arXiv subjects

Radu Tudor Ionescu

Publications and source records attributed to Radu Tudor Ionescu.

At least 109 records · Page 6Linked to original sources

arXiv2021

UnibucKernel: Geolocating Swiss German Jodels Using Ensemble Learning

In this work, we describe our approach addressing the Social Media Variety Geolocation task featured in the 2021 VarDial Evaluation Campaign. We focus on the second subtask, which is based on a data set formed of approximately 30 thousand Swiss German Jodels. The dialect identification task is about accurately predicting the latitude and longitude of test samples. We frame the task as a double regression problem, employing an XGBoost meta-learner with the combined power of a variety of machine learning approaches to predict both latitude and longitude. The models included in our ensemble range from simple regression techniques, such as Support Vector Regression, to deep neural models, such as a hybrid neural network and a neural transformer. To minimize the prediction error, we approach the problem from a few different perspectives and consider various types of features, from low-level character n-grams to high-level BERT embeddings. The XGBoost ensemble resulted from combining the power of the aforementioned methods achieves a median distance of 23.6 km on the test data, which places us on the third place in the ranking, at a difference of 6.05 km and 2.9 km from the submissions on the first and second places, respectively.

cs.CL↗

arXiv2021

Teacher-Student Training and Triplet Loss for Facial Expression Recognition under Occlusion

In this paper, we study the task of facial expression recognition under strong occlusion. We are particularly interested in cases where 50% of the face is occluded, e.g. when the subject wears a Virtual Reality (VR) headset. While previous studies show that pre-training convolutional neural networks (CNNs) on fully-visible (non-occluded) faces improves the accuracy, we propose to employ knowledge distillation to achieve further improvements. First of all, we employ the classic teacher-student training strategy, in which the teacher is a CNN trained on fully-visible faces and the student is a CNN trained on occluded faces. Second of all, we propose a new approach for knowledge distillation based on triplet loss. During training, the goal is to reduce the distance between an anchor embedding, produced by a student CNN that takes occluded faces as input, and a positive embedding (from the same class as the anchor), produced by a teacher CNN trained on fully-visible faces, so that it becomes smaller than the distance between the anchor and a negative embedding (from a different class than the anchor), produced by the student CNN. Third of all, we propose to combine the distilled embeddings obtained through the classic teacher-student strategy and our novel teacher-student strategy based on triplet loss into a single embedding vector. We conduct experiments on two benchmarks, FER+ and AffectNet, with two CNN architectures, VGG-f and VGG-face, showing that knowledge distillation can bring significant improvements over the state-of-the-art methods designed for occluded faces in the VR setting.

cs.CV↗

arXiv2021

Curriculum Self-Paced Learning for Cross-Domain Object Detection

Training (source) domain bias affects state-of-the-art object detectors, such as Faster R-CNN, when applied to new (target) domains. To alleviate this problem, researchers proposed various domain adaptation methods to improve object detection results in the cross-domain setting, e.g. by translating images with ground-truth labels from the source domain to the target domain using Cycle-GAN. On top of combining Cycle-GAN transformations and self-paced learning in a smart and efficient way, in this paper, we propose a novel self-paced algorithm that learns from easy to hard. Our method is simple and effective, without any overhead during inference. It uses only pseudo-labels for samples taken from the target domain, i.e. the domain adaptation is unsupervised. We conduct experiments on four cross-domain benchmarks, showing better results than the state of the art. We also perform an ablation study demonstrating the utility of each component in our framework. Additionally, we study the applicability of our framework to other object detectors. Furthermore, we compare our difficulty measure with other measures from the related literature, proving that it yields superior results and that it correlates well with the performance metric.

cs.CV↗

arXiv2021

Clustering Word Embeddings with Self-Organizing Maps. Application on LaRoSeDa -- A Large Romanian Sentiment Data Set

Romanian is one of the understudied languages in computational linguistics, with few resources available for the development of natural language processing tools. In this paper, we introduce LaRoSeDa, a Large Romanian Sentiment Data Set, which is composed of 15,000 positive and negative reviews collected from one of the largest Romanian e-commerce platforms. We employ two sentiment classification methods as baselines for our new data set, one based on low-level features (character n-grams) and one based on high-level features (bag-of-word-embeddings generated by clustering word embeddings with k-means). As an additional contribution, we replace the k-means clustering algorithm with self-organizing maps (SOMs), obtaining better results because the generated clusters of word embeddings are closer to the Zipf's law distribution, which is known to govern natural language. We also demonstrate the generalization capacity of using SOMs for the clustering of word embeddings on another recently-introduced Romanian data set, for text categorization by topic.

