Rapid growth in delivery and freight transportation is increasing in urban areas; as a result the use of delivery trucks and light commercial vehicles is evolving. Major cities can use traffic counting as a tool to monitor the presence of delivery vehicles in order to implement intelligent city planning measures. Classical methods for counting vehicles use mechanical, electromagnetic or pneumatic sensors, but these devices are costly, difficult to implement and only detect the presence of vehicles without giving information about their category, model or trajectory. This paper proposes a Deep Learning tool for classifying vehicles in a given image while considering different categories of logistic vehicles, namely: light-duty, medium-duty and heavy-duty vehicles. The proposed approach yields two main contributions: first we developed an architecture to create an annotated and balanced database of logistic vehicles, reducing manual annotation efforts. Second, we built a classifier that accurately classifies the logistic vehicles passing through a given road. The results of this work are: first, a database of 72 000 images for 4 vehicles classes; and second two retrained convolutional neural networks (InceptionV3 and MobileNetV2) capable of classifying vehicles with accuracies over 90%.
Deep learning models have a large number of freeparameters that need to be calculated by effective trainingof the models on a great deal of training data to improvetheir generalization performance. However, data obtaining andlabeling is expensive in practice. Data augmentation is one of themethods to alleviate this problem. In this paper, we conduct apreliminary study on how three variables (augmentation method,augmentation rate and size of basic dataset per label) can affectthe accuracy of deep learning for image classification. The studyprovides some guidelines: (1) it is better to use transformationsthat alter the geometry of the images rather than those justlighting and color. (2) 2-3 times augmentation rate is good enoughfor training. (3) the smaller amount of data, the more obviouscontributions could have.
Autonomous terrestrial vehicles must be capable of perceiving traffic lights and recognizing their current states to share the streets with human drivers. Most of the time, human drivers can easily identify the relevant traffic lights. To deal with this issue, a common solution for autonomous cars is to integrate recognition with prior maps. However, additional solution is required for the detection and recognition of the traffic light. Deep learning techniques have showed great performance and power of generalization including traffic related problems. Motivated by the advances in deep learning, some recent works leveraged some state-of-the-art deep detectors to locate (and further recognize) traffic lights from 2D camera images. However, none of them combine the power of the deep learning-based detectors with prior maps to recognize the state of the relevant traffic lights. Based on that, this work proposes to integrate the power of deep learning-based detection with the prior maps used by our car platform IARA (acronym for Intelligent Autonomous Robotic Automobile) to recognize the relevant traffic lights of predefined routes. The process is divided in two phases: an offline phase for map construction and traffic lights annotation; and an online phase for traffic light recognition and identification of the relevant ones. The proposed system was evaluated on five test cases (routes) in the city of Vit\'oria, each case being composed of a video sequence and a prior map with the relevant traffic lights for the route. Results showed that the proposed technique is able to correctly identify the relevant traffic light along the trajectory.
Data selection methods, such as active learning and core-set selection, are useful tools for machine learning on large datasets. However, they can be prohibitively expensive to apply in deep learning because they depend on feature representations that need to be learned. In this work, we show that we can greatly improve the computational efficiency by using a small proxy model to perform data selection (e.g., selecting data points to label for active learning). By removing hidden layers from the target model, using smaller architectures, and training for fewer epochs, we create proxies that are an order of magnitude faster to train. Although these small proxy models have higher error rates, we find that they empirically provide useful signals for data selection. We evaluate this "selection via proxy" (SVP) approach on several data selection tasks across five datasets: CIFAR10, CIFAR100, ImageNet, Amazon Review Polarity, and Amazon Review Full. For active learning, applying SVP can give an order of magnitude improvement in data selection runtime (i.e., the time it takes to repeatedly train and select points) without significantly increasing the final error (often within 0.1%). For core-set selection on CIFAR10, proxies that are over 10x faster to train than their larger, more accurate targets can remove up to 50% of the data without harming the final accuracy of the target, leading to a 1.6x end-to-end training time improvement.
