David Macêdo

David Macêdo, Cleber Zanchettin, Teresa Ludermir

Building robust deterministic neural networks remains a challenge. On the one hand, some approaches improve out-of-distribution detection at the cost of reducing classification accuracy in some situations. On the other hand, some methods simultaneously increase classification accuracy, uncertainty estimation, and out-of-distribution detection at the expense of reducing the inference efficiency. In this paper, we propose training deterministic neural networks using our DisMax loss, which works as a drop-in replacement for the usual SoftMax loss (i.e., the combination of the linear output layer, the SoftMax activation, and the cross-entropy loss). Starting from the IsoMax+ loss, we create each logit based on the distances to all prototypes, rather than just the one associated with the correct class. We also introduce a mechanism to combine images to construct what we call fractional probability regularization. Moreover, we present a fast way to calibrate the network after training. Finally, we propose a composite score to perform out-of-distribution detection. Our experiments show that DisMax usually outperforms current approaches simultaneously in classification accuracy, uncertainty estimation, and out-of-distribution detection while maintaining deterministic neural network inference efficiency. The code to reproduce the results is available at https://github.com/dlmacedo/distinction-maximization-loss.

David Macêdo, Teresa Ludermir

Current out-of-distribution detection approaches usually present special requirements (e.g., collecting outlier data and hyperparameter validation) and produce side effects (e.g., classification accuracy drop and slow/inefficient inferences). Recently, entropic out-of-distribution detection has been proposed as a seamless approach (i.e., a solution that avoids all previously mentioned drawbacks). The entropic out-of-distribution detection solution uses the IsoMax loss for training and the entropic score for out-of-distribution detection. The IsoMax loss works as a drop-in replacement of the SoftMax loss (i.e., the combination of the output linear layer, the SoftMax activation, and the cross-entropy loss) because swapping the SoftMax loss with the IsoMax loss requires no changes in the model's architecture or training procedures/hyperparameters. In this paper, we perform what we call an isometrization of the distances used in the IsoMax loss. Additionally, we propose replacing the entropic score with the minimum distance score. Experiments showed that these modifications significantly increase out-of-distribution detection performance while keeping the solution seamless. Besides being competitive with or outperforming all major current approaches, the proposed solution avoids all their current limitations, in addition to being much easier to use because only a simple loss replacement for training the neural network is required. The code to replace the SoftMax loss with the IsoMax+ loss and reproduce the results is available at https://github.com/dlmacedo/entropic-out-of-distribution-detection.

Heitor Felix, Walber M. Rodrigues, David Macêdo et al.

The detection of objects considering a 6DoF pose is a common requirement to build virtual and augmented reality applications. It is usually a complex task which requires real-time processing and high precision results for adequate user experience. Recently, different deep learning techniques have been proposed to detect objects in 6DoF in RGB images. However, they rely on high complexity networks, requiring a computational power that prevents them from working on mobile devices. In this paper, we propose an approach to reduce the complexity of 6DoF detection networks while maintaining accuracy. We used Knowledge Distillation to teach portables Convolutional Neural Networks (CNN) to learn from a real-time 6DoF detection CNN. The proposed method allows real-time applications using only RGB images while decreasing the hardware requirements. We used the LINEMOD dataset to evaluate the proposed method, and the experimental results show that the proposed method reduces the memory requirement by almost 99\% in comparison to the original architecture with the cost of reducing half the accuracy in one of the metrics. Code is available at https://github.com/heitorcfelix/singleshot6Dpose.

David Macêdo

Current deep learning solutions are well known for not informing whether they can reliably classify an example during inference. One of the most effective ways to build more reliable deep learning solutions is to improve their performance in the so-called out-of-distribution detection task, which essentially consists of "know that you do not know" or "know the unknown". In other words, out-of-distribution detection capable systems may reject performing a nonsense classification when submitted to instances of classes on which the neural network was not trained. This thesis tackles the defiant out-of-distribution detection task by proposing novel loss functions and detection scores. Uncertainty estimation is also a crucial auxiliary task in building more robust deep learning systems. Therefore, we also deal with this robustness-related task, which evaluates how realistic the probabilities presented by the deep neural network are. To demonstrate the effectiveness of our approach, in addition to a substantial set of experiments, which includes state-of-the-art results, we use arguments based on the principle of maximum entropy to establish the theoretical foundation of the proposed approaches. Unlike most current methods, our losses and scores are seamless and principled solutions that produce accurate predictions in addition to fast and efficient inference. Moreover, our approaches can be incorporated into current and future projects simply by replacing the loss used to train the deep neural network and computing a rapid score for detection.