cs.CL↗

arXiv2020

Natural vs Balanced Distribution in Deep Learning on Whole Slide Images for Cancer Detection

The class distribution of data is one of the factors that regulates the performance of machine learning models. However, investigations on the impact of different distributions available in the literature are very few, sometimes absent for domain-specific tasks. In this paper, we analyze the impact of natural and balanced distributions of the training set in deep learning (DL) models applied on histological images, also known as whole slide images (WSIs). WSIs are considered as the gold standard for cancer diagnosis. In recent years, researchers have turned their attention to DL models to automate and accelerate the diagnosis process. In the training of such DL models, filtering out the non-regions-of-interest from the WSIs and adopting an artificial distribution (usually, a balanced distribution) is a common trend. In our analysis, we show that keeping the WSIs data in their usual distribution (which we call natural distribution) for DL training produces fewer false positives (FPs) with comparable false negatives (FNs) than the artificially-obtained balanced distribution. We conduct an empirical comparative study with 10 random folds for each distribution, comparing the resulting average performance levels in terms of five different evaluation metrics. Experimental results show the effectiveness of the natural distribution over the balanced one across all the evaluation metrics.

cs.CV↗

arXiv2020

Adversarial Attacks on Deep Learning Systems for User Identification based on Motion Sensors

For the time being, mobile devices employ implicit authentication mechanisms, namely, unlock patterns, PINs or biometric-based systems such as fingerprint or face recognition. While these systems are prone to well-known attacks, the introduction of an explicit and unobtrusive authentication layer can greatly enhance security. In this study, we focus on deep learning methods for explicit authentication based on motion sensor signals. In this scenario, attackers could craft adversarial examples with the aim of gaining unauthorized access and even restraining a legitimate user to access his mobile device. To our knowledge, this is the first study that aims at quantifying the impact of adversarial attacks on machine learning models used for user identification based on motion sensors. To accomplish our goal, we study multiple methods for generating adversarial examples. We propose three research questions regarding the impact and the universality of adversarial examples, conducting relevant experiments in order to answer our research questions. Our empirical results demonstrate that certain adversarial example generation methods are specific to the attacked classification model, while others tend to be generic. We thus conclude that deep neural networks trained for user identification tasks based on motion sensors are subject to a high percentage of misclassification when given adversarial input.

cs.LG↗

arXiv2020

SuPEr-SAM: Using the Supervision Signal from a Pose Estimator to Train a Spatial Attention Module for Personal Protective Equipment Recognition

We propose a deep learning method to automatically detect personal protective equipment (PPE), such as helmets, surgical masks, reflective vests, boots and so on, in images of people. Typical approaches for PPE detection based on deep learning are (i) to train an object detector for items such as those listed above or (ii) to train a person detector and a classifier that takes the bounding boxes predicted by the detector and discriminates between people wearing and people not wearing the corresponding PPE items. We propose a novel and accurate approach that uses three components: a person detector, a body pose estimator and a classifier. Our novelty consists in using the pose estimator only at training time, to improve the prediction performance of the classifier. We modify the neural architecture of the classifier by adding a spatial attention mechanism, which is trained using supervision signal from the pose estimator. In this way, the classifier learns to focus on PPE items, using knowledge from the pose estimator with almost no computational overhead during inference.

cs.CV↗

arXiv2020

Black-Box Ripper: Copying black-box models using generative evolutionary algorithms

We study the task of replicating the functionality of black-box neural models, for which we only know the output class probabilities provided for a set of input images. We assume back-propagation through the black-box model is not possible and its training images are not available, e.g. the model could be exposed only through an API. In this context, we present a teacher-student framework that can distill the black-box (teacher) model into a student model with minimal accuracy loss. To generate useful data samples for training the student, our framework (i) learns to generate images on a proxy data set (with images and classes different from those used to train the black-box) and (ii) applies an evolutionary strategy to make sure that each generated data sample exhibits a high response for a specific class when given as input to the black box. Our framework is compared with several baseline and state-of-the-art methods on three benchmark data sets. The empirical evidence indicates that our model is superior to the considered baselines. Although our method does not back-propagate through the black-box network, it generally surpasses state-of-the-art methods that regard the teacher as a glass-box model. Our code is available at: https://github.com/antoniobarbalau/black-box-ripper.