Large neural networks are very successful in various tasks. However, with limited data, the generalization capabilities of deep neural networks are also very limited. In this paper, we empirically start showing that intrinsically sparse neural networks with adaptive sparse connectivity, which by design have a strict parameter budget during the training phase, have better generalization capabilities than their fully-connected counterparts. Besides this, we propose a new technique to train these sparse models by combining the Sparse Evolutionary Training (SET) procedure with neurons pruning. Operated on MultiLayer Perceptron (MLP) and tested on 15 datasets, our proposed technique zeros out around 50% of the hidden neurons during training, while having a linear number of parameters to optimize with respect to the number of neurons. The results show a competitive classification and generalization performance.
Video feedback provides a wealth of information about surgical procedures and is the main sensory cue for surgeons. Scene understanding is crucial to computer assisted interventions (CAI) and to post-operative analysis of the surgical procedure. A fundamental building block of such capabilities is the identification and localization of surgical instruments and anatomical structures through semantic segmentation. Deep learning has advanced semantic segmentation techniques in the recent years but is inherently reliant on the availability of labelled datasets for model training. This paper introduces a dataset for semantic segmentation of cataract surgery videos complementing the publicly available CATARACTS challenge dataset. In addition, we benchmark the performance of several state-of-the-art deep learning models for semantic segmentation on the presented dataset. The dataset is publicly available at https://cataracts-semantic-segmentation2020.grand-challenge.org/.
Water supplies are crucial for the development of living beings. However, change in the hydrological process i.e. climate and land usage are the key issues. Sustaining water level and accurate estimating for dynamic conditions is a critical job for hydrologists, but predicting hydrological extremes is an open issue. In this paper, we proposed two deep learning techniques and three machine learning algorithms to predict stream flow, given the present climate conditions. The results showed that the Recurrent Neural Network (RNN) or Long Short-term Memory (LSTM), an artificial neural network based method, outperform other conventional and machine-learning algorithms for predicting stream flow. Furthermore, we analyzed that stream flow is directly affected by precipitation, land usage, and temperature. These indexes are critical, which can be used by hydrologists to identify the potential for stream flow. We make the dataset publicly available (https://github.com/sadaqat007/Dataset) so that others should be able to replicate and build upon the results published.
Medical imaging is crucial in modern clinics to guide the diagnosis and treatment of diseases. Medical image reconstruction is one of the most fundamental and important components of medical imaging, whose major objective is to acquire high-quality medical images for clinical usage at minimal cost and risk to the patients. Mathematical models in medical image reconstruction or, more generally, image restoration in computer vision, have been playing a prominent role. Earlier mathematical models are mostly designed by human knowledge or hypothesis on the image to be reconstructed, and we shall call these models handcrafted models. Later, handcrafted plus data-driven modeling started to emerge which still mostly relies on human designs, while part of the model is learned from the observed data. More recently, as more data and computation resources are made available, deep learning based models (or deep models) pushed data-driven modeling to the extreme where the models are mostly based on learning with minimal human designs. Both handcrafted and data-driven modeling have their own advantages and disadvantages. One of the major research trends in medical imaging is to combine handcrafted modeling with deep modeling so that we can enjoy benefits from both approaches. The major part of this article is to provide a conceptual review of some recent works on deep modeling from the unrolling dynamics viewpoint. This viewpoint stimulates new designs of neural network architectures with inspiration from optimization algorithms and numerical differential equations. Given the popularity of deep modeling, there are still vast remaining challenges in the field, as well as opportunities which we shall discuss at the end of this article.
Machine learning algorithms generally suffer from a problem of explainability. Given a classification result from a model, it is typically hard to determine what caused the decision to be made, and to give an informative explanation. We explore a new method of generating counterfactual explanations, which instead of explaining why a particular classification was made explain how a different outcome can be achieved. This gives the recipients of the explanation a better way to understand the outcome, and provides an actionable suggestion. We show that the introduced method of Constrained Adversarial Examples (CADEX) can be used in real world applications, and yields explanations which incorporate business or domain constraints such as handling categorical attributes and range constraints.
Compressed sensing (CS) is a signal processing framework for efficiently reconstructing a signal from a small number of measurements, obtained by linear projections of the signal. In this paper we present an end-to-end deep learning approach for CS, in which a fully-connected network performs both the linear sensing and non-linear reconstruction stages. During the training phase, the sensing matrix and the non-linear reconstruction operator are jointly optimized using Structural similarity index (SSIM) as loss rather than the standard Mean Squared Error (MSE) loss. We compare the proposed approach with state-of-the-art in terms of reconstruction quality under both losses, i.e. SSIM score and MSE score.
