Paper Group ANR 421
Interactive Cognitive Assessment Tools: A Case Study on Digital Pens for the Clinical Assessment of Dementia. Automated Fact Checking: Task formulations, methods and future directions. Causal Inference by String Diagram Surgery. Estimating Causal Effects With Partial Covariates For Clinical Interpretability. Non-asymptotic bounds for sampling algor …
Interactive Cognitive Assessment Tools: A Case Study on Digital Pens for the Clinical Assessment of Dementia
| Title | Interactive Cognitive Assessment Tools: A Case Study on Digital Pens for the Clinical Assessment of Dementia |
| Authors | Daniel Sonntag |
| Abstract | Interactive cognitive assessment tools may be valuable for doctors and therapists to reduce costs and improve quality in healthcare systems. Use cases and scenarios include the assessment of dementia. In this paper, we present our approach to the semi-automatic assessment of dementia. We describe a case study with digital pens for the patients including background, problem description and possible solutions. We conclude with lessons learned when implementing digital tests, and a generalisation for use outside the cognitive impairments field. |
| Tasks | |
| Published | 2018-10-11 |
| URL | http://arxiv.org/abs/1810.04943v1 |
| http://arxiv.org/pdf/1810.04943v1.pdf | |
| PWC | https://paperswithcode.com/paper/interactive-cognitive-assessment-tools-a-case |
| Repo | |
| Framework | |
Automated Fact Checking: Task formulations, methods and future directions
| Title | Automated Fact Checking: Task formulations, methods and future directions |
| Authors | James Thorne, Andreas Vlachos |
| Abstract | The recently increased focus on misinformation has stimulated research in fact checking, the task of assessing the truthfulness of a claim. Research in automating this task has been conducted in a variety of disciplines including natural language processing, machine learning, knowledge representation, databases, and journalism. While there has been substantial progress, relevant papers and articles have been published in research communities that are often unaware of each other and use inconsistent terminology, thus impeding understanding and further progress. In this paper we survey automated fact checking research stemming from natural language processing and related disciplines, unifying the task formulations and methodologies across papers and authors. Furthermore, we highlight the use of evidence as an important distinguishing factor among them cutting across task formulations and methods. We conclude with proposing avenues for future NLP research on automated fact checking. |
| Tasks | |
| Published | 2018-06-20 |
| URL | http://arxiv.org/abs/1806.07687v2 |
| http://arxiv.org/pdf/1806.07687v2.pdf | |
| PWC | https://paperswithcode.com/paper/automated-fact-checking-task-formulations |
| Repo | |
| Framework | |
Causal Inference by String Diagram Surgery
| Title | Causal Inference by String Diagram Surgery |
| Authors | Bart Jacobs, Aleks Kissinger, Fabio Zanasi |
| Abstract | Extracting causal relationships from observed correlations is a growing area in probabilistic reasoning, originating with the seminal work of Pearl and others from the early 1990s. This paper develops a new, categorically oriented view based on a clear distinction between syntax (string diagrams) and semantics (stochastic matrices), connected via interpretations as structure-preserving functors. A key notion in the identification of causal effects is that of an intervention, whereby a variable is forcefully set to a particular value independent of any prior propensities. We represent the effect of such an intervention as an endofunctor which performs `string diagram surgery’ within the syntactic category of string diagrams. This diagram surgery in turn yields a new, interventional distribution via the interpretation functor. While in general there is no way to compute interventional distributions purely from observed data, we show that this is possible in certain special cases using a calculational tool called comb disintegration. We demonstrate the use of this technique on a well-known toy example, where we predict the causal effect of smoking on cancer in the presence of a confounding common cause. After developing this specific example, we show this technique provides simple sufficient conditions for computing interventions which apply to a wide variety of situations considered in the causal inference literature. | |
| Tasks | Causal Inference |
| Published | 2018-11-20 |
| URL | https://arxiv.org/abs/1811.08338v2 |
| https://arxiv.org/pdf/1811.08338v2.pdf | |
| PWC | https://paperswithcode.com/paper/causal-inference-by-string-diagram-surgery |
| Repo | |
| Framework | |
Estimating Causal Effects With Partial Covariates For Clinical Interpretability
