We are interested in the large-scale learning of Mahalanobis distances, with a particular focus o... more We are interested in the large-scale learning of Mahalanobis distances, with a particular focus on person re-identification. We propose a metric learning formulation called Weighted Approximate Rank Component Analysis (WARCA). WARCA optimizes the precision at top ranks by combining the WARP loss with a regularizer that favors orthonormal linear mappings, and avoids rank-deficient embeddings. Using this new regularizer allows us to adapt the large-scale WSABIE procedure and to leverage the Adam stochastic optimization algorithm, which results in an algorithm that scales gracefully to very large data-sets. Also, we derive a kernelized version which allows to take advantage of state-of-the-art features for re-identification when data-set size permits kernel computation. Benchmarks on recent and standard re-identification data-sets show that our method beats existing state-of-the-art techniques both in term of accuracy and speed. We also provide experimental analysis to shade lights on the properties of the regularizer we use, and how it improves performance.
International Conference on Machine Learning, Jun 19, 2016
We propose a tree-based procedure inspired by the Monte-Carlo Tree Search that dynamically modula... more We propose a tree-based procedure inspired by the Monte-Carlo Tree Search that dynamically modulates an importance-based sampling to prioritize computation, while getting unbiased estimates of weighted sums. We apply this generic method to learning on very large training sets, and to the evaluation of large-scale SVMs. The core idea is to reformulate the estimation of a score -whether a loss or a prediction estimateas an empirical expectation, and to use such a tree whose leaves carry the samples to focus efforts over the problematic "heavy weight" ones. We illustrate the potential of this approach on three problems: to improve Adaboost and a multi-layer perceptron on 2D synthetic tasks with several million points, to train a large-scale convolution network on several millions deformations of the CIFAR data-set, and to compute the response of a SVM with several hundreds of thousands of support vectors. In each case, we show how it either cuts down computation by more than one order of magnitude and/or allows to get better loss estimates.
People detection methods are highly sensitive to the perpetual occlusions among the targets. As m... more People detection methods are highly sensitive to the perpetual occlusions among the targets. As multi-camera set-ups become more frequently encountered, joint exploitation of the across views information would allow for improved detection performances. We provide a large-scale HD dataset named WILDTRACK which finally makes advanced deep learning methods applicable to this problem. The seven-static-camera set-up captures realistic and challenging scenarios of walking people. Notably, its camera calibration with jointly high-precision projection widens the range of algorithms which may make use of this dataset. In aim to help accelerate the research on automatic camera calibration, such annotations also accompany this dataset. Furthermore, the rich-in-appearance visual context of the pedestrian class makes this dataset attractive for monocular pedestrian detection as well, since: the HD cameras are placed relatively close to the people, and the size of the dataset further increases seven-fold. In summary, we overview existing multi-camera datasets and detection methods, enumerate details of our dataset, and we benchmark multi-camera state of the art detectors on this new dataset.
Our work addresses two important issues with recurrent neural networks: (1) they are over-paramet... more Our work addresses two important issues with recurrent neural networks: (1) they are over-parametrized, and (2) the recurrent weight matrix is ill-conditioned. The former increases the sample complexity of learning and the training time. The latter causes the vanishing and exploding gradient problem. We present a flexible recurrent neural network model called Kronecker Recurrent Units (KRU). KRU achieves parameter efficiency in RNNs through a Kronecker factored recurrent matrix. It overcomes the ill-conditioning of the recurrent matrix by enforcing soft unitary constraints on the factors. Thanks to the small dimensionality of the factors, maintaining these constraints is computationally efficient. Our experimental results on seven standard data-sets reveal that KRU can reduce the number of parameters by three orders of magnitude in the recurrent weight matrix compared to the existing recurrent models, without trading the statistical performance. These results in particular show that while there are advantages in having a high dimensional recurrent space, the capacity of the recurrent part of the model can be dramatically reduced.
International Conference on Machine Learning, Feb 12, 2018
Our work addresses two important issues with recurrent neural networks: (1) they are overparametr... more Our work addresses two important issues with recurrent neural networks: (1) they are overparametrized, and (2) the recurrent weight matrix is ill-conditioned. The former increases the sample complexity of learning and the training time. The latter causes the vanishing and exploding gradient problem. We present a flexible recurrent neural network model called Kronecker Recurrent Units (KRU). KRU achieves parameter efficiency in RNNs through a Kronecker factored recurrent matrix. It overcomes the ill-conditioning of the recurrent matrix by enforcing soft unitary constraints on the factors. Thanks to the small dimensionality of the factors, maintaining these constraints is computationally efficient. Our experimental results on seven standard data-sets reveal that KRU can reduce the number of parameters by three orders of magnitude in the recurrent weight matrix compared to the existing recurrent models, without trading the statistical performance. These results in particular show that while there are advantages in having a high dimensional recurrent space, the capacity of the recurrent part of the model can be dramatically reduced.
We propose a tree-based procedure inspired by the Monte-Carlo Tree Search that dynamically modula... more We propose a tree-based procedure inspired by the Monte-Carlo Tree Search that dynamically modulates an importance-based sampling to prioritize computation, while getting unbiased estimates of weighted sums. We apply this generic method to learning on very large training sets, and to the evaluation of large-scale SVMs. The core idea is to reformulate the estimation of a score - whether a loss or a prediction estimate - as an empirical expectation, and to use such a tree whose leaves carry the samples to focus efforts over the problematic "heavy weight" ones. We illustrate the potential of this approach on three problems: to improve Adaboost and a multi-layer perceptron on 2D synthetic tasks with several million points, to train a large-scale convolution network on several millions deformations of the CIFAR data-set, and to compute the response of a SVM with several hundreds of thousands of support vectors. In each case, we show how it either cuts down computation by more t...
People detection methods are highly sensitive to the perpetual occlusions among the targets. As m... more People detection methods are highly sensitive to the perpetual occlusions among the targets. As multi-camera set-ups become more frequently encountered, joint exploitation of the across views information would allow for improved detection performances. We provide a large-scale HD dataset named WILDTRACK which finally makes advanced deep learning methods applicable to this problem. The seven-static-camera set-up captures realistic and challenging scenarios of walking people. Notably, its camera calibration with jointly high-precision projection widens the range of algorithms which may make use of this dataset. In aim to help accelerate the research on automatic camera calibration, such annotations also accompany this dataset. Furthermore, the rich-in-appearance visual context of the pedestrian class makes this dataset attractive for monocular pedestrian detection as well, since: the HD cameras are placed relatively close to the people, and the size of the dataset further increases se...
Uploads
Papers by cijo jose