Paper Group ANR 245
Twitter Speaks: A Case of National Disaster Situational Awareness. $VJA\dot{G}\dot{G}$ – A Thick-Client Smart-Phone Journey Detection Algorithm. DLIME: A Deterministic Local Interpretable Model-Agnostic Explanations Approach for Computer-Aided Diagnosis Systems. Teacher-Student Training for Robust Tacotron-based TTS. DeepHoyer: Learning Sparser Ne …
Twitter Speaks: A Case of National Disaster Situational Awareness
| Title | Twitter Speaks: A Case of National Disaster Situational Awareness |
| Authors | Amir Karami, Vishal Shah, Reza Vaezi, Amit Bansal |
| Abstract | In recent years, we have been faced with a series of natural disasters causing a tremendous amount of financial, environmental, and human losses. The unpredictable nature of natural disasters’ behavior makes it hard to have a comprehensive situational awareness (SA) to support disaster management. Using opinion surveys is a traditional approach to analyze public concerns during natural disasters; however, this approach is limited, expensive, and time-consuming. Luckily the advent of social media has provided scholars with an alternative means of analyzing public concerns. Social media enable users (people) to freely communicate their opinions and disperse information regarding current events including natural disasters. This research emphasizes the value of social media analysis and proposes an analytical framework: Twitter Situational Awareness (TwiSA). This framework uses text mining methods including sentiment analysis and topic modeling to create a better SA for disaster preparedness, response, and recovery. TwiSA has also effectively deployed on a large number of tweets and tracks the negative concerns of people during the 2015 South Carolina flood. |
| Tasks | Sentiment Analysis |
| Published | 2019-03-07 |
| URL | http://arxiv.org/abs/1903.02706v1 |
| http://arxiv.org/pdf/1903.02706v1.pdf | |
| PWC | https://paperswithcode.com/paper/twitter-speaks-a-case-of-national-disaster |
| Repo | |
| Framework | |
$VJA\dot{G}\dot{G}$ – A Thick-Client Smart-Phone Journey Detection Algorithm
| Title | $VJA\dot{G}\dot{G}$ – A Thick-Client Smart-Phone Journey Detection Algorithm |
| Authors | Michael P. J. Camilleri, Adrian Muscat, Victor J. Buttigieg, Maria Attard |
| Abstract | In this paper we describe $Vja\dot{g}\dot{g}$, a battery-aware journey detection algorithm that executes on the mobile device. The algorithm can be embedded in the client app of the transport service provider or in a general purpose mobility data collector. The thick client setup allows the customer/participant to select which journeys are transferred to the server, keeping customers in control of their personal data and encouraging user uptake. The algorithm is tested in the field and optimised for both accuracy in registering complete journeys and battery power consumption. Typically the algorithm can run for a full day without the need of recharging and more than 88% of journeys are correctly detected from origin to destination, whilst 12% would be missing part of the journey. |
| Tasks | |
| Published | 2019-08-28 |
| URL | https://arxiv.org/abs/1908.10725v1 |
| https://arxiv.org/pdf/1908.10725v1.pdf | |
| PWC | https://paperswithcode.com/paper/vjadotgdotg-a-thick-client-smart-phone |
| Repo | |
| Framework | |
DLIME: A Deterministic Local Interpretable Model-Agnostic Explanations Approach for Computer-Aided Diagnosis Systems
| Title | DLIME: A Deterministic Local Interpretable Model-Agnostic Explanations Approach for Computer-Aided Diagnosis Systems |
| Authors | Muhammad Rehman Zafar, Naimul Mefraz Khan |
| Abstract | Local Interpretable Model-Agnostic Explanations (LIME) is a popular technique used to increase the interpretability and explainability of black box Machine Learning (ML) algorithms. LIME typically generates an explanation for a single prediction by any ML model by learning a simpler interpretable model (e.g. linear classifier) around the prediction through generating simulated data around the instance by random perturbation, and obtaining feature importance through applying some form of feature selection. While LIME and similar local algorithms have gained popularity due to their simplicity, the random perturbation and feature selection methods result in “instability” in the generated explanations, where