arXiv subjects

Matias Valdenegro-Toro

Publications and source records attributed to Matias Valdenegro-Toro.

71 records · Page 4Linked to original sources

arXiv2020

Perception for Autonomous Systems (PAZ)

In this paper we introduce the Perception for Autonomous Systems (PAZ) software library. PAZ is a hierarchical perception library that allow users to manipulate multiple levels of abstraction in accordance to their requirements or skill level. More specifically, PAZ is divided into three hierarchical levels which we refer to as pipelines, processors, and backends. These abstractions allows users to compose functions in a hierarchical modular scheme that can be applied for preprocessing, data-augmentation, prediction and postprocessing of inputs and outputs of machine learning (ML) models. PAZ uses these abstractions to build reusable training and prediction pipelines for multiple robot perception tasks such as: 2D keypoint estimation, 2D object detection, 3D keypoint discovery, 6D pose estimation, emotion classification, face recognition, instance segmentation, and attention mechanisms.

cs.CV↗

arXiv2020

Hey Human, If your Facial Emotions are Uncertain, You Should Use Bayesian Neural Networks!

Facial emotion recognition is the task to classify human emotions in face images. It is a difficult task due to high aleatoric uncertainty and visual ambiguity. A large part of the literature aims to show progress by increasing accuracy on this task, but this ignores the inherent uncertainty and ambiguity in the task. In this paper we show that Bayesian Neural Networks, as approximated using MC-Dropout, MC-DropConnect, or an Ensemble, are able to model the aleatoric uncertainty in facial emotion recognition, and produce output probabilities that are closer to what a human expects. We also show that calibration metrics show strange behaviors for this task, due to the multiple classes that can be considered correct, which motivates future work. We believe our work will motivate other researchers to move away from Classical and into Bayesian Neural Networks.

cs.CV↗

arXiv2020

Evaluating Uncertainty Estimation Methods on 3D Semantic Segmentation of Point Clouds

Deep learning models are extensively used in various safety critical applications. Hence these models along with being accurate need to be highly reliable. One way of achieving this is by quantifying uncertainty. Bayesian methods for UQ have been extensively studied for Deep Learning models applied on images but have been less explored for 3D modalities such as point clouds often used for Robots and Autonomous Systems. In this work, we evaluate three uncertainty quantification methods namely Deep Ensembles, MC-Dropout and MC-DropConnect on the DarkNet21Seg 3D semantic segmentation model and comprehensively analyze the impact of various parameters such as number of models in ensembles or forward passes, and drop probability values, on task performance and uncertainty estimate quality. We find that Deep Ensembles outperforms other methods in both performance and uncertainty metrics. Deep ensembles outperform other methods by a margin of 2.4% in terms of mIOU, 1.3% in terms of accuracy, while providing reliable uncertainty for decision making.

cs.CV↗

arXiv2019

Deep Sub-Ensembles for Fast Uncertainty Estimation in Image Classification

Fast estimates of model uncertainty are required for many robust robotics applications. Deep Ensembles provides state of the art uncertainty without requiring Bayesian methods, but still it is computationally expensive. In this paper we propose deep sub-ensembles, an approximation to deep ensembles where the core idea is to ensemble only the layers close to the output, and not the whole model. With ResNet-20 on the CIFAR10 dataset, we obtain 1.5-2.5 speedup over a Deep Ensemble, with a small increase in error and NLL, and similarly up to 5-15 speedup with a VGG-like network on the SVHN dataset. Our results show that this idea enables a trade-off between error and uncertainty quality versus computational performance.

cs.LG↗

arXiv2019

Results from the Robocademy ITN: Autonomy, Disturbance Rejection and Perception for Advanced Marine Robotics