Willams Costa, David Macêdo, Cleber Zanchettin et al.

Expressing and identifying emotions through facial and physical expressions is a significant part of social interaction. Emotion recognition is an essential task in computer vision due to its various applications and mainly for allowing a more natural interaction between humans and machines. The common approaches for emotion recognition focus on analyzing facial expressions and requires the automatic localization of the face in the image. Although these methods can correctly classify emotion in controlled scenarios, such techniques are limited when dealing with unconstrained daily interactions. We propose a new deep learning approach for emotion recognition based on adaptive multi-cues that extract information from context and body poses, which humans commonly use in social interaction and communication. We compare the proposed approach with the state-of-art approaches in the CAER-S dataset, evaluating different components in a pipeline that reached an accuracy of 89.30%

David Macêdo, Pedro Dreyer, Teresa Ludermir et al.

Proper optimization of deep neural networks is an open research question since an optimal procedure to change the learning rate throughout training is still unknown. Manually defining a learning rate schedule involves troublesome time-consuming try and error procedures to determine hyperparameters such as learning rate decay epochs and learning rate decay rates. Although adaptive learning rate optimizers automatize this process, recent studies suggest they may produce overffiting and reduce performance when compared to fine-tuned learning rate schedules. Considering that deep neural networks loss functions present landscapes with much more saddle points than local minima, we proposed the Training Aware Sigmoidal Optimizer (TASO), which consists of a two-phases automated learning rate schedule. The first phase uses a high learning rate to fast traverse the numerous saddle point, while the second phase uses low learning rate to slowly approach the center of the local minimum previously found. We compared the proposed approach with commonly used adaptive learning rate schedules such as Adam, RMSProp, and Adagrad. Our experiments showed that TASO outperformed all competing methods in both optimal (i.e., performing hyperparameter validation) and suboptimal (i.e., using default hyperparameters) scenarios.

Angel Ayala, Bruno Fernandes, Francisco Cruz et al.

Most of the automatic fire alarm systems detect the fire presence through sensors like thermal, smoke, or flame. One of the new approaches to the problem is the use of images to perform the detection. The image approach is promising since it does not need specific sensors and can be easily embedded in different devices. However, besides the high performance, the computational cost of the used deep learning methods is a challenge to their deployment in portable devices. In this work, we propose a new deep learning architecture that requires fewer floating-point operations (flops) for fire recognition. Additionally, we propose a portable approach for fire recognition and the use of modern techniques such as inverted residual block, convolutions like depth-wise, and octave, to reduce the model's computational cost. The experiments show that our model keeps high accuracy while substantially reducing the number of parameters and flops. One of our models presents 71\% fewer parameters than FireNet, while still presenting competitive accuracy and AUROC performance. The proposed methods are evaluated on FireNet and FiSmo datasets. The obtained results are promising for the implementation of the model in a mobile device, considering the reduced number of flops and parameters acquired.

David Macêdo, Tsang Ing Ren, Cleber Zanchettin et al.

In this paper, we argue that the unsatisfactory out-of-distribution (OOD) detection performance of neural networks is mainly due to the SoftMax loss anisotropy and propensity to produce low entropy probability distributions in disagreement with the principle of maximum entropy. Current out-of-distribution (OOD) detection approaches usually do not directly fix the SoftMax loss drawbacks, but rather build techniques to circumvent it. Unfortunately, those methods usually produce undesired side effects (e.g., classification accuracy drop, additional hyperparameters, slower inferences, and collecting extra data). In the opposite direction, we propose replacing SoftMax loss with a novel loss function that does not suffer from the mentioned weaknesses. The proposed IsoMax loss is isotropic (exclusively distance-based) and provides high entropy posterior probability distributions. Replacing the SoftMax loss by IsoMax loss requires no model or training changes. Additionally, the models trained with IsoMax loss produce as fast and energy-efficient inferences as those trained using SoftMax loss. Moreover, no classification accuracy drop is observed. The proposed method does not rely on outlier/background data, hyperparameter tuning, temperature calibration, feature extraction, metric learning, adversarial training, ensemble procedures, or generative models. Our experiments showed that IsoMax loss works as a seamless SoftMax loss drop-in replacement that significantly improves neural networks' OOD detection performance. Hence, it may be used as a baseline OOD detection approach to be combined with current or future OOD detection techniques to achieve even higher results.