for the same prediction, different explanations can be generated. This is a critical issue that can prevent deployment of LIME in a Computer-Aided Diagnosis (CAD) system, where stability is of utmost importance to earn the trust of medical professionals. In this paper, we propose a deterministic version of LIME. Instead of random perturbation, we utilize agglomerative Hierarchical Clustering (HC) to group the training data together and K-Nearest Neighbour (KNN) to select the relevant cluster of the new instance that is being explained. After finding the relevant cluster, a linear model is trained over the selected cluster to generate the explanations. Experimental results on three different medical datasets show the superiority for Deterministic Local Interpretable Model-Agnostic Explanations (DLIME), where we quantitatively determine the stability of DLIME compared to LIME utilizing the Jaccard similarity among multiple generated explanations. |
| Tasks | Feature Importance, Feature Selection |
| Published | 2019-06-24 |
| URL | https://arxiv.org/abs/1906.10263v1 |
| https://arxiv.org/pdf/1906.10263v1.pdf | |
| PWC | https://paperswithcode.com/paper/dlime-a-deterministic-local-interpretable |
| Repo | |
| Framework | |
Teacher-Student Training for Robust Tacotron-based TTS
| Title | Teacher-Student Training for Robust Tacotron-based TTS |
| Authors | Rui Liu, Berrak Sisman, Jingdong Li, Feilong Bao, Guanglai Gao, Haizhou Li |
| Abstract | While neural end-to-end text-to-speech (TTS) is superior to conventional statistical methods in many ways, the exposure bias problem in the autoregressive models remains an issue to be resolved. The exposure bias problem arises from the mismatch between the training and inference process, that results in unpredictable performance for out-of-domain test data at run-time. To overcome this, we propose a teacher-student training scheme for Tacotron-based TTS by introducing a distillation loss function in addition to the feature loss function. We first train a Tacotron2-based TTS model by always providing natural speech frames to the decoder, that serves as a teacher model. We then train another Tacotron2-based model as a student model, of which the decoder takes the predicted speech frames as input, similar to how the decoder works during run-time inference. With the distillation loss, the student model learns the output probabilities from the teacher model, that is called knowledge distillation. Experiments show that our proposed training scheme consistently improves the voice quality for out-of-domain test data both in Chinese and English systems. |
| Tasks | |
| Published | 2019-11-07 |
| URL | https://arxiv.org/abs/1911.02839v2 |
| https://arxiv.org/pdf/1911.02839v2.pdf | |
| PWC | https://paperswithcode.com/paper/teacher-student-training-for-robust-tacotron |
| Repo | |
| Framework | |
DeepHoyer: Learning Sparser Neural Network with Differentiable Scale-Invariant Sparsity Measures
| Title | DeepHoyer: Learning Sparser Neural Network with Differentiable Scale-Invariant Sparsity Measures |
| Authors | Huanrui Yang, Wei Wen, Hai Li |
| Abstract | In seeking for sparse and efficient neural network models, many previous works investigated on enforcing L1 or L0 regularizers to encourage weight sparsity during training. The L0 regularizer measures the parameter sparsity directly and is invariant to the scaling of parameter values, but it cannot provide useful gradients, and therefore requires complex optimization techniques. The L1 regularizer is almost everywhere differentiable and can be easily optimized with gradient descent. Yet it is not scale-invariant, causing the same shrinking rate to all parameters, which is inefficient in increasing sparsity. Inspired by the Hoyer measure (the ratio between L1 and L2 norms) used in traditional compressed sensing problems, we present DeepHoyer, a set of sparsity-inducing regularizers that are both differentiable almost everywhere and scale-invariant. Our experiments show that enforcing DeepHoyer regularizers can produce even sparser neural network models than previous works, under the same accuracy level. We also show that DeepHoyer can be applied to both element-wise and structural pruning. |
| Tasks | |
| Published | 2019-08-27 |
| URL | https://arxiv.org/abs/1908.09979v2 |