The rapidly-advancing technology of deep learning (DL) into the world of the Internet of Things (IoT) has not fully entered in the fields of m-Health yet. Among the main reasons are the high computational demands of DL algorithms and the inherent resource-limitation of wearable devices. In this paper, we present initial results for two deep learning architectures used to diagnose and analyze sleep patterns, and we compare them with a previously presented hand-crafted algorithm. The algorithms are designed to be reliable for consumer healthcare applications and to be integrated into low-power wearables with limited computational resources.
Chest X-rays are the most common diagnostic exams in emergency rooms and hospitals. There has been a surge of work on automatic interpretation of chest X-rays using deep learning approaches after the availability of large open source chest X-ray dataset from NIH. However, the labels are not sufficiently rich and descriptive for training classification tools. Further, it does not adequately address the findings seen in Chest X-rays taken in anterior-posterior (AP) view which also depict the placement of devices such as central vascular lines and tubes. In this paper, we present a new chest X-ray benchmark database of 73 rich sentence-level descriptors of findings seen in AP chest X-rays. We describe our method of obtaining these findings through a semi-automated ground truth generation process from crowdsourcing of clinician annotations. We also present results of building classifiers for these findings that show that such higher granularity labels can also be learned through the framework of deep learning classifiers.
Abdominal magnetic resonance imaging (MRI) provides a straightforward way of characterizing tissue and locating lesions of patients as in standard diagnosis. However, abdominal MRI often suffers from respiratory motion artifacts, which leads to blurring and ghosting that significantly deteriorate the imaging quality. Conventional methods to reduce or eliminate these motion artifacts include breath holding, patient sedation, respiratory gating, and image post-processing, but these strategies inevitably involve extra scanning time and patient discomfort. In this paper, we propose a novel deep-learning-based model to recover MR images from respiratory motion artifacts. The proposed model comprises a densely connected U-net with generative adversarial network (GAN)-guided training and a perceptual loss function. We validate the model using a diverse collection of MRI data that are adversely affected by both synthetic and authentic respiration artifacts. Effective outcomes of motion removal are demonstrated. Our experimental results show the great potential of utilizing deep-learning-based methods in respiratory motion correction for abdominal MRI.
While deep learning technologies for computer vision have developed rapidly since 2012, modeling of remote sensing systems has remained focused around human vision. In particular, remote sensing systems are usually constructed to optimize sensing cost-quality trade-offs with respect to human image interpretability. While some recent studies have explored remote sensing system design as a function of simple computer vision algorithm performance, there has been little work relating this design to the state-of-the-art in computer vision: deep learning with convolutional neural networks. We develop experimental systems to conduct this analysis, showing results with modern deep learning algorithms and recent overhead image data. Our results are compared to standard image quality measurements based on human visual perception, and we conclude not only that machine and human interpretability differ significantly, but that computer vision performance is largely self-consistent across a range of disparate conditions. This research is presented as a cornerstone for a new generation of sensor design systems which focus on computer algorithm performance instead of human visual perception.
One of the most exciting technology breakthroughs in the last few years has been the rise of deep learning. State-of-the-art deep learning models are being widely deployed in academia and industry, across a variety of areas, from image analysis to natural language processing. These models have grown from fledgling research subjects to mature techniques in real-world use. The increasing scale of data, computational power and the associated algorithmic innovations are the main drivers for the progress we see in this field. These developments also have a huge potential for the automotive industry and therefore the interest in deep learning-based technology is growing. A lot of the product innovations, such as self-driving cars, parking and lane-change assist or safety functions, such as autonomous emergency braking, are powered by deep learning algorithms. Deep learning is poised to offer gains in performance and functionality for most ADAS (Advanced Driver Assistance System) solutions. Virtual sensing for vehicle dynamics application, vehicle inspection/heath monitoring, automated driving and data-driven product development are key areas that are expected to get the most attention. This article provides an overview of the recent advances and some associated challenges in deep learning techniques in the context of automotive applications.