Marine and Underwater resources are important part of the economy of many countries. This requires significant financial resources into their construction and maintentance. Robotics is expected to fill this void, by automating and/or removing humans from hostile environments in order to easily perform maintenance tasks. The Robocademy Marie Sklodowska-Curie Initial Training Network was funded by the European Union's FP7 research program in order to train 13 Fellows into world-leading researchers in Marine and Underwater Robotics. The fellows developed guided research into three areas of key importance: Autonomy, Disturbance Rejection, and Perception. This paper presents a summary of the fellows' research in the three action lines. 71 scientific publications were the primary result of this project, with many other publications currently in the pipeline. Most of the fellows have found employment in Europe, which shows the high demand for this kind of experts. We believe the results from this project are already having an impact in the marine robotics industry, as key technologies are being adopted already.

cs.RO↗

arXiv2019

Data augmentation with Symbolic-to-Real Image Translation GANs for Traffic Sign Recognition

Traffic sign recognition is an important component of many advanced driving assistance systems, and it is required for full autonomous driving. Computational performance is usually the bottleneck in using large scale neural networks for this purpose. SqueezeNet is a good candidate for efficient image classification of traffic signs, but in our experiments it does not reach high accuracy, and we believe this is due to lack of data, requiring data augmentation. Generative adversarial networks can learn the high dimensional distribution of empirical data, allowing the generation of new data points. In this paper we apply pix2pix GANs architecture to generate new traffic sign images and evaluate the use of these images in data augmentation. We were motivated to use pix2pix to translate symbolic sign images to real ones due to the mode collapse in Conditional GANs. Through our experiments we found that data augmentation using GAN can increase classification accuracy for circular traffic signs from 92.1% to 94.0%, and for triangular traffic signs from 93.8% to 95.3%, producing an overall improvement of 2%. However some traditional augmentation techniques can outperform GAN data augmentation, for example contrast variation in circular traffic signs (95.5%) and displacement on triangular traffic signs (96.7 %). Our negative results shows that while GANs can be naively used for data augmentation, they are not always the best choice, depending on the problem and variability in the data.

cs.CV↗

arXiv2019

Improving Predictive Uncertainty Estimation using Dropout -- Hamiltonian Monte Carlo

Estimating predictive uncertainty is crucial for many computer vision tasks, from image classification to autonomous driving systems. Hamiltonian Monte Carlo (HMC) is an sampling method for performing Bayesian inference. On the other hand, Dropout regularization has been proposed as an approximate model averaging technique that tends to improve generalization in large scale models such as deep neural networks. Although, HMC provides convergence guarantees for most standard Bayesian models, it does not handle discrete parameters arising from Dropout regularization. In this paper, we present a robust methodology for improving predictive uncertainty in classification problems, based on Dropout and Hamiltonian Monte Carlo. Even though Dropout induces a non-smooth energy function with no such convergence guarantees, the resulting discretization of the Hamiltonian proves empirical success. The proposed method allows to effectively estimate the predictive accuracy and to provide better generalization for difficult test examples.

cs.LG↗

arXiv2019

Learning Objectness from Sonar Images for Class-Independent Object Detection

Detecting novel objects without class information is not trivial, as it is difficult to generalize from a small training set. This is an interesting problem for underwater robotics, as modeling marine objects is inherently more difficult in sonar images, and training data might not be available apriori. Detection proposals algorithms can be used for this purpose but usually requires a large amount of output bounding boxes. In this paper we propose the use of a fully convolutional neural network that regresses an objectness value directly from a Forward-Looking sonar image. By ranking objectness, we can produce high recall (96 %) with only 100 proposals per image. In comparison, EdgeBoxes requires 5000 proposals to achieve a slightly better recall of 97 %, while Selective Search requires 2000 proposals to achieve 95 % recall. We also show that our method outperforms a template matching baseline by a considerable margin, and is able to generalize to completely new objects. We expect that this kind of technique can be used in the field to find lost objects under the sea.