| https://arxiv.org/pdf/1908.09979v2.pdf | |
| PWC | https://paperswithcode.com/paper/deephoyer-learning-sparser-neural-network |
| Repo | |
| Framework | |
Info Intervention
| Title | Info Intervention |
| Authors | Gong Heyang, Zhu Ke |
| Abstract | We highlight the information processing aspect of causal models by proposing the info intervention, which intervening the information on the output edges of a node. We point out issues of the existing definition of $do$ intervention(also known as “surgical” or “atomatic” or “perfect” intervention) and other notations for causation. We show that \emph{info intervention} are competitive in formalizing causal queries, identification of cause-effect, and it can solve (or alleviate) some issues in the existing causal modeling frameworks. |
| Tasks | |
| Published | 2019-07-24 |
| URL | https://arxiv.org/abs/1907.11090v2 |
| https://arxiv.org/pdf/1907.11090v2.pdf | |
| PWC | https://paperswithcode.com/paper/info-intervention |
| Repo | |
| Framework | |
Deep learning at scale for subgrid modeling in turbulent flows
| Title | Deep learning at scale for subgrid modeling in turbulent flows |
| Authors | Mathis Bode, Michael Gauding, Konstantin Kleinheinz, Heinz Pitsch |
| Abstract | Modeling of turbulent flows is still challenging. One way to deal with the large scale separation due to turbulence is to simulate only the large scales and model the unresolved contributions as done in large-eddy simulation (LES). This paper focuses on two deep learning (DL) strategies, regression and reconstruction, which are data-driven and promising alternatives to classical modeling concepts. Using three-dimensional (3-D) forced turbulence direct numerical simulation (DNS) data, subgrid models are evaluated, which predict the unresolved part of quantities based on the resolved solution. For regression, it is shown that feedforward artificial neural networks (ANNs) are able to predict the fully-resolved scalar dissipation rate using filtered input data. It was found that a combination of a large-scale quantity, such as the filtered passive scalar itself, and a small-scale quantity, such as the filtered energy dissipation rate, gives the best agreement with the actual DNS data. Furthermore, a DL network motivated by enhanced super-resolution generative adversarial networks (ESRGANs) was used to reconstruct fully-resolved 3-D velocity fields from filtered velocity fields. The energy spectrum shows very good agreement. As size of scientific data is often in the order of terabytes or more, DL needs to be combined with high performance computing (HPC). Necessary code improvements for HPC-DL are discussed with respect to the supercomputer JURECA. After optimizing the training code, 396.2 TFLOPS were achieved. |
| Tasks | Super-Resolution |
| Published | 2019-10-01 |
| URL | https://arxiv.org/abs/1910.00928v1 |
| https://arxiv.org/pdf/1910.00928v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-at-scale-for-subgrid-modeling |
| Repo | |
| Framework | |
AI Ethics for Systemic Issues: A Structural Approach
| Title | AI Ethics for Systemic Issues: A Structural Approach |
| Authors | Agnes Schim van der Loeff, Iggy Bassi, Sachin Kapila, Jevgenij Gamper |
| Abstract | The debate on AI ethics largely focuses on technical improvements and stronger regulation to prevent accidents or misuse of AI, with solutions relying on holding individual actors accountable for responsible AI development. While useful and necessary, we argue that this “agency” approach disregards more indirect and complex risks resulting from AI’s interaction with the socio-economic and political context. This paper calls for a “structural” approach to assessing AI’s effects in order to understand and prevent such systemic risks where no individual can be held accountable for the broader negative impacts. This is particularly relevant for AI applied to systemic issues such as climate change and food security which require political solutions and global cooperation. To properly address the wide range of AI risks and ensure ‘AI for social good’, agency-focused policies must be complemented by policies informed by a structural approach. |
| Tasks | |
| Published | 2019-11-08 |
| URL | https://arxiv.org/abs/1911.03216v1 |
| https://arxiv.org/pdf/1911.03216v1.pdf | |