cs.CV↗

arXiv2020

Combining Deep Learning and String Kernels for the Localization of Swiss German Tweets

In this work, we introduce the methods proposed by the UnibucKernel team in solving the Social Media Variety Geolocation task featured in the 2020 VarDial Evaluation Campaign. We address only the second subtask, which targets a data set composed of nearly 30 thousand Swiss German Jodels. The dialect identification task is about accurately predicting the latitude and longitude of test samples. We frame the task as a double regression problem, employing a variety of machine learning approaches to predict both latitude and longitude. From simple models for regression, such as Support Vector Regression, to deep neural networks, such as Long Short-Term Memory networks and character-level convolutional neural networks, and, finally, to ensemble models based on meta-learners, such as XGBoost, our interest is focused on approaching the problem from a few different perspectives, in an attempt to minimize the prediction error. With the same goal in mind, we also considered many types of features, from high-level features, such as BERT embeddings, to low-level features, such as characters n-grams, which are known to provide good results in dialect identification. Our empirical results indicate that the handcrafted model based on string kernels outperforms the deep learning approaches. Nevertheless, our best performance is given by the ensemble model that combines both handcrafted and deep learning models.

cs.CL↗

arXiv2020

Accurate and Efficient Intracranial Hemorrhage Detection and Subtype Classification in 3D CT Scans with Convolutional and Long Short-Term Memory Neural Networks

In this paper, we present our system for the RSNA Intracranial Hemorrhage Detection challenge. The proposed system is based on a lightweight deep neural network architecture composed of a convolutional neural network (CNN) that takes as input individual CT slices, and a Long Short-Term Memory (LSTM) network that takes as input feature embeddings provided by the CNN. For efficient processing, we consider various feature selection methods to produce a subset of useful CNN features for the LSTM. Furthermore, we reduce the CT slices by a factor of 2x, allowing ourselves to train the model faster. Even if our model is designed to balance speed and accuracy, we report a weighted mean log loss of 0.04989 on the final test set, which places us in the top 30 ranking (2%) from a total of 1345 participants. Although our computing infrastructure does not allow it, processing CT slices at their original scale is likely to improve performance. In order to enable others to reproduce our results, we provide our code as open source at https://github.com/warchildmd/ihd. After the challenge, we conducted a subjective intracranial hemorrhage detection assessment by radiologists, indicating that the performance of our deep model is on par with that of doctors specialized in reading CT scans. Another contribution of our work is to integrate Grad-CAM visualizations in our system, providing useful explanations for its predictions. We therefore consider our system as a viable option when a fast diagnosis or a second opinion on intracranial hemorrhage detection are needed.

cs.CV↗

arXiv2020

To augment or not to augment? Data augmentation in user identification based on motion sensors

Nowadays, commonly-used authentication systems for mobile device users, e.g. password checking, face recognition or fingerprint scanning, are susceptible to various kinds of attacks. In order to prevent some of the possible attacks, these explicit authentication systems can be enhanced by considering a two-factor authentication scheme, in which the second factor is an implicit authentication system based on analyzing motion sensor data captured by accelerometers or gyroscopes. In order to avoid any additional burdens to the user, the registration process of the implicit authentication system must be performed quickly, i.e. the number of data samples collected from the user is typically small. In the context of designing a machine learning model for implicit user authentication based on motion signals, data augmentation can play an important role. In this paper, we study several data augmentation techniques in the quest of finding useful augmentation methods for motion sensor data. We propose a set of four research questions related to data augmentation in the context of few-shot user identification based on motion sensor signals. We conduct experiments on a benchmark data set, using two deep learning architectures, convolutional neural networks and Long Short-Term Memory networks, showing which and when data augmentation methods bring accuracy improvements. Interestingly, we find that data augmentation is not very helpful, most likely because the signal patterns useful to discriminate users are too sensitive to the transformations brought by certain data augmentation techniques. This result is somewhat contradictory to the common belief that data augmentation is expected to increase the accuracy of machine learning models.