Crater ellipticity determination is a complex and time consuming task that so far has evaded successful automation. We train a state of the art computer vision algorithm to identify craters in Lunar digital elevation maps and retrieve their sizes and 2D shapes. The computational backbone of the model is MaskRCNN, an "instance segmentation" general framework that detects craters in an image while simultaneously producing a mask for each crater that traces its outer rim. Our post-processing pipeline then finds the closest fitting ellipse to these masks, allowing us to retrieve the crater ellipticities. Our model is able to correctly identify 87\% of known craters in the longitude range we hid from the network during training and validation (test set), while predicting thousands of additional craters not present in our training data. Manual validation of a subset of these "new" craters indicates that a majority of them are real, which we take as an indicator of the strength of our model in learning to identify craters, despite incomplete training data. The crater size, ellipticity, and depth distributions predicted by our model are consistent with human-generated results. The model allows us to perform a large scale search for differences in crater diameter and shape distributions between the lunar highlands and maria, and we exclude any such differences with a high statistical significance. The predicted test set catalogue and trained model are available here: https://github.com/malidib/Craters_MaskRCNN/.
This tutorial will introduce the Computational Network Toolkit, or CNTK, Microsoft's cutting-edge open-source deep-learning toolkit for Windows and Linux. CNTK is a powerful computation-graph based deep-learning toolkit for training and evaluating deep neural networks. Microsoft product groups use CNTK, for example to create the Cortana speech models and web ranking. CNTK supports feed-forward, convolutional, and recurrent networks for speech, image, and text workloads, also in combination. Popular network types are supported either natively (convolution) or can be described as a CNTK configuration (LSTM, sequence-to-sequence). CNTK scales to multiple GPU servers and is designed around efficiency. The tutorial will give an overview of CNTK's general architecture and describe the specific methods and algorithms used for automatic differentiation, recurrent-loop inference and execution, memory sharing, on-the-fly randomization of large corpora, and multi-server parallelization. We will then show how typical uses looks like for relevant tasks like image recognition, sequence-to-sequence modeling, and speech recognition.
Software frameworks for neural networks play key roles in the development and application of deep learning methods. However, as new types of deep learning models are developed, existing frameworks designed for convolutional neural networks are becoming less useful. In this paper, we introduce Chainer, a Python based, standalone open source framework for deep learning models. Chainer provides a flexible, intuitive, and high performance means of implementing a full range of deep learning models, including state-of-the-art models such as recurrent neural networks and variational autoencoders.
In the integrative analyses of omics data, it is often of interest to extract data representation from one data type that best reflect its relations with another data type. This task is traditionally fulfilled by linear methods such as canonical correlation analysis (CCA) and partial least squares (PLS). However, information contained in one data type pertaining to the other data type may be complex and in nonlinear form. Deep learning provides a convenient alternative to extract low-dimensional nonlinear data embedding. In addition, the deep learning setup can naturally incorporate the effects of clinical confounding factors into the integrative analysis. Here we report a deep learning setup, named Autoencoder-based Integrative Multi-omics data Embedding (AIME), to extract data representation for omics data integrative analysis. The method can adjust for confounder variables, achieve informative data embedding, rank features in terms of their contributions, and find pairs of features from the two data types that are related to each other through the data embedding. In simulation studies, the method was highly effective in the extraction of major contributing features between data types. Using a real microRNA-gene expression dataset, and a real DNA methylation-gene expression dataset, we show that AIME excluded the influence of confounders including batch effects, and extracted biologically plausible novel information. The R package based on Keras and the TensorFlow backend is available at https://github.com/tianwei-yu/AIME.
Medical imaging is playing a more and more important role in clinics. However, there are several issues in different imaging modalities such as slow imaging speed in MRI, radiation injury in CT and PET. Therefore, accelerating MRI, reducing radiation dose in CT and PET have been ongoing research topics since their invention. Usually, acquiring less data is a direct but important strategy to address these issues. However, less acquisition usually results in aliasing artifacts in reconstructions. Recently, deep learning (DL) has been introduced in medical image reconstruction and shown potential on significantly speeding up MR reconstruction and reducing radiation dose. In this paper, we propose a general framework on combining the reconstruction model with deep learning to maximize the potential of deep learning and model-based reconstruction, and give the examples to demonstrate the performance and requirements of unrolling different algorithms using deep learning.