| PWC | https://paperswithcode.com/paper/ai-ethics-for-systemic-issues-a-structural |
| Repo | |
| Framework | |
Disentangling Pose from Appearance in Monochrome Hand Images
| Title | Disentangling Pose from Appearance in Monochrome Hand Images |
| Authors | Yikang Li, Chris Twigg, Yuting Ye, Lingling Tao, Xiaogang Wang |
| Abstract | Hand pose estimation from the monocular 2D image is challenging due to the variation in lighting, appearance, and background. While some success has been achieved using deep neural networks, they typically require collecting a large dataset that adequately samples all the axes of variation of hand images. It would, therefore, be useful to find a representation of hand pose which is independent of the image appearance~(like hand texture, lighting, background), so that we can synthesize unseen images by mixing pose-appearance combinations. In this paper, we present a novel technique that disentangles the representation of pose from a complementary appearance factor in 2D monochrome images. We supervise this disentanglement process using a network that learns to generate images of hand using specified pose+appearance features. Unlike previous work, we do not require image pairs with a matching pose; instead, we use the pose annotations already available and introduce a novel use of cycle consistency to ensure orthogonality between the factors. Experimental results show that our self-disentanglement scheme successfully decomposes the hand image into the pose and its complementary appearance features of comparable quality as the method using paired data. Additionally, training the model with extra synthesized images with unseen hand-appearance combinations by re-mixing pose and appearance factors from different images can improve the 2D pose estimation performance. |
| Tasks | Hand Pose Estimation, Pose Estimation |
| Published | 2019-04-16 |
| URL | http://arxiv.org/abs/1904.07528v1 |
| http://arxiv.org/pdf/1904.07528v1.pdf | |
| PWC | https://paperswithcode.com/paper/disentangling-pose-from-appearance-in |
| Repo | |
| Framework | |
Testing DNN Image Classifiers for Confusion & Bias Errors
| Title | Testing DNN Image Classifiers for Confusion & Bias Errors |
| Authors | Yuchi Tian, Ziyuan Zhong, Vicente Ordonez, Gail Kaiser, Baishakhi Ray |
| Abstract | Image classifiers are an important component of today’s software, from consumer and business applications to safety-critical domains. The advent of Deep Neural Networks (DNNs) is the key catalyst behind such wide-spread success. However, wide adoption comes with serious concerns about the robustness of software systems dependent on DNNs for image classification, as several severe erroneous behaviors have been reported under sensitive and critical circumstances. We argue that developers need to rigorously test their software’s image classifiers and delay deployment until acceptable. We present an approach to testing image classifier robustness based on class property violations. We found that many of the reported erroneous cases in popular DNN image classifiers occur because the trained models confuse one class with another or show biases towards some classes over others. These bugs usually violate some class properties of one or more of those classes. Most DNN testing techniques focus on per-image violations, so fail to detect class-level confusions or biases. We developed a testing technique to automatically detect class-based confusion and bias errors in DNN-driven image classification software. We evaluated our implementation, DeepInspect, on several popular image classifiers with precision up to 100% (avg.~72.6%) for confusion errors, and up to 84.3% (avg.~66.8%) for bias errors. DeepInspect found hundreds of classification mistakes in widely-used models, many exposing errors indicating confusion or bias. |
| Tasks | Image Classification |
| Published | 2019-05-20 |
| URL | https://arxiv.org/abs/1905.07831v3 |
| https://arxiv.org/pdf/1905.07831v3.pdf | |
| PWC | https://paperswithcode.com/paper/testing-deep-neural-network-based-image |
| Repo | |
| Framework | |
Unsupervised Learning of Neural Networks to Explain Neural Networks (extended abstract)
| Title | Unsupervised Learning of Neural Networks to Explain Neural Networks (extended abstract) |
| Authors | Quanshi Zhang, Yu Yang, Ying Nian Wu |
