</p>
-          </div>
         </div>
-        <br/>
-        <!--/ Interpolating. -->
-        <!-- Re-rendering. -->
-        <h3 class="title is-4">Re-rendering the input video</h3>
-        <div class="content has-text-justified">
-          <p>
-            Using <span class="dnerf">Nerfies</span>, you can re-render a video from a novel
-            viewpoint such as a stabilized camera by playing back the training deformations.
           </p>
         </div>
-        <div class="content has-text-centered">
-          <video id="replay-video"
-                 controls
-                 muted
-                 preload
-                 playsinline
-                 width="75%">
-            <source src="./static/videos/replay.mp4"
-                    type="video/mp4">
-          </video>
         </div>
-        <!--/ Re-rendering. -->
       </div>
-    </div>
-    <!--/ Animation. -->
-    <!-- Concurrent Work. -->
     <div class="columns is-centered">
       <div class="column is-full-width">
-        <h2 class="title is-3">Related Links</h2>
         <div class="content has-text-justified">
           <p>
-            There's a lot of excellent work that was introduced around the same time as ours.
-          </p>
-          <p>
-            <a href="https://arxiv.org/abs/2104.09125" target="_blank">Progressive Encoding for Neural Optimization</a> introduces an idea similar to our windowed position encoding for coarse-to-fine optimization.
-          </p>
-          <p>
-            <a href="https://www.albertpumarola.com/research/D-NeRF/index.html" target="_blank">D-NeRF</a> and <a href="https://gvv.mpi-inf.mpg.de/projects/nonrigid_nerf/" target="_blank">NR-NeRF</a>
-            both use deformation fields to model non-rigid scenes.
-          </p>
-          <p>
-            Some works model videos with a NeRF by directly modulating the density, such as <a href="https://video-nerf.github.io/" target="_blank">Video-NeRF</a>, <a href="https://www.cs.cornell.edu/~zl548/NSFF/" target="_blank">NSFF</a>, and <a href="https://neural-3d-video.github.io/" target="_blank">DyNeRF</a>
-          </p>
-          <p>
-            There are probably many more by the time you are reading this. Check out <a href="https://dellaert.github.io/NeRF/" target="_blank">Frank Dellart's survey on recent NeRF papers</a>, and <a href="https://github.com/yenchenlin/awesome-NeRF" target="_blank">Yen-Chen Lin's curated list of NeRF papers</a>.
           </p>
         </div>
-      </div>
-    </div>
-    <!--/ Concurrent Work. -->
   </div>
 </section>
@@ -389,11 +182,13 @@
 <section class="section" id="BibTeX">
   <div class="container is-max-desktop content">
     <h2 class="title">BibTeX</h2>
-    <pre><code>@article{park2021nerfies,
-  author    = {Park, Keunhong and Sinha, Utkarsh and Barron, Jonathan T. and Bouaziz, Sofien and Goldman, Dan B and Seitz, Steven M. and Martin-Brualla, Ricardo},
-  title     = {Nerfies: Deformable Neural Radiance Fields},
-  journal   = {ICCV},
-  year      = {2021},
 }</code></pre>
   </div>
 </section>
@@ -402,11 +197,10 @@
 <footer class="footer">
   <div class="container">
     <div class="content has-text-centered">
-      <a class="icon-link" target="_blank"
-         href="./static/videos/nerfies_paper.pdf">
         <i class="fas fa-file-pdf"></i>
       </a>
-      <a class="icon-link" href="https://github.com/keunhong" target="_blank" class="external-link" disabled>
         <i class="fab fa-github"></i>
       </a>
     </div>
@@ -414,16 +208,7 @@
       <div class="column is-8">
         <div class="content">
           <p>
-            This website is licensed under a <a rel="license" target="_blank"
-                                                href="http://creativecommons.org/licenses/by-sa/4.0/">Creative
-            Commons Attribution-ShareAlike 4.0 International License</a>.
-          </p>
-          <p>
-            This means you are free to borrow the <a target="_blank"
-              href="https://github.com/nerfies/nerfies.github.io">source code</a> of this website,
-            we just ask that you link back to this page in the footer.
-            Please remember to remove the analytics code included in the header of the website which
-            you do not want on your website.
           </p>
         </div>
       </div>