cs.CV↗

arXiv2020

A Generic and Model-Agnostic Exemplar Synthetization Framework for Explainable AI

With the growing complexity of deep learning methods adopted in practical applications, there is an increasing and stringent need to explain and interpret the decisions of such methods. In this work, we focus on explainable AI and propose a novel generic and model-agnostic framework for synthesizing input exemplars that maximize a desired response from a machine learning model. To this end, we use a generative model, which acts as a prior for generating data, and traverse its latent space using a novel evolutionary strategy with momentum updates. Our framework is generic because (i) it can employ any underlying generator, e.g. Variational Auto-Encoders (VAEs) or Generative Adversarial Networks (GANs), and (ii) it can be applied to any input data, e.g. images, text samples or tabular data. Since we use a zero-order optimization method, our framework is model-agnostic, in the sense that the machine learning model that we aim to explain is a black-box. We stress out that our novel framework does not require access or knowledge of the internal structure or the training data of the black-box model. We conduct experiments with two generative models, VAEs and GANs, and synthesize exemplars for various data formats, image, text and tabular, demonstrating that our framework is generic. We also employ our prototype synthetization framework on various black-box models, for which we only know the input and the output formats, showing that it is model-agnostic. Moreover, we compare our framework (available at https://github.com/antoniobarbalau/exemplar) with a model-dependent approach based on gradient descent, proving that our framework obtains equally-good exemplars in a shorter computational time.

cs.LG↗

arXiv2020

Are you wearing a mask? Improving mask detection from speech using augmentation by cycle-consistent GANs

The task of detecting whether a person wears a face mask from speech is useful in modelling speech in forensic investigations, communication between surgeons or people protecting themselves against infectious diseases such as COVID-19. In this paper, we propose a novel data augmentation approach for mask detection from speech. Our approach is based on (i) training Generative Adversarial Networks (GANs) with cycle-consistency loss to translate unpaired utterances between two classes (with mask and without mask), and on (ii) generating new training utterances using the cycle-consistent GANs, assigning opposite labels to each translated utterance. Original and translated utterances are converted into spectrograms which are provided as input to a set of ResNet neural networks with various depths. The networks are combined into an ensemble through a Support Vector Machines (SVM) classifier. With this system, we participated in the Mask Sub-Challenge (MSC) of the INTERSPEECH 2020 Computational Paralinguistics Challenge, surpassing the baseline proposed by the organizers by 2.8%. Our data augmentation technique provided a performance boost of 0.9% on the private test set. Furthermore, we show that our data augmentation approach yields better results than other baseline and state-of-the-art augmentation methods.

eess.AS↗

arXiv2020

Fully Convolutional Neural Networks for Automotive Radar Interference Mitigation

The interest of the automotive industry has progressively focused on subjects related to driver assistance systems as well as autonomous cars. Cars combine a variety of sensors to perceive their surroundings robustly. Among them, radar sensors are indispensable because of their independence of lighting conditions and the possibility to directly measure velocity. However, radar interference is an issue that becomes prevalent with the increasing amount of radar systems in automotive scenarios. In this paper, we address this issue for frequency modulated continuous wave (FMCW) radars with fully convolutional neural networks (FCNs), a state-of-the-art deep learning technique. We propose two FCNs that take spectrograms of the beat signals as input, and provide the corresponding clean range profiles as output. We propose two architectures for interference mitigation which outperform the classical zeroing technique. Moreover, considering the lack of databases for this task, we release as open source a large scale data set that closely replicates real world automotive scenarios for single-interference cases, allowing others to objectively compare their future work in this domain. The data set is available for download at: http://github.com/ristea/arim.

eess.SP↗

arXiv2020

Convolutional Neural Networks for User Identificationbased on Motion Sensors Represented as Image

