Search Results for author: Pierre Moulin

Found 12 papers, 1 papers with code

Locally optimal detection of stochastic targeted universal adversarial perturbations

no code implementations8 Dec 2020 Amish Goel, Pierre Moulin

Deep learning image classifiers are known to be vulnerable to small adversarial perturbations of input images.

Image Classification

Robust Machine Learning via Privacy/Rate-Distortion Theory

no code implementations22 Jul 2020 Ye Wang, Shuchin Aeron, Adnan Siraj Rakin, Toshiaki Koike-Akino, Pierre Moulin

Robust machine learning formulations have emerged to address the prevalent vulnerability of deep neural networks to adversarial examples.

BIG-bench Machine Learning

Detecting Audio Attacks on ASR Systems with Dropout Uncertainty

no code implementations2 Jun 2020 Tejas Jayashankar, Jonathan Le Roux, Pierre Moulin

Various adversarial audio attacks have recently been developed to fool automatic speech recognition (ASR) systems.

Automatic Speech Recognition speech-recognition

Robust Visual Tracking Using Oblique Random Forests

1 code implementation CVPR 2017 Le Zhang, Jagannadan Varadarajan, Ponnuthurai Nagaratnam Suganthan, Narendra Ahuja, Pierre Moulin

Unlike conventional orthogonal decision trees that use a single feature and heuristic measures to obtain a split at each node, we propose to use a more powerful proximal SVM to obtain oblique hyperplanes to capture the geometric structure of the data better.

General Classification Image Classification +5

Faster Subgradient Methods for Functions with Hölderian Growth

no code implementations1 Apr 2017 Patrick R. Johnstone, Pierre Moulin

Thirdly we develop a novel "descending stairs" stepsize which obtains this faster convergence rate and also obtains linear convergence for the special case of weakly sharp functions.

Variable-Length Hashing

no code implementations17 Mar 2016 Honghai Yu, Pierre Moulin, Hong Wei Ng, XiaoLi Li

In particular, we propose a block K-means hashing (B-KMH) method to obtain significantly improved retrieval performance with no increase in storage and marginal increase in computational cost.

Code Search

Local and Global Convergence of a General Inertial Proximal Splitting Scheme

no code implementations8 Feb 2016 Patrick R. Johnstone, Pierre Moulin

Our local analysis is applicable to certain recent variants of the Fast Iterative Shrinkage-Thresholding Algorithm (FISTA), for which we establish active manifold identification and local linear convergence.

Deep Hashing for Compact Binary Codes Learning

no code implementations CVPR 2015 Venice Erin Liong, Jiwen Lu, Gang Wang, Pierre Moulin, Jie zhou

In this paper, we propose a new deep hashing (DH) approach to learn compact binary codes for large scale visual search.

Multi-Manifold Deep Metric Learning for Image Set Classification

no code implementations CVPR 2015 Jiwen Lu, Gang Wang, Weihong Deng, Pierre Moulin, Jie zhou

In this paper, we propose a multi-manifold deep metric learning (MMDML) method for image set classification, which aims to recognize an object of interest from a set of image instances captured from varying viewpoints or under varying illuminations.

Classification General Classification +1

Motion Part Regularization: Improving Action Recognition via Trajectory Selection

no code implementations CVPR 2015 Bingbing Ni, Pierre Moulin, Xiaokang Yang, Shuicheng Yan

Inspired by the recent advance in sentence regularization for text classification, we introduce a Motion Part Regularization framework to mining discriminative semi-local groups of dense trajectories.

Action Recognition text-classification +1

Multiple Granularity Analysis for Fine-grained Action Detection

no code implementations CVPR 2014 Bingbing Ni, Vignesh R. Paramathayalan, Pierre Moulin

We propose to decompose the fine-grained human activity analysis problem into two sequential tasks with increasing granularity.

Fine-Grained Action Detection

Beta Process Multiple Kernel Learning

no code implementations CVPR 2014 Bingbing Ni, Teng Li, Pierre Moulin

Specifically, for the kernel representation calculated for each input feature instance, we multiply it element-wise with a latent binary vector named as instance selection variables, which targets at selecting good instances and attenuate the effect of ambiguous ones in the resulting new kernel representation.

Variational Inference

Cannot find the paper you are looking for? You can Submit a new open access paper.