 <head>
   <meta charset="utf-8">
   <meta name="description"
+        content="NeuralFuse provides model-independent protection for AI accelerators built on a chip, allowing them to maintain stable performance when suffering low-voltage-induced bit errors.">
+  <meta name="keywords" content="machine learning, energy efficient inference, bit error resilience">
   <meta name="viewport" content="width=device-width, initial-scale=1">
+  <title>NeuralFuse: Learning to Recover the Accuracy of Access-Limited Neural Network Inference in Low-Voltage Regimes</title>
   <link href="https://fonts.googleapis.com/css?family=Google+Sans|Noto+Sans|Castoro"
         rel="stylesheet">
   <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="apple-touch-icon" sizes="180x180" href="./static/images/favicon/apple-touch-icon.png">
+  <link rel="icon" type="image/png" sizes="32x32" href="./static/images/favicon/favicon-32x32.png">
+  <link rel="icon" type="image/png" sizes="16x16" href="./static/images/favicon/favicon-16x16.png">
+  <link rel="manifest" href="./static/images/favicon/site.webmanifest">
   <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>
     <div class="container is-max-desktop">
       <div class="columns is-centered">
         <div class="column has-text-centered">
+          <h1 class="title is-1 publication-title">✨NeuralFuse✨</h1>
+          <h1 class="title publication-subtitle">Learning to Recover the Accuracy of Access-Limited Neural Network Inference in Low-Voltage Regimes</h1>
           <div class="is-size-5 publication-authors">
             <span class="author-block">
+              <a href="https://scholar.google.com/citations?user=g2MolmMAAAAJ&hl=en" target="_blank">Hao-Lun Sun</a><sup>1</sup>,</span>
             <span class="author-block">
+              <a href="https://hsiung.cc" target="_blank">Lei Hsiung</a><sup>2</sup>,</span>
             <span class="author-block">
+              <a href="https://scholar.google.com/citations?user=qurg568AAAAJ&hl=en" target="_blank">Nandhini Chandramoorthy</a><sup>3</sup>,
             </span>
             <span class="author-block">
+              <a href="https://sites.google.com/site/pinyuchenpage/home" target="_blank">Pin-Yu Chen</a><sup>3</sup>,
             </span>
             <span class="author-block">
+              <a href="https://tsungyiho.github.io" target="_blank">Tsung-Yi Ho</a><sup>4</sup>,
             </span>
           </div>
           <div class="is-size-5 publication-authors">
+            <span class="author-block"><sup>1</sup>National Tsing Hua University</span>
+            <span class="author-block"><sup>2</sup>Dartmouth College</span>
+            <span class="author-block"><sup>3</sup>IBM Research</span>
+            <span class="author-block"><sup>4</sup>CUHK</span>
           </div>
           <div class="column has-text-centered">
             <div class="publication-links">
               <span class="link-block">
+                <a href="https://arxiv.org/abs/2306.16869" target="_blank"
                    class="external-link button is-normal is-rounded is-dark">
                   <span class="icon">
                       <i class="ai ai-arxiv"></i>
                   <span>arXiv</span>
                 </a>
               </span>
               <!-- Code Link. -->
               <span class="link-block">
+                <a href="https://github.com/IBM/NeuralFuse" target="_blank"
                    class="external-link button is-normal is-rounded is-dark">
                   <span class="icon">
                       <i class="fab fa-github"></i>
                   <span>Code</span>
                   </a>
               </span>
             </div>
           </div>
 <section class="hero teaser">
   <div class="container is-max-desktop">
     <div class="hero-body">
+      <img id="teaser" src="./static/images/teaser.png"
+           class=""
+           alt="NeuralFuse Teaser"/>
       <h2 class="subtitle has-text-centered">
+        The pipeline of the <span class="small_caps">NeuralFuse</span> framework at inference.
       </h2>
     </div>
   </div>
 </section>
 <section class="section">
   <div class="container is-max-desktop">
     <!-- Abstract. -->
         <h2 class="title is-3">Abstract</h2>
         <div class="content has-text-justified">
           <p>
+            Deep neural networks (DNNs) have become ubiquitous in machine learning, but their energy consumption remains problematically high. An effective strategy for reducing such consumption is supply-voltage reduction, but if done too aggressively, it can lead to accuracy degradation. This is due to random bit-flips in static random access memory (SRAM), where model parameters are stored.
           </p>
           <p>
