2 Search Results for "Wan, Andrew"


Document
Susceptibility to Image Resolution in Face Recognition and Training Strategies to Enhance Robustness

Authors: Martin Knoche, Stefan Hörmann, and Gerhard Rigoll

Published in: LITES, Volume 8, Issue 1 (2022): Special Issue on Embedded Systems for Computer Vision. Leibniz Transactions on Embedded Systems, Volume 8, Issue 1


Abstract
Many face recognition approaches expect the input images to have similar image resolution. However, in real-world applications, the image resolution varies due to different image capture mechanisms or sources, affecting the performance of face recognition systems. This work first analyzes the image resolution susceptibility of modern face recognition. Face verification on the very popular LFW dataset drops from 99.23% accuracy to almost 55% when image dimensions of both images are reduced to arguable very poor resolution. With cross-resolution image pairs (one HR and one LR image), face verification accuracy is even worse. This characteristic is investigated more in-depth by analyzing the feature distances utilized for face verification. To increase the robustness, we propose two training strategies applied to a state-of-the-art face recognition model: 1) Training with 50% low resolution images within each batch and 2) using the cosine distance loss between high and low resolution features in a siamese network structure. Both methods significantly boost face verification accuracy for matching training and testing image resolutions. Training a network with different resolutions simultaneously instead of adding only one specific low resolution showed improvements across all resolutions and made a single model applicable to unknown resolutions. However, models trained for one particular low resolution perform better when using the exact resolution for testing. We improve the face verification accuracy from 96.86% to 97.72% on the popular LFW database with uniformly distributed image dimensions between 112 × 112 px and 5 × 5 px. Our approaches improve face verification accuracy even more from 77.56% to 87.17% for distributions focusing on lower images resolutions. Lastly, we propose specific image dimension sets focusing on high, mid, and low resolution for five well-known datasets to benchmark face verification accuracy in cross-resolution scenarios.

Cite as

Martin Knoche, Stefan Hörmann, and Gerhard Rigoll. Susceptibility to Image Resolution in Face Recognition and Training Strategies to Enhance Robustness. In LITES, Volume 8, Issue 1 (2022): Special Issue on Embedded Systems for Computer Vision. Leibniz Transactions on Embedded Systems, Volume 8, Issue 1, pp. 01:1-01:20, Schloss Dagstuhl - Leibniz-Zentrum für Informatik (2022)


Copy BibTex To Clipboard

@Article{knoche_et_al:LITES.8.1.1,
  author =	{Knoche, Martin and H\"{o}rmann, Stefan and Rigoll, Gerhard},
  title =	{{Susceptibility to Image Resolution in Face Recognition and Training Strategies to Enhance Robustness}},
  booktitle =	{LITES, Volume 8, Issue 1 (2022): Special Issue on Embedded Systems for Computer Vision},
  pages =	{01:1--01:20},
  journal =	{Leibniz Transactions on Embedded Systems},
  ISSN =	{2199-2002},
  year =	{2022},
  volume =	{8},
  number =	{1},
  editor =	{Knoche, Martin and H\"{o}rmann, Stefan and Rigoll, Gerhard},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LITES.8.1.1},
  doi =		{10.4230/LITES.8.1.1},
  annote =	{Keywords: recognition, resolution, cross, face, identification}
}
Document
Pseudorandomness and Fourier Growth Bounds for Width-3 Branching Programs

Authors: Thomas Steinke, Salil Vadhan, and Andrew Wan

Published in: LIPIcs, Volume 28, Approximation, Randomization, and Combinatorial Optimization. Algorithms and Techniques (APPROX/RANDOM 2014)


Abstract
We present an explicit pseudorandom generator for oblivious, read-once, width-3 branching programs, which can read their input bits in any order. The generator has seed length O~( log^3 n ). The previously best known seed length for this model is n^{1/2+o(1)} due to Impagliazzo, Meka, and Zuckerman (FOCS'12). Our work generalizes a recent result of Reingold, Steinke, and Vadhan (RANDOM'13) for permutation branching programs. The main technical novelty underlying our generator is a new bound on the Fourier growth of width-3, oblivious, read-once branching programs. Specifically, we show that for any f : {0,1}^n -> {0,1} computed by such a branching program, and k in [n], sum_{|s|=k} |hat{f}(s)| < n^2 * (O(\log n))^k, where f(x) = sum_s hat{f}(s) (-1)^<s,x> is the standard Fourier transform over Z_2^n. The base O(log n) of the Fourier growth is tight up to a factor of log log n.

Cite as

Thomas Steinke, Salil Vadhan, and Andrew Wan. Pseudorandomness and Fourier Growth Bounds for Width-3 Branching Programs. In Approximation, Randomization, and Combinatorial Optimization. Algorithms and Techniques (APPROX/RANDOM 2014). Leibniz International Proceedings in Informatics (LIPIcs), Volume 28, pp. 885-899, Schloss Dagstuhl - Leibniz-Zentrum für Informatik (2014)


Copy BibTex To Clipboard

@InProceedings{steinke_et_al:LIPIcs.APPROX-RANDOM.2014.885,
  author =	{Steinke, Thomas and Vadhan, Salil and Wan, Andrew},
  title =	{{Pseudorandomness and Fourier Growth Bounds for Width-3 Branching Programs}},
  booktitle =	{Approximation, Randomization, and Combinatorial Optimization. Algorithms and Techniques (APPROX/RANDOM 2014)},
  pages =	{885--899},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-939897-74-3},
  ISSN =	{1868-8969},
  year =	{2014},
  volume =	{28},
  editor =	{Jansen, Klaus and Rolim, Jos\'{e} and Devanur, Nikhil R. and Moore, Cristopher},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.APPROX-RANDOM.2014.885},
  URN =		{urn:nbn:de:0030-drops-47456},
  doi =		{10.4230/LIPIcs.APPROX-RANDOM.2014.885},
  annote =	{Keywords: Pseudorandomness, Branching Programs, Discrete Fourier Analysis}
}
  • Refine by Author
  • 1 Hörmann, Stefan
  • 1 Knoche, Martin
  • 1 Rigoll, Gerhard
  • 1 Steinke, Thomas
  • 1 Vadhan, Salil
  • Show More...

  • Refine by Classification
  • 1 Computing methodologies → Neural networks

  • Refine by Keyword
  • 1 Branching Programs
  • 1 Discrete Fourier Analysis
  • 1 Pseudorandomness
  • 1 cross
  • 1 face
  • Show More...

  • Refine by Type
  • 2 document

  • Refine by Publication Year
  • 1 2014
  • 1 2022

Questions / Remarks / Feedback
X

Feedback for Dagstuhl Publishing


Thanks for your feedback!

Feedback submitted

Could not send message

Please try again later or send an E-mail