| Title | Estimating Causal Effects With Partial Covariates For Clinical Interpretability |
| Authors | Sonali Parbhoo, Mario Wieser, Volker Roth |
| Abstract | Estimating the causal effects of an intervention in the presence of confounding is a frequently occurring problem in applications such as medicine. The task is challenging since there may be multiple confounding factors, some of which may be missing, and inferences must be made from high-dimensional, noisy measurements. In this paper, we propose a decision-theoretic approach to estimate the causal effects of interventions where a subset of the covariates is unavailable for some patients during testing. Our approach uses the information bottleneck principle to perform a discrete, low-dimensional sufficient reduction of the covariate data to estimate a distribution over confounders. In doing so, we can estimate the causal effect of an intervention where only partial covariate information is available. Our results on a causal inference benchmark and a real application for treating sepsis show that our method achieves state-of-the-art performance, without sacrificing interpretability. |
| Tasks | Causal Inference |
| Published | 2018-11-26 |
| URL | http://arxiv.org/abs/1811.10347v1 |
| http://arxiv.org/pdf/1811.10347v1.pdf | |
| PWC | https://paperswithcode.com/paper/estimating-causal-effects-with-partial |
| Repo | |
| Framework | |
Non-asymptotic bounds for sampling algorithms without log-concavity
| Title | Non-asymptotic bounds for sampling algorithms without log-concavity |
| Authors | Mateusz B. Majka, Aleksandar Mijatović, Lukasz Szpruch |
| Abstract | Discrete time analogues of ergodic stochastic differential equations (SDEs) are one of the most popular and flexible tools for sampling high-dimensional probability measures. Non-asymptotic analysis in the $L^2$ Wasserstein distance of sampling algorithms based on Euler discretisations of SDEs has been recently developed by several authors for log-concave probability distributions. In this work we replace the log-concavity assumption with a log-concavity at infinity condition. We provide novel $L^2$ convergence rates for Euler schemes, expressed explicitly in terms of problem parameters. From there we derive non-asymptotic bounds on the distance between the laws induced by Euler schemes and the invariant laws of SDEs, both for schemes with standard and with randomised (inaccurate) drifts. We also obtain bounds for the hierarchy of discretisation, which enables us to deploy a multi-level Monte Carlo estimator. Our proof relies on a novel construction of a coupling for the Markov chains that can be used to control both the $L^1$ and $L^2$ Wasserstein distances simultaneously. Finally, we provide a weak convergence analysis that covers both the standard and the randomised (inaccurate) drift case. In particular, we reveal that the variance of the randomised drift does not influence the rate of weak convergence of the Euler scheme to the SDE. |
| Tasks | |
| Published | 2018-08-21 |
| URL | https://arxiv.org/abs/1808.07105v3 |
| https://arxiv.org/pdf/1808.07105v3.pdf | |
| PWC | https://paperswithcode.com/paper/non-asymptotic-bounds-for-sampling-algorithms |
| Repo | |
| Framework | |
Incremental Color Quantization for Color-Vision-Deficient Observers Using Mobile Gaming Data
| Title | Incremental Color Quantization for Color-Vision-Deficient Observers Using Mobile Gaming Data |
| Authors | Jose Cambronero, Phillip Stanley-Marbell, Martin Rinard |
| Abstract | The sizes of compressed images depend on their spatial resolution (number of pixels) and on their color resolution (number of color quantization levels). We introduce DaltonQuant, a new color quantization technique for image compression that cloud services can apply to images destined for a specific user with known color vision deficiencies. DaltonQuant improves compression in a user-specific but reversible manner thereby improving a user’s network bandwidth and data storage efficiency. DaltonQuant quantizes image data to account for user-specific color perception anomalies, using a new method for incremental color quantization based on a large corpus of color vision acuity data obtained from a popular mobile game. Servers that host images can revert DaltonQuant’s image requantization and compression when those images must be transmitted to a different user, making the technique practical to deploy on a large scale. We evaluate DaltonQuant’s compression performance on the Kodak PC reference image set and show that it improves compression by an additional 22%-29% over the state-of-the-art compressors TinyPNG and pngquant. |
| Tasks | Image Compression, Quantization |
| Published | 2018-03-22 |
| URL | http://arxiv.org/abs/1803.08420v1 |
| http://arxiv.org/pdf/1803.08420v1.pdf | |