Johny Moreira, Chaina Oliveira, David Macêdo et al.

Relation extraction (RE) consists in categorizing the relationship between entities in a sentence. A recent paradigm to develop relation extractors is Distant Supervision (DS), which allows the automatic creation of new datasets by taking an alignment between a text corpus and a Knowledge Base (KB). KBs can sometimes also provide additional information to the RE task. One of the methods that adopt this strategy is the RESIDE model, which proposes a distantly-supervised neural relation extraction using side information from KBs. Considering that this method outperformed state-of-the-art baselines, in this paper, we propose a related approach to RESIDE also using additional side information, but simplifying the sentence encoding with BERT embeddings. Through experiments, we show the effectiveness of the proposed method in Google Distant Supervision and Riedel datasets concerning the BGWA and RESIDE baseline methods. Although Area Under the Curve is decreased because of unbalanced datasets, P@N results have shown that the use of BERT as sentence encoding allows superior performance to baseline methods.

Ricardo Batista das Neves Junior, Luiz Felipe Verçosa, David Macêdo et al.

The Know Your Customer (KYC) and Anti Money Laundering (AML) are worldwide practices to online customer identification based on personal identification documents, similarity and liveness checking, and proof of address. To answer the basic regulation question: are you whom you say you are? The customer needs to upload valid identification documents (ID). This task imposes some computational challenges since these documents are diverse, may present different and complex backgrounds, some occlusion, partial rotation, poor quality, or damage. Advanced text and document segmentation algorithms were used to process the ID images. In this context, we investigated a method based on U-Net to detect the document edges and text regions in ID images. Besides the promising results on image segmentation, the U-Net based approach is computationally expensive for a real application, since the image segmentation is a customer device task. We propose a model optimization based on Octave Convolutions to qualify the method to situations where storage, processing, and time resources are limited, such as in mobile and robotic applications. We conducted the evaluation experiments in two new datasets CDPhotoDataset and DTDDataset, which are composed of real ID images of Brazilian documents. Our results showed that the proposed models are efficient to document segmentation tasks and portable.

João Antônio Chagas Nunes, David Macêdo, Cleber Zanchettin

Speaker Recognition and Speaker Identification are challenging tasks with essential applications such as automation, authentication, and security. Deep learning approaches like SincNet and AM-SincNet presented great results on these tasks. The promising performance took these models to real-world applications that becoming fundamentally end-user driven and mostly mobile. The mobile computation requires applications with reduced storage size, non-processing and memory intensive and efficient energy-consuming. The deep learning approaches, in contrast, usually are energy expensive, demanding storage, processing power, and memory. To address this demand, we propose a portable model called Additive Margin MobileNet1D (AM-MobileNet1D) to Speaker Identification on mobile devices. We evaluated the proposed approach on TIMIT and MIT datasets obtaining equivalent or better performances concerning the baseline methods. Additionally, the proposed model takes only 11.6 megabytes on disk storage against 91.2 from SincNet and AM-SincNet architectures, making the model seven times faster, with eight times fewer parameters.

David Macêdo, Tsang Ing Ren, Cleber Zanchettin et al.

