arXiv subjects

Eduardo Valle

Publications and source records attributed to Eduardo Valle.

At least 55 records · Page 3Linked to original sources

arXiv2018

Deep-Learning Ensembles for Skin-Lesion Segmentation, Analysis, Classification: RECOD Titans at ISIC Challenge 2018

This extended abstract describes the participation of RECOD Titans in parts 1 to 3 of the ISIC Challenge 2018 "Skin Lesion Analysis Towards Melanoma Detection" (MICCAI 2018). Although our team has a long experience with melanoma classification and moderate experience with lesion segmentation, the ISIC Challenge 2018 was the very first time we worked on lesion attribute detection. For each task we submitted 3 different ensemble approaches, varying combinations of models and datasets. Our best results on the official testing set, regarding the official metric of each task, were: 0.728 (segmentation), 0.344 (attribute detection) and 0.803 (classification). Those submissions reached, respectively, the 56th, 14th and 9th places.

cs.CV↗

arXiv2018

Adversarial Attacks on Variational Autoencoders

Adversarial attacks are malicious inputs that derail machine-learning models. We propose a scheme to attack autoencoders, as well as a quantitative evaluation framework that correlates well with the qualitative assessment of the attacks. We assess --- with statistically validated experiments --- the resistance to attacks of three variational autoencoders (simple, convolutional, and DRAW) in three datasets (MNIST, SVHN, CelebA), showing that both DRAW's recurrence and attention mechanism lead to better resistance. As autoencoders are proposed for compressing data --- a scenario in which their safety is paramount --- we expect more attention will be given to adversarial attacks on them.

cs.CV↗

arXiv2017

Paperclickers: Affordable Solution for Classroom Response Systems

We propose a low-cost classroom response system requiring a single mobile device for the teacher and cards with printed codes for the students. We aim at broadening the adoption of active learning techniques in developing countries, offering a tool for easy implementation. We embody the solution as a smartphone application, describing the development history, pitfalls, and lessons learned that might be helpful for other small academic teams. We also described the results of the first round usability tests we performed on the first prototype, and how the affected the current version of the software. A beta release version is currently available for the public at large.

cs.CY↗

arXiv2017

Knowledge Transfer for Melanoma Screening with Deep Learning

Knowledge transfer impacts the performance of deep learning -- the state of the art for image classification tasks, including automated melanoma screening. Deep learning's greed for large amounts of training data poses a challenge for medical tasks, which we can alleviate by recycling knowledge from models trained on different tasks, in a scheme called transfer learning. Although much of the best art on automated melanoma screening employs some form of transfer learning, a systematic evaluation was missing. Here we investigate the presence of transfer, from which task the transfer is sourced, and the application of fine tuning (i.e., retraining of the deep learning model after transfer). We also test the impact of picking deeper (and more expensive) models. Our results favor deeper models, pre-trained over ImageNet, with fine-tuning, reaching an AUC of 80.7% and 84.5% for the two skin-lesion datasets evaluated.

cs.CV↗

arXiv2017

RECOD Titans at ISIC Challenge 2017

This extended abstract describes the participation of RECOD Titans in parts 1 and 3 of the ISIC Challenge 2017 "Skin Lesion Analysis Towards Melanoma Detection" (ISBI 2017). Although our team has a long experience with melanoma classification, the ISIC Challenge 2017 was the very first time we worked on skin-lesion segmentation. For part 1 (segmentation), our final submission used four of our models: two trained with all 2000 samples, without a validation split, for 250 and for 500 epochs respectively; and other two trained and validated with two different 1600/400 splits, for 220 epochs. Those four models, individually, achieved between 0.780 and 0.783 official validation scores. Our final submission averaged the output of those four models achieved a score of 0.793. For part 3 (classification), the submitted test run as well as our last official validation run were the result from a meta-model that assembled seven base deep-learning models: three based on Inception-V4 trained on our largest dataset; three based on Inception trained on our smallest dataset; and one based on ResNet-101 trained on our smaller dataset. The results of those component models were stacked in a meta-learning layer based on an SVM trained on the validation set of our largest dataset.