| Abstract | This paper presents an unsupervised method to learn a neural network, namely an explainer, to interpret a pre-trained convolutional neural network (CNN), i.e., the explainer uses interpretable visual concepts to explain features in middle conv-layers of a CNN. Given feature maps of a conv-layer of the CNN, the explainer performs like an auto-encoder, which decomposes the feature maps into object-part features. The object-part features are learned to reconstruct CNN features without much loss of information. We can consider the disentangled representations of object parts a paraphrase of CNN features, which help people understand the knowledge encoded by the CNN. More crucially, we learn the explainer via knowledge distillation without using any annotations of object parts or textures for supervision. In experiments, our method was widely used to interpret features of different benchmark CNNs, and explainers significantly boosted the feature interpretability without hurting the discrimination power of the CNNs. |
| Tasks | |
| Published | 2019-01-21 |
| URL | http://arxiv.org/abs/1901.07538v1 |
| http://arxiv.org/pdf/1901.07538v1.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-learning-of-neural-networks-to |
| Repo | |
| Framework | |
Pushing the Envelope for RGB-based Dense 3D Hand Pose Estimation via Neural Rendering
| Title | Pushing the Envelope for RGB-based Dense 3D Hand Pose Estimation via Neural Rendering |
| Authors | Seungryul Baek, Kwang In Kim, Tae-Kyun Kim |
| Abstract | Estimating 3D hand meshes from single RGB images is challenging, due to intrinsic 2D-3D mapping ambiguities and limited training data. We adopt a compact parametric 3D hand model that represents deformable and articulated hand meshes. To achieve the model fitting to RGB images, we investigate and contribute in three ways: 1) Neural rendering: inspired by recent work on human body, our hand mesh estimator (HME) is implemented by a neural network and a differentiable renderer, supervised by 2D segmentation masks and 3D skeletons. HME demonstrates good performance for estimating diverse hand shapes and improves pose estimation accuracies. 2) Iterative testing refinement: Our fitting function is differentiable. We iteratively refine the initial estimate using the gradients, in the spirit of iterative model fitting methods like ICP. The idea is supported by the latest research on human body. 3) Self-data augmentation: collecting sized RGB-mesh (or segmentation mask)-skeleton triplets for training is a big hurdle. Once the model is successfully fitted to input RGB images, its meshes i.e. shapes and articulations, are realistic, and we augment view-points on top of estimated dense hand poses. Experiments using three RGB-based benchmarks show that our framework offers beyond state-of-the-art accuracy in 3D pose estimation, as well as recovers dense 3D hand shapes. Each technical component above meaningfully improves the accuracy in the ablation study. |
| Tasks | 3D Pose Estimation, Data Augmentation, Hand Pose Estimation, Pose Estimation |
| Published | 2019-04-08 |
| URL | http://arxiv.org/abs/1904.04196v2 |
| http://arxiv.org/pdf/1904.04196v2.pdf | |
| PWC | https://paperswithcode.com/paper/pushing-the-envelope-for-rgb-based-dense-3d |
| Repo | |
| Framework | |
Hardware-friendly Neural Network Architecture for Neuromorphic Computing
| Title | Hardware-friendly Neural Network Architecture for Neuromorphic Computing |
| Authors | Roshan Gopalakrishnan, Yansong Chua, Ashish Jith Sreejith Kumar |
| Abstract | The hardware-software co-optimization of neural network architectures is becoming a major stream of research especially due to the emergence of commercial neuromorphic chips such as the IBM Truenorth and Intel Loihi. Development of specific neural network architectures in tandem with the design of the neuromorphic hardware considering the hardware constraints will make a huge impact in the complete system level application. In this paper, we study various neural network architectures and propose one that is hardware-friendly for a neuromorphic hardware with crossbar array of synapses. Considering the hardware constraints, we demonstrate how one may design the neuromorphic hardware so as to maximize classification accuracy in the trained network architecture, while concurrently, we choose a neural network architecture so as to maximize utilization in the neuromorphic cores. We also proposed a framework for mapping a neural network onto a neuromorphic chip named as the Mapping and Debugging (MaD) framework. The MaD framework is designed to be generic in the sense that it is a Python wrapper which in principle can be integrated with any simulator tool for neuromorphic chips. |