| PWC | https://paperswithcode.com/paper/incremental-color-quantization-for-color |
| Repo | |
| Framework | |
The Need for Speed of AI Applications: Performance Comparison of Native vs. Browser-based Algorithm Implementations
| Title | The Need for Speed of AI Applications: Performance Comparison of Native vs. Browser-based Algorithm Implementations |
| Authors | Bernd Malle, Nicola Giuliani, Peter Kieseberg, Andreas Holzinger |
| Abstract | AI applications pose increasing demands on performance, so it is not surprising that the era of client-side distributed software is becoming important. On top of many AI applications already using mobile hardware, and even browsers for computationally demanding AI applications, we are already witnessing the emergence of client-side (federated) machine learning algorithms, driven by the interests of large corporations and startups alike. Apart from mathematical and algorithmic concerns, this trend especially demands new levels of computational efficiency from client environments. Consequently, this paper deals with the question of state-of-the-art performance by presenting a comparison study between native code and different browser-based implementations: JavaScript, ASM.js as well as WebAssembly on a representative mix of algorithms. Our results show that current efforts in runtime optimization push the boundaries well towards (and even beyond) native binary performance. We analyze the results obtained and speculate on the reasons behind some surprises, rounding the paper off by outlining future possibilities as well as some of our own research efforts. |
| Tasks | |
| Published | 2018-02-11 |
| URL | http://arxiv.org/abs/1802.03707v1 |
| http://arxiv.org/pdf/1802.03707v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-need-for-speed-of-ai-applications |
| Repo | |
| Framework | |
Layout-induced Video Representation for Recognizing Agent-in-Place Actions
| Title | Layout-induced Video Representation for Recognizing Agent-in-Place Actions |
| Authors | Ruichi Yu, Hongcheng Wang, Ang Li, Jingxiao Zheng, Vlad I. Morariu, Larry S. Davis |
| Abstract | We address the recognition of agent-in-place actions, which are associated with agents who perform them and places where they occur, in the context of outdoor home surveillance. We introduce a representation of the geometry and topology of scene layouts so that a network can generalize from the layouts observed in the training set to unseen layouts in the test set. This Layout-Induced Video Representation (LIVR) abstracts away low-level appearance variance and encodes geometric and topological relationships of places in a specific scene layout. LIVR partitions the semantic features of a video clip into different places to force the network to learn place-based feature descriptions; to predict the confidence of each action, LIVR aggregates features from the place associated with an action and its adjacent places on the scene layout. We introduce the Agent-in-Place Action dataset to show that our method allows neural network models to generalize significantly better to unseen scenes. |
| Tasks | |
| Published | 2018-04-04 |
| URL | http://arxiv.org/abs/1804.01429v3 |
| http://arxiv.org/pdf/1804.01429v3.pdf | |
| PWC | https://paperswithcode.com/paper/layout-induced-video-representation-for |
| Repo | |
| Framework | |
Imagining an Engineer: On GAN-Based Data Augmentation Perpetuating Biases
| Title | Imagining an Engineer: On GAN-Based Data Augmentation Perpetuating Biases |
| Authors | Niharika Jain, Lydia Manikonda, Alberto Olmo Hernandez, Sailik Sengupta, Subbarao Kambhampati |
| Abstract | The use of synthetic data generated by Generative Adversarial Networks (GANs) has become quite a popular method to do data augmentation for many applications. While practitioners celebrate this as an economical way to get more synthetic data that can be used to train downstream classifiers, it is not clear that they recognize the inherent pitfalls of this technique. In this paper, we aim to exhort practitioners against deriving any false sense of security against data biases based on data augmentation. To drive this point home, we show that starting with a dataset consisting of head-shots of engineering researchers, GAN-based augmentation “imagines” synthetic engineers, most of whom have masculine features and white skin color (inferred from a human subject study conducted on Amazon Mechanical Turk). This demonstrates how biases inherent in the training data are reinforced, and sometimes even amplified, by GAN-based data augmentation; it should serve as a cautionary tale for the lay practitioners. |
| Tasks | Data Augmentation |
| Published | 2018-11-09 |
| URL | http://arxiv.org/abs/1811.03751v1 |
| http://arxiv.org/pdf/1811.03751v1.pdf | |
