Word cloud generated from my papers and notes.

Publications

Cortical Flow: A Diffeomorphic Mesh Deformation Network for Cortical Surface Reconstruction

Léo Lebrat*, Rodrigo Santa Cruz*, Frederic de Gournay, Pierrick Bourgeat, Jurgen Fripp, Darren Fu, Clinton Fookes, Olivier Salvado
In Conference on Neural Information Processing Systems (NeurIPS), 2021. * equal contribution.

read_more

In this paper, we introduce CorticalFlow, a new geometric deep-learning model that, given a 3-dimensional image, learns to deform a reference template towards a targeted object. To conserve the template mesh’s topological properties, we train our model over a set of diffeomorphic transformations. This framework can generate surfaces with several hundred thousand vertices in seconds requiring only a small GPU memory footprint. We evaluate its performance for the challenging task of brain cortical surface reconstruction from MRI.

MongeNet: Efficient Sampler For Geometric Deep Learning

Léo Lebrat*, Rodrigo Santa Cruz*, Clinton Fookes, and Olivier Salvado
In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021. * equal contribution.

read_more

This paper proposes a novel algorithm to sample point clouds from triangular meshes. We formulate this problem as an optimal transport problem between simplexes and discrete Dirac measures, and develop an algorithm to compute the optimal solution. Due to the computational challenge of this algorithm, we train a neural network, named MongeNet, to predict its solution efficiently. MongeNet can be adopted as a mesh sampler during training or testing of 3D deep learning models providing a better representation of the underlying surface with a very small computational overhead.

Going Deeper With Brain Morphometry Using Neural Networks

Rodrigo Santa Cruz, Léo Lebrat, Pierrick Bourgeat, Vincent Doré, Jason Dowling, Jurgen Fripp, Clinton Fookes, and Olivier Salvado
In IEEE International Symposium on Biomedical Imaging (ISBI), 2021

read_more

In this paper, we propose a more accurate and efficient neural network model for brain morphometry named HerstonNet. More specifically, we develop a 3D ResNet-based neural network to learn rich features directly from MRI, design a multi-scale regression scheme by predicting morphometric measures at feature maps of different resolutions, and leverage a robust optimization method to avoid poor quality minima and reduce the prediction variance. As a result, HerstonNet improves the existing approach by 24.30% in terms of intraclass correlation coefficient (agreement measure) to FreeSurfer silver-standards while maintaining a competitive run-time.

SMOCAM: SMOoth Conditional Attention Mask for 3D-Regression Models

Salamata Konate, Léo Lebrat, Rodrigo Santa Cruz, Pierrick Bourgeat, Vincent Doré, Jurgen Fripp, Andrew Bradley, Clinton Fookes, and Olivier Salvado
In IEEE International Symposium on Biomedical Imaging (ISBI), 2021

read_more

Despite the pervasive growth of deep neural networks in medical image analysis, methods to monitor and assess network outputs, such as segmentation or regression, remain limited. In this paper, we introduce SMOCAM (SMOoth Conditional Attention Mask), an optimization method that reveals the specific regions of the input image taken into account by the prediction of a trained neural network. We developed SMOCAM explicitly to perform saliency analysis for complex regression tasks in 3D medical imagery like brain morphometry from MRI.

DeepCSR: A 3D Deep Learning Approach for Cortical Surface Reconstruction

Rodrigo Santa Cruz, Leo Lebrat, Pierrick Bourgeat, Clinton Fookes, Jurgen Fripp, and Olivier Salvado
In IEEE Winter Conference on Applications of Computer Vision (WACV), 2021.

read_more

In this paper, we propose a 3D deep learning framework for cortical surface reconstruction from MR images named DeepCSR. More specifically, we first reformulate this problem as the prediction of an implicit surface representation for points in a continuous coordinate system. Then, the cortical surfaces are extracted using this implicit surface representation, a lightweight topological correction method, and an isosurface mesh extraction technique.

3D Brain MRI GAN-Based Synthesis Conditioned on Partial Volume Maps

Filip Rusak, Rodrigo Santa Cruz, Pierrick Bourgeat, Clinton Fookes, Jurgen Fripp, Andrew Bradley, and Olivier Salvado
In the International Workshop on Simulation and Synthesis in Medical Imaging at MICCAI, 2020.

read_more

In this paper, we propose a GAN-Based framework for synthesising 3D brain T1-weighted (T1-w) MRI images from Partial Volume (PV) maps for the purpose of generating synthetic MRI volumes with more accurate tissue borders.

Inferring Temporal Compositions of Actions Using Probabilistic Automata

Rodrigo Santa Cruz, Anoop Cherian, Basura Fernando, Dylan Campbell, and Stephen Gould
In Workshop on Compositionality in Computer Vision at CVPR, 2020.

read_more

In this paper, we address the problem of recognizing complex compositional activities in videos. To this end, we describe activities unambiguously as regular expressions of simple primitive actions and derive framework based on Probabilistic Automata to recognize instances of these regular expressions in videos.

Visual Recognition From Structured Supervision

Rodrigo Santa Cruz
Ph.D. Thesis, Australian National University (ANU), December 2019.

read_more

This thesis describes methods that reduce the need for human supervision when training deep learning models by leveraging the structure in the visual world targeting visual recognition in difficult scenarios where annotated data is scarce and the visual concepts are innumerable or ambiguous.

Visual Permutation Learning

Rodrigo Santa Cruz, Basura Fernando, Anoop Cherian, and Stephen Gould
In IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 2018.

read_more

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 Classifiers

Rodrigo Santa Cruz, Basura Fernando, Anoop Cherian, and Stephen Gould
In IEEE Winter Conference on Applications of Computer Vision (WACV), 2018.

read_more

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 Learning

Rodrigo Santa Cruz, Basura Fernando, Anoop Cherian, and Stephen Gould
In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017.

read_more

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.

On Differentiating Parameterized Argmin and Argmax Problems with Application to Bi-level Optimization

Stephen Gould, Basura Fernando, Anoop Cherian, Peter Anderson, Rodrigo Santa Cruz, and Edison Guo
Technical Report, available online on arXiv, 2016.

read_more

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.

Human detection in digital videos using motion features extractors

Rodrigo F. S. C. Oliveira and Carmelo J. A. Bastos-Filho
In IEEE Latin American Conference on Computational Intelligence (LA-CCI), 2016.

read_more

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.

Bayesian Model Averaging Naive Bayes: Averaging over an Exponential Number of Feature Models in Linear Time

Ga Wu, Scott Sanner, and Rodrigo F. S. C. Oliveira
In Proceedings of the 29th Conference on Artificial Intelligence (AAAI), 2015.

read_more

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 Algorithm

Renan 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.

read_more

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.