cs.CV↗

arXiv2019

Deep Neural Networks for Marine Debris Detection in Sonar Images

Garbage and waste disposal is one of the biggest challenges currently faced by mankind. Proper waste disposal and recycling is a must in any sustainable community, and in many coastal areas there is significant water pollution in the form of floating or submerged garbage. This is called marine debris. Submerged marine debris threatens marine life, and for shallow coastal areas, it can also threaten fishing vessels [Iñiguez et al. 2016, Renewable and Sustainable Energy Reviews]. Submerged marine debris typically stays in the environment for a long time (20+ years), and consists of materials that can be recycled, such as metals, plastics, glass, etc. Many of these items should not be disposed in water bodies as this has a negative effect in the environment and human health. This thesis performs a comprehensive evaluation on the use of DNNs for the problem of marine debris detection in FLS images, as well as related problems such as image classification, matching, and detection proposals. We do this in a dataset of 2069 FLS images that we captured with an ARIS Explorer 3000 sensor on marine debris objects lying in the floor of a small water tank. The objects we used to produce this dataset contain typical household marine debris and distractor marine objects (tires, hooks, valves, etc), divided in 10 classes plus a background class. Our results show that for the evaluated tasks, DNNs are a superior technique than the corresponding state of the art. There are large gains particularly for the matching and detection proposal tasks. We also study the effect of sample complexity and object size in many tasks, which is valuable information for practitioners. We expect that our results will advance the objective of using Autonomous Underwater Vehicles to automatically survey, detect and collect marine debris from underwater environments.

cs.CV↗

arXiv2019

Implementing Noise with Hash functions for Graphics Processing Units

We propose a modification to Perlin noise which use computable hash functions instead of textures as lookup tables. We implemented the FNV1, Jenkins and Murmur hashes on Shader Model 4.0 Graphics Processing Units for noise generation. Modified versions of the FNV1 and Jenkins hashes provide very close performance compared to a texture based Perlin noise implementation. Our noise modification enables noise function evaluation without any texture fetches, trading computational power for memory bandwidth.

cs.GR↗

arXiv2018

Modeling and Soft-fault Diagnosis of Underwater Thrusters with Recurrent Neural Networks

Noncritical soft-faults and model deviations are a challenge for Fault Detection and Diagnosis (FDD) of resident Autonomous Underwater Vehicles (AUVs). Such systems may have a faster performance degradation due to the permanent exposure to the marine environment, and constant monitoring of component conditions is required to ensure their reliability. This works presents an evaluation of Recurrent Neural Networks (RNNs) for a data-driven fault detection and diagnosis scheme for underwater thrusters with empirical data. The nominal behavior of the thruster was modeled using the measured control input, voltage, rotational speed and current signals. We evaluated the performance of fault classification using all the measured signals compared to using the computed residuals from the nominal model as features.

cs.RO↗

arXiv2017

Image Captioning and Classification of Dangerous Situations

Current robot platforms are being employed to collaborate with humans in a wide range of domestic and industrial tasks. These environments require autonomous systems that are able to classify and communicate anomalous situations such as fires, injured persons, car accidents; or generally, any potentially dangerous situation for humans. In this paper we introduce an anomaly detection dataset for the purpose of robot applications as well as the design and implementation of a deep learning architecture that classifies and describes dangerous situations using only a single image as input. We report a classification accuracy of 97 % and METEOR score of 16.2. We will make the dataset publicly available after this paper is accepted.

cs.CV↗

arXiv2017

Real-time Convolutional Neural Networks for Emotion and Gender Classification

In this paper we propose an implement a general convolutional neural network (CNN) building framework for designing real-time CNNs. We validate our models by creating a real-time vision system which accomplishes the tasks of face detection, gender classification and emotion classification simultaneously in one blended step using our proposed CNN architecture. After presenting the details of the training procedure setup we proceed to evaluate on standard benchmark sets. We report accuracies of 96% in the IMDB gender dataset and 66% in the FER-2013 emotion dataset. Along with this we also introduced the very recent real-time enabled guided back-propagation visualization technique. Guided back-propagation uncovers the dynamics of the weight changes and evaluates the learned features. We argue that the careful implementation of modern CNN architectures, the use of the current regularization methods and the visualization of previously hidden features are necessary in order to reduce the gap between slow performances and real-time architectures. Our system has been validated by its deployment on a Care-O-bot 3 robot used during RoboCup@Home competitions. All our code, demos and pre-trained architectures have been released under an open-source license in our public repository.

