Visual Permutation LearningRodrigo Santa Cruz, Basura Fernando, Anoop Cherian, and Stephen Gould
In IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 2018.
We present a principled approach to uncover the structure of visual data by solving a deep learning task coined visual permutation learning. To this end, we resort to a continuous approximation using doubly-stochastic matrices, formulate a novel bi-level optimization problem, and propose a computationally cheap scheme based on Sinkhorn iterations. The utility of these models are demonstrated on relative attributes learning, supervised learning-to-rank, and self-supervised representation learning.
Neural Algebra of ClassifiersRodrigo Santa Cruz, Basura Fernando, Anoop Cherian, and Stephen Gould
In IEEE Winter Conference on Applications of Computer Vision (WACV), 2018.
We build on the compositionality principle and develop an “algebra” to compose classifiers for complex visual concepts. To this end, we learn neural network modules to perform boolean algebra operations on simple visual classifiers. Since these modules form a complete functional set, a classifier for any complex visual concept defined as a boolean expression of primitives can be obtained by recursively applying the learned modules, even if we do not have a single training sample.
DeepPermNet: Visual Permutation LearningRodrigo Santa Cruz, Basura Fernando, Anoop Cherian, and Stephen Gould
In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017.
We present a principled approach to uncover the structure of visual data by solving a novel deep learning task coined visual permutation learning. Moreover, we propose DeepPermNet, an end-to-end CNN model for this task. The utility of our proposed approach is demonstrated on two challenging computer vision problems, namely, relative attributes learning and self-supervised representation learning.
Human detection in digital videos using motion features extractorsRodrigo F. S. C. Oliveira and Carmelo J. A. Bastos-Filho
In IEEE Latin American Conference on Computational Intelligence (LA-CCI), 2016.
We combine motion features to the Aggregated Channel Features (ACF) pedestrian detector. We demonstrate that motion features can provide more accurate results and reduce false alarms.
On Differentiating Parameterized Argmin and Argmax Problems with Application to Bi-level OptimizationStephen Gould, Basura Fernando, Anoop Cherian, Peter Anderson, Rodrigo Santa Cruz, and Edison Guo
Technical Report, available online on arXiv, 2016.
In this technical report we collect some results on differentiating argmin and argmax optimization problems with and without constraints and provide some insightful motivating applications. Such results are very useful for developing end-to-end gradient based learning methods.
Bayesian Model Averaging Naive Bayes: Averaging over an Exponential Number of Feature Models in Linear TimeGa Wu, Scott Sanner, and Rodrigo F. S. C. Oliveira
In Proceedings of the 29th Conference on Artificial Intelligence (AAAI), 2015.
We demonstrate that it is possible to exactly evaluate Bayesian model averaging (BMA) over the exponentially-sized powerset of Naive Bayes (NB) feature models in linear-time in the number of features; this yields an algorithm about as expensive to train as a single NB model with all features, but yet provably converges to the globally optimal feature subset in the asymptotic limit of data.
Regenerator Placement and Link Capacity Optimization in Translucent Optical Networks Using a Multi-objective Evolutionary AlgorithmRenan V. Carvalho, Rodrigo F. Oliveira, Carmelo J. Bastos Filho, Daniel A. Chaves, and Joaquim F. Martins Filho.
In Proceedings of Optical Fiber Conference (OFC/NFOEC), 2012.
We present an Evolutionary algorithm to tackle simultaneously the regenerator placement and link capacity optimization problems in translucent optical networks. Our proposed method can assist a network designer to manage resources balancing cost and performance.