+            To address this challenge, we have developed <span class="small_caps">NeuralFuse</span>, a novel add-on module that handles the energy-accuracy tradeoff in low-voltage regimes by learning input transformations and using them to generate error-resistant data representations, thereby protecting DNN accuracy in both nominal and low-voltage scenarios. As well as being easy to implement, NeuralFuse can be readily applied to DNNs with limited access, such cloud-based APIs that are accessed remotely or non-configurable hardware. Our experimental results demonstrate that, at a 1% bit-error rate, NeuralFuse can reduce SRAM access energy by up to 24% while recovering accuracy by up to 57%. To the best of our knowledge, this is the first approach to addressing low-voltage-induced bit errors that requires no model retraining.
           </p>
         </div>
       </div>
     </div>
     <!--/ Abstract. -->
   </div>
 </section>
 <section class="section">
   <div class="container is-max-desktop">
     <div class="columns is-centered">
       <div class="column is-full-width">
+        <h2 class="title is-3">Our Contributions</h2>
+        <div class="content has-text-justified highlight-box">
+          <p><span class="contribution-subtitle">Boosts DNN Accuracy Under Low Power</span>
+              <span class="small_caps">NeuralFuse</span> improves the accuracy of deep neural networks (DNNs) operating in low-power environments with random bit errors, without needing to retrain the models.
           </p>
         </div>
+        <div class="content has-text-justified highlight-box">
+          <p><span class="contribution-subtitle">Protects DNN Accuracy Under Unstable Power</span>
+              <span class="small_caps">NeuralFuse</span> improves the accuracy of deep neural networks (DNNs) operating in low-power environments with random bit errors, without needing to retrain the models.
+          </p>
         </div>
+        <div class="content has-text-justified highlight-box">
+          <p><span class="contribution-subtitle">Adapts to Limited-Access Settings</span>
+               <span class="small_caps">NeuralFuse</span> supports deployment in scenarios with limited access to model details, using flexible training methods to adapt effectively across diverse DNN architectures.
           </p>
         </div>
+        <div class="content has-text-justified highlight-box">
+          <p><span class="contribution-subtitle">Reduces Energy Use with Proven Performance</span>
+              <span class="small_caps">NeuralFuse</span> recovers up to 57% of lost accuracy and reduces memory access energy by up to 24%, tested across diverse models (ResNet18, ResNet50, VGG11, VGG16, and VGG19) and datasets (CIFAR-10, CIFAR-100, GTSRB, and ImageNet-10).
+          </p>
         </div>
       </div>
+    </div>
+  </div>
+</section>
+<section class="section">
+  <div class="container is-max-desktop">
     <div class="columns is-centered">
       <div class="column is-full-width">
+        <h2 class="title is-3">NeuralFuse Performance</h2>
+        <h3 class="title is-4">Energy/Accuracy Tradeoff</h3>
         <div class="content has-text-justified">
           <p>
+            On the same base model (ResNet18), we illustrate the energy/accuracy tradeoff of six NeuralFuse implementations.
+The x-axis represents the percentage reduction in dynamic-memory access energy at low-voltage settings (base model protected by NeuralFuse), as compared to the bit-error-free (nominal) voltage. The y-axis represents the perturbed accuracy (evaluated at low voltage) with a 1% bit-error rate.
           </p>
         </div>
+        <img id="performance" src="./static/images/performance.png"
+             class=""
+             alt="NeuralFuse Performance"/>
+      </div>
+    </div>
   </div>
 </section>
 <section class="section" id="BibTeX">
   <div class="container is-max-desktop content">
     <h2 class="title">BibTeX</h2>
+    <pre><code>@inproceedings{sun2024neuralfuse,
+  title={{NeuralFuse: Learning to Recover the Accuracy of Access-Limited Neural Network Inference in Low-Voltage Regimes}},
+  author={Hao-Lun Sun and Lei Hsiung and Nandhini Chandramoorthy and Pin-Yu Chen and Tsung-Yi Ho},
+  booktitle = {Advances in Neural Information Processing Systems},
+  publisher = {Curran Associates, Inc.},
+  volume = {37},
+  year = {2024}
 }</code></pre>
   </div>
 </section>
 <footer class="footer">
   <div class="container">
     <div class="content has-text-centered">
+      <a class="icon-link" href="https://arxiv.org/abs/2306.16869" target="_blank" class="external-link">
         <i class="fas fa-file-pdf"></i>
       </a>
+      <a class="icon-link" href="https://github.com/IBM/NeuralFuse" target="_blank" class="external-link">
         <i class="fab fa-github"></i>
       </a>
     </div>
       <div class="column is-8">
         <div class="content">
           <p>
+            This page is maintained by <a target="_blank" href="https://hsiung.cc">Lei Hsiung</a>. Page template is borrowed from <a target="_blank" rel="nofollow" href="https://github.com/nerfies/nerfies.github.io">here</a>.
           </p>
         </div>
       </div>