Out-of-distribution (OOD) detection approaches usually present special requirements (e.g., hyperparameter validation, collection of outlier data) and produce side effects (e.g., classification accuracy drop, slower energy-inefficient inferences). We argue that these issues are a consequence of the SoftMax loss anisotropy and disagreement with the maximum entropy principle. Thus, we propose the IsoMax loss and the entropic score. The seamless drop-in replacement of the SoftMax loss by IsoMax loss requires neither additional data collection nor hyperparameter validation. The trained models do not exhibit classification accuracy drop and produce fast energy-efficient inferences. Moreover, our experiments show that training neural networks with IsoMax loss significantly improves their OOD detection performance. The IsoMax loss exhibits state-of-the-art performance under the mentioned conditions (fast energy-efficient inference, no classification accuracy drop, no collection of outlier data, and no hyperparameter validation), which we call the seamless OOD detection task. In future work, current OOD detection methods may replace the SoftMax loss with the IsoMax loss to improve their performance on the commonly studied non-seamless OOD detection problem.

Cleison Correia de Amorim, David Macêdo, Cleber Zanchettin

The recognition of sign language is a challenging task with an important role in society to facilitate the communication of deaf persons. We propose a new approach of Spatial-Temporal Graph Convolutional Network to sign language recognition based on the human skeletal movements. The method uses graphs to capture the signs dynamics in two dimensions, spatial and temporal, considering the complex aspects of the language. Additionally, we present a new dataset of human skeletons for sign language based on ASLLVD to contribute to future related studies.

Jefferson L. P. Lima, David Macêdo, Cleber Zanchettin

Cardiovascular diseases are one of the most common causes of death in the world. Prevention, knowledge of previous cases in the family, and early detection is the best strategy to reduce this fact. Different machine learning approaches to automatic diagnostic are being proposed to this task. As in most health problems, the imbalance between examples and classes is predominant in this problem and affects the performance of the automated solution. In this paper, we address the classification of heartbeats images in different cardiovascular diseases. We propose a two-dimensional Convolutional Neural Network for classification after using a InfoGAN architecture for generating synthetic images to unbalanced classes. We call this proposal Adversarial Oversampling and compare it with the classical oversampling methods as SMOTE, ADASYN, and RandomOversampling. The results show that the proposed approach improves the classifier performance for the minority classes without harming the performance in the balanced classes.

Andréa B. Duque, Luã Lázaro J. Santos, David Macêdo et al.

Most of the research in convolutional neural networks has focused on increasing network depth to improve accuracy, resulting in a massive number of parameters which restricts the trained network to platforms with memory and processing constraints. We propose to modify the structure of the Very Deep Convolutional Neural Networks (VDCNN) model to fit mobile platforms constraints and keep performance. In this paper, we evaluate the impact of Temporal Depthwise Separable Convolutions and Global Average Pooling in the network parameters, storage size, and latency. The squeezed model (SVDCNN) is between 10x and 20x smaller, depending on the network depth, maintaining a maximum size of 6MB. Regarding accuracy, the network experiences a loss between 0.4% and 1.3% and obtains lower latencies compared to the baseline model.

João Antônio Chagas Nunes, David Macêdo, Cleber Zanchettin

Speaker Recognition is a challenging task with essential applications such as authentication, automation, and security. The SincNet is a new deep learning based model which has produced promising results to tackle the mentioned task. To train deep learning systems, the loss function is essential to the network performance. The Softmax loss function is a widely used function in deep learning methods, but it is not the best choice for all kind of problems. For distance-based problems, one new Softmax based loss function called Additive Margin Softmax (AM-Softmax) is proving to be a better choice than the traditional Softmax. The AM-Softmax introduces a margin of separation between the classes that forces the samples from the same class to be closer to each other and also maximizes the distance between classes. In this paper, we propose a new approach for speaker recognition systems called AM-SincNet, which is based on the SincNet but uses an improved AM-Softmax layer. The proposed method is evaluated in the TIMIT dataset and obtained an improvement of approximately 40% in the Frame Error Rate compared to SincNet.

Jader Abreu, Luis Fred, David Macêdo et al.

Document classification is a challenging task with important applications. The deep learning approaches to the problem have gained much attention recently. Despite the progress, the proposed models do not incorporate the knowledge of the document structure in the architecture efficiently and not take into account the contexting importance of words and sentences. In this paper, we propose a new approach based on a combination of convolutional neural networks, gated recurrent units, and attention mechanisms for document classification tasks. The main contribution of this work is the use of convolution layers to extract more meaningful, generalizable and abstract features by the hierarchical representation. The proposed method in this paper improves the results of the current attention-based approaches for document classification.