cs.CV↗

arXiv2016

Known Unknowns: Uncertainty Quality in Bayesian Neural Networks

We evaluate the uncertainty quality in neural networks using anomaly detection. We extract uncertainty measures (e.g. entropy) from the predictions of candidate models, use those measures as features for an anomaly detector, and gauge how well the detector differentiates known from unknown classes. We assign higher uncertainty quality to candidate models that lead to better detectors. We also propose a novel method for sampling a variational approximation of a Bayesian neural network, called One-Sample Bayesian Approximation (OSBA). We experiment on two datasets, MNIST and CIFAR10. We compare the following candidate neural network models: Maximum Likelihood, Bayesian Dropout, OSBA, and --- for MNIST --- the standard variational approximation. We show that Bayesian Dropout and OSBA provide better uncertainty information than Maximum Likelihood, and are essentially equivalent to the standard variational approximation, but much faster.

stat.ML↗

arXiv2016

Adversarial Images for Variational Autoencoders

We investigate adversarial attacks for autoencoders. We propose a procedure that distorts the input image to mislead the autoencoder in reconstructing a completely different target image. We attack the internal latent representations, attempting to make the adversarial input produce an internal representation as similar as possible as the target's. We find that autoencoders are much more robust to the attack than classifiers: while some examples have tolerably small input distortion, and reasonable similarity to the target image, there is a quasi-linear trade-off between those aims. We report results on MNIST and SVHN datasets, and also test regular deterministic autoencoders, reaching similar conclusions in all cases. Finally, we show that the usual adversarial attack for classifiers, while being much easier, also presents a direct proportion between distortion on the input, and misdirection on the output. That proportionality however is hidden by the normalization of the output, which maps a linear layer into non-linear probabilities.

cs.NE↗

arXiv2016

Towards Automated Melanoma Screening: Exploring Transfer Learning Schemes

Deep learning is the current bet for image classification. Its greed for huge amounts of annotated data limits its usage in medical imaging context. In this scenario transfer learning appears as a prominent solution. In this report we aim to clarify how transfer learning schemes may influence classification results. We are particularly focused in the automated melanoma screening problem, a case of medical imaging in which transfer learning is still not widely used. We explored transfer with and without fine-tuning, sequential transfers and usage of pre-trained models in general and specific datasets. Although some issues remain open, our findings may drive future researches.

cs.CV↗

arXiv2016

Where Is My Puppy? Retrieving Lost Dogs by Facial Features

A pet that goes missing is among many people's worst fears: a moment of distraction is enough for a dog or a cat wandering off from home. Some measures help matching lost animals to their owners; but automated visual recognition is one that - although convenient, highly available, and low-cost - is surprisingly overlooked. In this paper, we inaugurate that promising avenue by pursuing face recognition for dogs. We contrast four ready-to-use human facial recognizers (EigenFaces, FisherFaces, LBPH, and a Sparse method) to two original solutions based upon convolutional neural networks: BARK (inspired in architecture-optimized networks employed for human facial recognition) and WOOF (based upon off-the-shelf OverFeat features). Human facial recognizers perform poorly for dogs (up to 60.5% accuracy), showing that dog facial recognition is not a trivial extension of human facial recognition. The convolutional network solutions work much better, with BARK attaining up to 81.1% accuracy, and WOOF, 89.4%. The tests were conducted in two datasets: Flickr-dog, with 42 dogs of two breeds (pugs and huskies); and Snoopybook, with 18 mongrel dogs.

cs.CV↗

arXiv2016

Exploring the Space of Adversarial Images

Adversarial examples have raised questions regarding the robustness and security of deep neural networks. In this work we formalize the problem of adversarial images given a pretrained classifier, showing that even in the linear case the resulting optimization problem is nonconvex. We generate adversarial images using shallow and deep classifiers on the MNIST and ImageNet datasets. We probe the pixel space of adversarial images using noise of varying intensity and distribution. We bring novel visualizations that showcase the phenomenon and its high variability. We show that adversarial images appear in large regions in the pixel space, but that, for the same task, a shallow classifier seems more robust to adversarial images than a deep convolutional network.

