11 accepted papers
Metric learning requires the identification of far-apart similar pairs and close dissimilar pairs during training, and this is difficult to achieve with unlabeled data because pairs are typically assumed to be similar if they are close. We present a novel metric learning method which circumvents thi…
Three of the key challenges in semi-supervised metric learning are the difficulty in sampling loss-producing triplets, the difficulty in locating similar data which are faraway from the anchor points, and the difficulty in making the model robust to noisy predicted pseudolabels. We propose a method…
Deep learning image classifiers are known to be vulnerable to small adversarial perturbations of input images. In this paper, we derive the locally optimal generalized likelihood ratio test based detector for detecting stochastic targeted universal adversarial perturbations to a classifier’s input.…
We present a supervised semantic hashing method which uses a variational autoencoder to represent each database image sample as a product Bernoulli distribution. We show that the probability parameters approach extreme values during training, allowing them to be used directly as hash bits. We show h…
We study the convergence properties of a general inertial first-order proximal splitting algorithm for solving nonconvex nonsmooth optimization problems. Using the Kurdyka-Łojaziewicz (KL) inequality we establish new convergence rates which apply to several inertial algorithms in the literature. Our…
Random forest has emerged as a powerful classification technique with promising results in various vision tasks including image classification, pose estimation and object detection. However, current techniques have shown little improvements in visual tracking as they mostly rely on piece wise orthog…
A fast, low-complexity, algorithm for solving the ℓ <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sub> -regularized least-squares problem is devised and analyzed. Our algorithm, which we call the Inertial Iterative Soft-Thresholding Algorithm (I-IS…
In this paper, we propose a new deep hashing (DH) approach to learn compact binary codes for large scale visual search. Unlike most existing binary codes learning methods which seek a single linear projection to map each sample into a binary vector, we develop a deep neural network to seek multiple…
Dense local motion features such as dense trajectories have been widely used in action recognition. For most actions, only a few local features (e.g., critical movements of the hand, arm, leg etc.) are responsible to the action label. Therefore, discovering important motion part will lead to a more…
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. Motivated by the fact that manifold can be effecti…
In this paper, we propose a novel robust hashing algorithm based on signal-to-noise ratio (SNR) maximization to learn binary codes. We first motivate SNR maximization for robust hashing in a statistical model, under which maximizing SNR minimizes the robust hashing error probability. A globally opti…