cs.CV↗

arXiv2017

Best Practices in Convolutional Networks for Forward-Looking Sonar Image Recognition

Convolutional Neural Networks (CNN) have revolutionized perception for color images, and their application to sonar images has also obtained good results. But in general CNNs are difficult to train without a large dataset, need manual tuning of a considerable number of hyperparameters, and require many careful decisions by a designer. In this work, we evaluate three common decisions that need to be made by a CNN designer, namely the performance of transfer learning, the effect of object/image size and the relation between training set size. We evaluate three CNN models, namely one based on LeNet, and two based on the Fire module from SqueezeNet. Our findings are: Transfer learning with an SVM works very well, even when the train and transfer sets have no classes in common, and high classification performance can be obtained even when the target dataset is small. The ADAM optimizer combined with Batch Normalization can make a high accuracy CNN classifier, even with small image sizes (16 pixels). At least 50 samples per class are required to obtain $90\%$ test accuracy, and using Dropout with a small dataset helps improve performance, but Batch Normalization is better when a large dataset is available.

cs.CV↗

arXiv2017

Objectness Scoring and Detection Proposals in Forward-Looking Sonar Images with Convolutional Neural Networks

Forward-looking sonar can capture high resolution images of underwater scenes, but their interpretation is complex. Generic object detection in such images has not been solved, specially in cases of small and unknown objects. In comparison, detection proposal algorithms have produced top performing object detectors in real-world color images. In this work we develop a Convolutional Neural Network that can reliably score objectness of image windows in forward-looking sonar images and by thresholding objectness, we generate detection proposals. In our dataset of marine garbage objects, we obtain 94% recall, generating around 60 proposals per image. The biggest strength of our method is that it can generalize to previously unseen objects. We show this by detecting chain links, walls and a wrench without previous training in such objects. We strongly believe our method can be used for class-independent object detection, with many real-world applications such as chain following and mine detection.

cs.CV↗

arXiv2017

Improving Sonar Image Patch Matching via Deep Learning

Matching sonar images with high accuracy has been a problem for a long time, as sonar images are inherently hard to model due to reflections, noise and viewpoint dependence. Autonomous Underwater Vehicles require good sonar image matching capabilities for tasks such as tracking, simultaneous localization and mapping (SLAM) and some cases of object detection/recognition. We propose the use of Convolutional Neural Networks (CNN) to learn a matching function that can be trained from labeled sonar data, after pre-processing to generate matching and non-matching pairs. In a dataset of 39K training pairs, we obtain 0.91 Area under the ROC Curve (AUC) for a CNN that outputs a binary classification matching decision, and 0.89 AUC for another CNN that outputs a matching score. In comparison, classical keypoint matching methods like SIFT, SURF, ORB and AKAZE obtain AUC 0.61 to 0.68. Alternative learning methods obtain similar results, with a Random Forest Classifier obtaining AUC 0.79, and a Support Vector Machine resulting in AUC 0.66.

cs.CV↗

arXiv2017

Real-time convolutional networks for sonar image classification in low-power embedded systems

Deep Neural Networks have impressive classification performance, but this comes at the expense of significant computational resources at inference time. Autonomous Underwater Vehicles use low-power embedded systems for sonar image perception, and cannot execute large neural networks in real-time. We propose the use of max-pooling aggressively, and we demonstrate it with a Fire-based module and a new Tiny module that includes max-pooling in each module. By stacking them we build networks that achieve the same accuracy as bigger ones, while reducing the number of parameters and considerably increasing computational performance. Our networks can classify a 96x96 sonar image with 98.8 - 99.7 accuracy on only 41 to 61 milliseconds on a Raspberry Pi 2, which corresponds to speedups of 28.6 - 19.7.

cs.CV↗