| PWC | https://paperswithcode.com/paper/imagining-an-engineer-on-gan-based-data |
| Repo | |
| Framework | |
DiGrad: Multi-Task Reinforcement Learning with Shared Actions
| Title | DiGrad: Multi-Task Reinforcement Learning with Shared Actions |
| Authors | Parijat Dewangan, S Phaniteja, K Madhava Krishna, Abhishek Sarkar, Balaraman Ravindran |
| Abstract | Most reinforcement learning algorithms are inefficient for learning multiple tasks in complex robotic systems, where different tasks share a set of actions. In such environments a compound policy may be learnt with shared neural network parameters, which performs multiple tasks concurrently. However such compound policy may get biased towards a task or the gradients from different tasks negate each other, making the learning unstable and sometimes less data efficient. In this paper, we propose a new approach for simultaneous training of multiple tasks sharing a set of common actions in continuous action spaces, which we call as DiGrad (Differential Policy Gradient). The proposed framework is based on differential policy gradients and can accommodate multi-task learning in a single actor-critic network. We also propose a simple heuristic in the differential policy gradient update to further improve the learning. The proposed architecture was tested on 8 link planar manipulator and 27 degrees of freedom(DoF) Humanoid for learning multi-goal reachability tasks for 3 and 2 end effectors respectively. We show that our approach supports efficient multi-task learning in complex robotic systems, outperforming related methods in continuous action spaces. |
| Tasks | Multi-Task Learning |
| Published | 2018-02-27 |
| URL | http://arxiv.org/abs/1802.10463v1 |
| http://arxiv.org/pdf/1802.10463v1.pdf | |
| PWC | https://paperswithcode.com/paper/digrad-multi-task-reinforcement-learning-with |
| Repo | |
| Framework | |
Doubly Reparameterized Gradient Estimators for Monte Carlo Objectives
| Title | Doubly Reparameterized Gradient Estimators for Monte Carlo Objectives |
| Authors | George Tucker, Dieterich Lawson, Shixiang Gu, Chris J. Maddison |
| Abstract | Deep latent variable models have become a popular model choice due to the scalable learning algorithms introduced by (Kingma & Welling, 2013; Rezende et al., 2014). These approaches maximize a variational lower bound on the intractable log likelihood of the observed data. Burda et al. (2015) introduced a multi-sample variational bound, IWAE, that is at least as tight as the standard variational lower bound and becomes increasingly tight as the number of samples increases. Counterintuitively, the typical inference network gradient estimator for the IWAE bound performs poorly as the number of samples increases (Rainforth et al., 2018; Le et al., 2018). Roeder et al. (2017) propose an improved gradient estimator, however, are unable to show it is unbiased. We show that it is in fact biased and that the bias can be estimated efficiently with a second application of the reparameterization trick. The doubly reparameterized gradient (DReG) estimator does not suffer as the number of samples increases, resolving the previously raised issues. The same idea can be used to improve many recently introduced training techniques for latent variable models. In particular, we show that this estimator reduces the variance of the IWAE gradient, the reweighted wake-sleep update (RWS) (Bornschein & Bengio, 2014), and the jackknife variational inference (JVI) gradient (Nowozin, 2018). Finally, we show that this computationally efficient, unbiased drop-in gradient estimator translates to improved performance for all three objectives on several modeling tasks. |
| Tasks | Latent Variable Models |
| Published | 2018-10-09 |
| URL | http://arxiv.org/abs/1810.04152v2 |
| http://arxiv.org/pdf/1810.04152v2.pdf | |
| PWC | https://paperswithcode.com/paper/doubly-reparameterized-gradient-estimators |
| Repo | |
| Framework | |
Learning Kinematic Descriptions using SPARE: Simulated and Physical ARticulated Extendable dataset
| Title | Learning Kinematic Descriptions using SPARE: Simulated and Physical ARticulated Extendable dataset |
| Authors | Abhishek Venkataraman, Brent Griffin, Jason J. Corso |