cs.NE↗

arXiv2016

Deep Neural Networks Under Stress

In recent years, deep architectures have been used for transfer learning with state-of-the-art performance in many datasets. The properties of their features remain, however, largely unstudied under the transfer perspective. In this work, we present an extensive analysis of the resiliency of feature vectors extracted from deep models, with special focus on the trade-off between performance and compression rate. By introducing perturbations to image descriptions extracted from a deep convolutional neural network, we change their precision and number of dimensions, measuring how it affects the final score. We show that deep features are more robust to these disturbances when compared to classical approaches, achieving a compression rate of 98.4%, while losing only 0.88% of their original score for Pascal VOC 2007.

cs.CV↗

arXiv2016

Towards Automated Melanoma Screening: Proper Computer Vision & Reliable Results

In this paper we survey, analyze and criticize current art on automated melanoma screening, reimplementing a baseline technique, and proposing two novel ones. Melanoma, although highly curable when detected early, ends as one of the most dangerous types of cancer, due to delayed diagnosis and treatment. Its incidence is soaring, much faster than the number of trained professionals able to diagnose it. Automated screening appears as an alternative to make the most of those professionals, focusing their time on the patients at risk while safely discharging the other patients. However, the potential of automated melanoma diagnosis is currently unfulfilled, due to the emphasis of current literature on outdated computer vision models. Even more problematic is the irreproducibility of current art. We show how streamlined pipelines based upon current Computer Vision outperform conventional models - a model based on an advanced bags of words reaches an AUC of 84.6%, and a model based on deep neural networks reaches 89.3%, while the baseline (a classical bag of words) stays at 81.2%. We also initiate a dialog to improve reproducibility in our community

cs.CV↗

arXiv2015

Semantic Diversity versus Visual Diversity in Visual Dictionaries

Visual dictionaries are a critical component for image classification/retrieval systems based on the bag-of-visual-words (BoVW) model. Dictionaries are usually learned without supervision from a training set of images sampled from the collection of interest. However, for large, general-purpose, dynamic image collections (e.g., the Web), obtaining a representative sample in terms of semantic concepts is not straightforward. In this paper, we evaluate the impact of semantics in the dictionary quality, aiming at verifying the importance of semantic diversity in relation visual diversity for visual dictionaries. In the experiments, we vary the amount of classes used for creating the dictionary and then compute different BoVW descriptors, using multiple codebook sizes and different coding and pooling methods (standard BoVW and Fisher Vectors). Results for image classification show that as visual dictionaries are based on low-level visual appearances, visual diversity is more important than semantic diversity. Our conclusions open the opportunity to alleviate the burden in generating visual dictionaries as we need only a visually diverse set of images instead of the whole collection to create a good dictionary.

cs.CV↗

arXiv2013

Scalable Locality-Sensitive Hashing for Similarity Search in High-Dimensional, Large-Scale Multimedia Datasets

Similarity search is critical for many database applications, including the increasingly popular online services for Content-Based Multimedia Retrieval (CBMR). These services, which include image search engines, must handle an overwhelming volume of data, while keeping low response times. Thus, scalability is imperative for similarity search in Web-scale applications, but most existing methods are sequential and target shared-memory machines. Here we address these issues with a distributed, efficient, and scalable index based on Locality-Sensitive Hashing (LSH). LSH is one of the most efficient and popular techniques for similarity search, but its poor referential locality properties has made its implementation a challenging problem. Our solution is based on a widely asynchronous dataflow parallelization with a number of optimizations that include a hierarchical parallelization to decouple indexing and data storage, locality-aware data partition strategies to reduce message passing, and multi-probing to limit memory usage. The proposed parallelization attained an efficiency of 90% in a distributed system with about 800 CPU cores. In particular, the original locality-aware data partition reduced the number of messages exchanged in 30%. Our parallel LSH was evaluated using the largest public dataset for similarity search (to the best of our knowledge) with $10^9$ 128-d SIFT descriptors extracted from Web images. This is two orders of magnitude larger than datasets that previous LSH parallelizations could handle.