static/css/index.css CHANGED Viewed

@@ -13,7 +13,7 @@ body {
     margin-bottom: 5px;
 }
-.dnerf {
   font-variant: small-caps;
 }
@@ -31,6 +31,10 @@ body {
 .publication-title {
 }
 .publication-banner {
   max-height: parent;
@@ -155,3 +159,22 @@ body {
 #interpolation-image-wrapper img {
   border-radius: 5px;
 }

     margin-bottom: 5px;
 }
+.small_caps {
   font-variant: small-caps;
 }
 .publication-title {
 }
+.publication-subtitle {
+  font-size: 1.25em;
+}
 .publication-banner {
   max-height: parent;
 #interpolation-image-wrapper img {
   border-radius: 5px;
 }
+.contribution-subtitle{
+  display: block;
+  text-align: center;
+  margin-bottom: 10px;
+  font-weight: bold;
+}
+.highlight-box{
+  padding: 10px;
+  border-radius: 5px 5px 25px 5px;
+  background: #ffe087;
+  border: 2px solid #ffeab7;
+  margin: 5px 0;
+}
+.ack{
+  color: #CCC;
+  a {
+    font-style: 'italic';
+  }
+}

static/images/favicon.svg DELETED Viewed

static/images/favicon/android-chrome-192x192.png ADDED Viewed

static/images/favicon/android-chrome-512x512.png ADDED Viewed

static/images/favicon/apple-touch-icon.png ADDED Viewed

static/images/favicon/favicon-16x16.png ADDED Viewed

static/images/favicon/favicon-32x32.png ADDED Viewed

static/images/favicon/favicon.ico ADDED Viewed

static/images/favicon/site.webmanifest ADDED Viewed

	@@ -0,0 +1 @@


1	+ {"name":"","short_name":"","icons":[{"src":"/android-chrome-192x192.png","sizes":"192x192","type":"image/png"},{"src":"/android-chrome-512x512.png","sizes":"512x512","type":"image/png"}],"theme_color":"#ffffff","background_color":"#ffffff","display":"standalone"}

static/images/interpolate_end.jpg DELETED Viewed

Binary file (113 kB)

static/images/interpolate_start.jpg DELETED Viewed

Binary file (117 kB)

static/images/performance.png ADDED Viewed

static/images/steve.webm DELETED Viewed

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:95c9528dadfebb0cef5b88012f1b11a7789364d66f48513203fdb8f0794ad0df
-size 1090546

static/images/teaser.png ADDED Viewed

static/interpolation/stacked/000000.jpg DELETED Viewed

Binary file (128 kB)

static/interpolation/stacked/000001.jpg DELETED Viewed

Binary file (128 kB)

static/interpolation/stacked/000002.jpg DELETED Viewed

Binary file (128 kB)

static/interpolation/stacked/000003.jpg DELETED Viewed

Binary file (128 kB)

static/interpolation/stacked/000004.jpg DELETED Viewed

Binary file (128 kB)

static/interpolation/stacked/000005.jpg DELETED Viewed

Binary file (129 kB)

static/interpolation/stacked/000006.jpg DELETED Viewed

Binary file (129 kB)

static/interpolation/stacked/000007.jpg DELETED Viewed

Binary file (129 kB)

static/interpolation/stacked/000008.jpg DELETED Viewed

Binary file (129 kB)

static/interpolation/stacked/000009.jpg DELETED Viewed

Binary file (129 kB)

static/interpolation/stacked/000010.jpg DELETED Viewed

Binary file (129 kB)

static/interpolation/stacked/000011.jpg DELETED Viewed

Binary file (129 kB)

static/interpolation/stacked/000012.jpg DELETED Viewed

Binary file (130 kB)

static/interpolation/stacked/000013.jpg DELETED Viewed

Binary file (130 kB)

static/interpolation/stacked/000014.jpg DELETED Viewed

Binary file (130 kB)

static/interpolation/stacked/000015.jpg DELETED Viewed

Binary file (130 kB)

static/interpolation/stacked/000016.jpg DELETED Viewed

Binary file (130 kB)

static/interpolation/stacked/000017.jpg DELETED Viewed

Binary file (131 kB)

static/interpolation/stacked/000018.jpg DELETED Viewed

Binary file (131 kB)

static/interpolation/stacked/000019.jpg DELETED Viewed

Binary file (130 kB)

static/interpolation/stacked/000020.jpg DELETED Viewed

Binary file (130 kB)

static/interpolation/stacked/000021.jpg DELETED Viewed

Binary file (131 kB)

static/interpolation/stacked/000022.jpg DELETED Viewed

Binary file (131 kB)

static/interpolation/stacked/000023.jpg DELETED Viewed

Binary file (131 kB)

static/interpolation/stacked/000024.jpg DELETED Viewed

Binary file (131 kB)

static/interpolation/stacked/000025.jpg DELETED Viewed

Binary file (131 kB)

static/interpolation/stacked/000026.jpg DELETED Viewed

Binary file (131 kB)

static/interpolation/stacked/000027.jpg DELETED Viewed

Binary file (131 kB)

static/interpolation/stacked/000028.jpg DELETED Viewed

Binary file (131 kB)

static/interpolation/stacked/000029.jpg DELETED Viewed

Binary file (131 kB)

static/interpolation/stacked/000030.jpg DELETED Viewed

Binary file (131 kB)

static/interpolation/stacked/000031.jpg DELETED Viewed

Binary file (131 kB)

static/interpolation/stacked/000032.jpg DELETED Viewed

Binary file (131 kB)

static/interpolation/stacked/000033.jpg DELETED Viewed

Binary file (131 kB)