| Abstract | Next generation robots will need to understand intricate and articulated objects as they cooperate in human environments. To do so, these robots will need to move beyond their current abilities— working with relatively simple objects in a task-indifferent manner— toward more sophisticated abilities that dynamically estimate the properties of complex, articulated objects. To that end, we make two compelling contributions toward general articulated (physical) object understanding in this paper. First, we introduce a new dataset, SPARE: Simulated and Physical ARticulated Extendable dataset. SPARE is an extendable open-source dataset providing equivalent simulated and physical instances of articulated objects (kinematic chains), providing the greater research community with a training and evaluation tool for methods generating kinematic descriptions of articulated objects. To the best of our knowledge, this is the first joint visual and physical (3D-printable) dataset for the Vision community. Second, we present a deep neural network that can predit the number of links and the length of the links of an articulated object. These new ideas outperform classical approaches to understanding kinematic chains, such tracking-based methods, which fail in the case of occlusion and do not leverage multiple views when available. |
| Tasks | |
| Published | 2018-03-29 |
| URL | http://arxiv.org/abs/1803.11147v1 |
| http://arxiv.org/pdf/1803.11147v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-kinematic-descriptions-using-spare |
| Repo | |
| Framework | |
ASR-based Features for Emotion Recognition: A Transfer Learning Approach
| Title | ASR-based Features for Emotion Recognition: A Transfer Learning Approach |
| Authors | Noé Tits, Kevin El Haddad, Thierry Dutoit |
| Abstract | During the last decade, the applications of signal processing have drastically improved with deep learning. However areas of affecting computing such as emotional speech synthesis or emotion recognition from spoken language remains challenging. In this paper, we investigate the use of a neural Automatic Speech Recognition (ASR) as a feature extractor for emotion recognition. We show that these features outperform the eGeMAPS feature set to predict the valence and arousal emotional dimensions, which means that the audio-to-text mapping learning by the ASR system contain information related to the emotional dimensions in spontaneous speech. We also examine the relationship between first layers (closer to speech) and last layers (closer to text) of the ASR and valence/arousal. |
| Tasks | Emotion Recognition, Speech Recognition, Speech Synthesis, Transfer Learning |
| Published | 2018-05-23 |
| URL | http://arxiv.org/abs/1805.09197v3 |
| http://arxiv.org/pdf/1805.09197v3.pdf | |
| PWC | https://paperswithcode.com/paper/asr-based-features-for-emotion-recognition-a |
| Repo | |
| Framework | |
PortraitGAN for Flexible Portrait Manipulation
| Title | PortraitGAN for Flexible Portrait Manipulation |
| Authors | Jiali Duan, Xiaoyuan Guo, Yuhang Song, Chao Yang, C. -C. Jay Kuo |
| Abstract | Previous methods have dealt with discrete manipulation of facial attributes such as smile, sad, angry, surprise etc, out of canonical expressions and they are not scalable, operating in single modality. In this paper, we propose a novel framework that supports continuous edits and multi-modality portrait manipulation using adversarial learning. Specifically, we adapt cycle-consistency into the conditional setting by leveraging additional facial landmarks information. This has two effects: first cycle mapping induces bidirectional manipulation and identity preserving; second pairing samples from different modalities can thus be utilized. To ensure high-quality synthesis, we adopt texture-loss that enforces texture consistency and multi-level adversarial supervision that facilitates gradient flow. Quantitative and qualitative experiments show the effectiveness of our framework in performing flexible and multi-modality portrait manipulation with photo-realistic effects. |
| Tasks | |
| Published | 2018-07-05 |
| URL | http://arxiv.org/abs/1807.01826v2 |
| http://arxiv.org/pdf/1807.01826v2.pdf | |
| PWC | https://paperswithcode.com/paper/portraitgan-for-flexible-portrait |
| Repo | |
| Framework | |
Edge-based LBP description of surfaces with colorimetric patterns
| Title | Edge-based LBP description of surfaces with colorimetric patterns |
| Authors | Elia Moscoso Thompson, Silvia Biasotti |
| Abstract | In this paper we target the problem of the retrieval of colour patterns over surfaces. We generalize to surface tessellations the well known Local Binary Pattern (LBP) descriptor for images. The key concept of the LBP is to code the variability of the colour values around each pixel. In the case of a surface tessellation we adopt rings around vertices that are obtained with a sphere-mesh intersection driven by the edges of the mesh; for this reason, we name our method edgeLBP. Experimental results are provided to show how this description performs well for pattern retrieval, also when patterns come from degraded and corrupted archaeological fragments. |
| Tasks | |
| Published | 2018-04-11 |
| URL | http://arxiv.org/abs/1804.03977v1 |
| http://arxiv.org/pdf/1804.03977v1.pdf | |
| PWC | https://paperswithcode.com/paper/edge-based-lbp-description-of-surfaces-with |
| Repo | |
| Framework | |