cs.DC↗

arXiv2012

Approximate Similarity Search for Online Multimedia Services on Distributed CPU-GPU Platforms

Similarity search in high-dimentional spaces is a pivotal operation found a variety of database applications. Recently, there has been an increase interest in similarity search for online content-based multimedia services. Those services, however, introduce new challenges with respect to the very large volumes of data that have to be indexed/searched, and the need to minimize response times observed by the end-users. Additionally, those users dynamically interact with the systems creating fluctuating query request rates, requiring the search algorithm to adapt in order to better utilize the underline hardware to reduce response times. In order to address these challenges, we introduce hypercurves, a flexible framework for answering approximate k-nearest neighbor (kNN) queries for very large multimedia databases, aiming at online content-based multimedia services. Hypercurves executes on hybrid CPU--GPU environments, and is able to employ those devices cooperatively to support massive query request rates. In order to keep the response times optimal as the request rates vary, it employs a novel dynamic scheduler to partition the work between CPU and GPU. Hypercurves was throughly evaluated using a large database of multimedia descriptors. Its cooperative CPU--GPU execution achieved performance improvements of up to 30x when compared to the single CPU-core version. The dynamic work partition mechanism reduces the observed query response times in about 50% when compared to the best static CPU--GPU task partition configuration. In addition, Hypercurves achieves superlinear scalability in distributed (multi-node) executions, while keeping a high guarantee of equivalence with its sequential version --- thanks to the proof of probabilistic equivalence, which supported its aggressive parallelization design.

cs.MM↗

arXiv2012

Are visual dictionaries generalizable?

Mid-level features based on visual dictionaries are today a cornerstone of systems for classification and retrieval of images. Those state-of-the-art representations depend crucially on the choice of a codebook (visual dictionary), which is usually derived from the dataset. In general-purpose, dynamic image collections (e.g., the Web), one cannot have the entire collection in order to extract a representative dictionary. However, based on the hypothesis that the dictionary reflects only the diversity of low-level appearances and does not capture semantics, we argue that a dictionary based on a small subset of the data, or even on an entirely different dataset, is able to produce a good representation, provided that the chosen images span a diverse enough portion of the low-level feature space. Our experiments confirm that hypothesis, opening the opportunity to greatly alleviate the burden in generating the codebook, and confirming the feasibility of employing visual dictionaries in large-scale dynamic environments.

cs.CV↗

arXiv2011

Content-Based Spam Filtering on Video Sharing Social Networks

In this work we are concerned with the detection of spam in video sharing social networks. Specifically, we investigate how much visual content-based analysis can aid in detecting spam in videos. This is a very challenging task, because of the high-level semantic concepts involved; of the assorted nature of social networks, preventing the use of constrained a priori information; and, what is paramount, of the context dependent nature of spam. Content filtering for social networks is an increasingly demanded task: due to their popularity, the number of abuses also tends to increase, annoying the user base and disrupting their services. We systematically evaluate several approaches for processing the visual information: using static and dynamic (motionaware) features, with and without considering the context, and with or without latent semantic analysis (LSA). Our experiments show that LSA is helpful, but taking the context into consideration is paramount. The whole scheme shows good results, showing the feasibility of the concept.

cs.CV↗

arXiv2011

Bayesian approach for near-duplicate image detection

In this paper we propose a bayesian approach for near-duplicate image detection, and investigate how different probabilistic models affect the performance obtained. The task of identifying an image whose metadata are missing is often demanded for a myriad of applications: metadata retrieval in cultural institutions, detection of copyright violations, investigation of latent cross-links in archives and libraries, duplicate elimination in storage management, etc. The majority of current solutions are based either on voting algorithms, which are very precise, but expensive; either on the use of visual dictionaries, which are efficient, but less precise. Our approach, uses local descriptors in a novel way, which by a careful application of decision theory, allows a very fine control of the compromise between precision and efficiency. In addition, the method attains a great compromise between those two axes, with more than 99% accuracy with less than 10 database operations.

cs.CV↗