| Tasks | |
| Published | 2019-04-03 |
| URL | https://arxiv.org/abs/1906.08853v1 |
| https://arxiv.org/pdf/1906.08853v1.pdf | |
| PWC | https://paperswithcode.com/paper/hardware-friendly-neural-network-architecture |
| Repo | |
| Framework | |
Using anomaly detection to support classification of fast running (packaging) processes
| Title | Using anomaly detection to support classification of fast running (packaging) processes |
| Authors | Tilman Klaeger, Andre Schult, Lukas Oehm |
| Abstract | In this paper we propose a new method to assist in labeling data arriving from fast running processes using anomaly detection. A result is the possibility to manually classify data arriving at a high rates to train machine learning models. To circumvent the problem of not having a real ground truth we propose specific metrics for model selection and validation of the results. The use case is taken from the food packaging industry, where processes are affected by regular but short breakdowns causing interruptions in the production process. Fast production rates make it hard for machine operators to identify the source and thus the cause of the breakdown. Self learning assistance systems can help them finding the root cause of the problem and assist the machine operator in applying lasting solutions. These learning systems need to be trained to identify reoccurring problems using data analytics. Training is not easy as the process is too fast to be manually monitored to add specific classifications on the single data points. |
| Tasks | Anomaly Detection, Model Selection |
| Published | 2019-06-06 |
| URL | https://arxiv.org/abs/1906.02473v2 |
| https://arxiv.org/pdf/1906.02473v2.pdf | |
| PWC | https://paperswithcode.com/paper/using-anomaly-detection-to-support |
| Repo | |
| Framework | |
Hand range of motion evaluation for Rheumatoid Arthritis patients
| Title | Hand range of motion evaluation for Rheumatoid Arthritis patients |
| Authors | Luciano Walenty Xavier Cejnog, Roberto Marcondes Cesar Jr., Teofilo Emidio de Campos, Valeria Meirelles Carril Elui |
| Abstract | We introduce a framework for dynamic evaluation of the fingers movements: flexion, extension, abduction and adduction. This framework estimates angle measurements from joints computed by a hand pose estimation algorithm using a depth sensor (Realsense SR300). Given depth maps as input, our framework uses Pose-REN, which is a state-of-art hand pose estimation method that estimates 3D hand joint positions using a deep convolutional neural network. The pose estimation algorithm runs in real-time, allowing users to visualise 3D skeleton tracking results at the same time as the depth images are acquired. Once 3D joint poses are obtained, our framework estimates a plane containing the wrist and MCP joints and measures flexion/extension and abduction/aduction angles by applying computational geometry operations with respect to this plane. We analysed flexion and abduction movement patterns using real data, extracting the movement trajectories. Our preliminary results show that this method allows an automatic discrimination of hands with Rheumatoid Arthritis (RA) and healthy patients. The angle between joints can be used as an indicative of current movement capabilities and function. Although the measurements can be noisy and less accurate than those obtained statically through goniometry, the acquisition is much easier, non-invasive and patient-friendly, which shows the potential of our approach. The system can be used with and without orthosis. Our framework allows the acquisition of measurements with minimal intervention and significantly reduces the evaluation time. |
| Tasks | Hand Pose Estimation, Pose Estimation |
| Published | 2019-03-16 |
| URL | http://arxiv.org/abs/1903.06949v1 |
| http://arxiv.org/pdf/1903.06949v1.pdf | |
| PWC | https://paperswithcode.com/paper/hand-range-of-motion-evaluation-for |
| Repo | |
| Framework | |