In this paper, we propose a deep learning approach for smartphone user identification based on analyzing motion signals recorded by the accelerometer and the gyroscope, during a single tap gesture performed by the user on the screen. We transform the discrete 3-axis signals from the motion sensors into a gray-scale image representation which is provided as input to a convolutional neural network (CNN) that is pre-trained for multi-class user classification. In the pre-training stage, we benefit from different users and multiple samples per user. After pre-training, we use our CNN as feature extractor, generating an embedding associated to each single tap on the screen. The resulting embeddings are used to train a Support Vector Machines (SVM) model in a few-shot user identification setting, i.e. requiring only 20 taps on the screen during the registration phase. We compare our identification system based on CNN features with two baseline systems, one that employs handcrafted features and another that employs recurrent neural network (RNN) features. All systems are based on the same classifier, namely SVM. To pre-train the CNN and the RNN models for multi-class user classification, we use a different set of users than the set used for few-shot user identification, ensuring a realistic scenario. The empirical results demonstrate that our CNN model yields a top accuracy of 89.75% in multi-class user classification and a top accuracy of 96.72% in few-shot user identification. In conclusion, we believe that our system is ready for practical use, having a better generalization capacity than both baselines.

cs.LG↗

arXiv2020

Local Learning with Deep and Handcrafted Features for Facial Expression Recognition

We present an approach that combines automatic features learned by convolutional neural networks (CNN) and handcrafted features computed by the bag-of-visual-words (BOVW) model in order to achieve state-of-the-art results in facial expression recognition. To obtain automatic features, we experiment with multiple CNN architectures, pre-trained models and training procedures, e.g. Dense-Sparse-Dense. After fusing the two types of features, we employ a local learning framework to predict the class label for each test image. The local learning framework is based on three steps. First, a k-nearest neighbors model is applied in order to select the nearest training samples for an input test image. Second, a one-versus-all Support Vector Machines (SVM) classifier is trained on the selected training samples. Finally, the SVM classifier is used to predict the class label only for the test image it was trained for. Although we have used local learning in combination with handcrafted features in our previous work, to the best of our knowledge, local learning has never been employed in combination with deep features. The experiments on the 2013 Facial Expression Recognition (FER) Challenge data set, the FER+ data set and the AffectNet data set demonstrate that our approach achieves state-of-the-art results. With a top accuracy of 75.42% on FER 2013, 87.76% on the FER+, 59.58% on AffectNet 8-way classification and 63.31% on AffectNet 7-way classification, we surpass the state-of-the-art methods by more than 1% on all data sets.

cs.CV↗

arXiv2019

Forward and Backward Feature Selection for Query Performance Prediction

The goal of query performance prediction (QPP) is to automatically estimate the effectiveness of a search result for any given query, without relevance judgements. Post-retrieval features have been shown to be more effective for this task while being more expensive to compute than pre-retrieval features. Combining multiple post-retrieval features is even more effective, but state-of-the-art QPP methods are impossible to interpret because of the black-box nature of the employed machine learning models. However, interpretation is useful for understanding the predictive model and providing more answers about its behavior. Moreover, combining many post-retrieval features is not applicable to real-world cases, since the query running time is of utter importance. In this paper, we investigate a new framework for feature selection in which the trained model explains well the prediction. We introduce a step-wise (forward and backward) model selection approach where different subsets of query features are used to fit different models from which the system selects the best one. We evaluate our approach on four TREC collections using standard QPP features. We also develop two QPP features to address the issue of query-drift in the query feedback setting. We found that: (1) our model based on a limited number of selected features is as good as more complex models for QPP and better than non-selective models; (2) our model is more efficient than complex models during inference time since it requires fewer features; (3) the predictive model is readable and understandable; and (4) one of our new QPP features is consistently selected across different collections, proving its usefulness.

cs.IR↗

arXiv2019

Recognizing Facial Expressions of Occluded Faces using Convolutional Neural Networks

In this paper, we present an approach based on convolutional neural networks (CNNs) for facial expression recognition in a difficult setting with severe occlusions. More specifically, our task is to recognize the facial expression of a person wearing a virtual reality (VR) headset which essentially occludes the upper part of the face. In order to accurately train neural networks for this setting, in which faces are severely occluded, we modify the training examples by intentionally occluding the upper half of the face. This forces the neural networks to focus on the lower part of the face and to obtain better accuracy rates than models trained on the entire faces. Our empirical results on two benchmark data sets, FER+ and AffectNet, show that our CNN models' predictions on lower-half faces are up to 13% higher than the baseline CNN models trained on entire faces, proving their suitability for the VR setting. Furthermore, our models' predictions on lower-half faces are no more than 10% under the baseline models' predictions on full faces, proving that there are enough clues in the lower part of the face to accurately predict facial expressions.

cs.CV↗