Paper Group ANR 1154
Adaptive Activity Monitoring with Uncertainty Quantification in Switching Gaussian Process Models. Ordinal Regression as Structured Classification. Increasing Shape Bias in ImageNet-Trained Networks Using Transfer Learning and Domain-Adversarial Methods. Controlling for Biasing Signals in Images for Prognostic Models: Survival Predictions for Lung …
Adaptive Activity Monitoring with Uncertainty Quantification in Switching Gaussian Process Models
| Title | Adaptive Activity Monitoring with Uncertainty Quantification in Switching Gaussian Process Models |
| Authors | Randy Ardywibowo, Guang Zhao, Zhangyang Wang, Bobak Mortazavi, Shuai Huang, Xiaoning Qian |
| Abstract | Emerging wearable sensors have enabled the unprecedented ability to continuously monitor human activities for healthcare purposes. However, with so many ambient sensors collecting different measurements, it becomes important not only to maintain good monitoring accuracy, but also low power consumption to ensure sustainable monitoring. This power-efficient sensing scheme can be achieved by deciding which group of sensors to use at a given time, requiring an accurate characterization of the trade-off between sensor energy usage and the uncertainty in ignoring certain sensor signals while monitoring. To address this challenge in the context of activity monitoring, we have designed an adaptive activity monitoring framework. We first propose a switching Gaussian process to model the observed sensor signals emitting from the underlying activity states. To efficiently compute the Gaussian process model likelihood and quantify the context prediction uncertainty, we propose a block circulant embedding technique and use Fast Fourier Transforms (FFT) for inference. By computing the Bayesian loss function tailored to switching Gaussian processes, an adaptive monitoring procedure is developed to select features from available sensors that optimize the trade-off between sensor power consumption and the prediction performance quantified by state prediction entropy. We demonstrate the effectiveness of our framework on the popular benchmark of UCI Human Activity Recognition using Smartphones. |
| Tasks | Activity Recognition, Gaussian Processes, Human Activity Recognition |
| Published | 2019-01-08 |
| URL | http://arxiv.org/abs/1901.02427v1 |
| http://arxiv.org/pdf/1901.02427v1.pdf | |
| PWC | https://paperswithcode.com/paper/adaptive-activity-monitoring-with-uncertainty |
| Repo | |
| Framework | |
Ordinal Regression as Structured Classification
| Title | Ordinal Regression as Structured Classification |
| Authors | Niall Twomey, Rafael Poyiadzi, Callum Mann, Raúl Santos-Rodríguez |
| Abstract | This paper extends the class of ordinal regression models with a structured interpretation of the problem by applying a novel treatment of encoded labels. The net effect of this is to transform the underlying problem from an ordinal regression task to a (structured) classification task which we solve with conditional random fields, thereby achieving a coherent and probabilistic model in which all model parameters are jointly learnt. Importantly, we show that although we have cast ordinal regression to classification, our method still fall within the class of decomposition methods in the ordinal regression ontology. This is an important link since our experience is that many applications of machine learning to healthcare ignores completely the important nature of the label ordering, and hence these approaches should considered naive in this ontology. We also show that our model is flexible both in how it adapts to data manifolds and in terms of the operations that are available for practitioner to execute. Our empirical evaluation demonstrates that the proposed approach overwhelmingly produces superior and often statistically significant results over baseline approaches on forty popular ordinal regression models, and demonstrate that the proposed model significantly out-performs baselines on synthetic and real datasets. Our implementation, together with scripts to reproduce the results of this work, will be available on a public GitHub repository. |
| Tasks | |
| Published | 2019-05-31 |
| URL | https://arxiv.org/abs/1905.13658v1 |
| https://arxiv.org/pdf/1905.13658v1.pdf | |
| PWC | https://paperswithcode.com/paper/ordinal-regression-as-structured |
| Repo | |
| Framework | |
Increasing Shape Bias in ImageNet-Trained Networks Using Transfer Learning and Domain-Adversarial Methods
| Title | Increasing Shape Bias in ImageNet-Trained Networks Using Transfer Learning and Domain-Adversarial Methods |
| Authors | Francis Brochu |
| Abstract | Convolutional Neural Networks (CNNs) have become the state-of-the-art method to learn from image data. However, recent research shows that they may include a texture and colour bias in their representation, contrary to the intuition that they learn the shapes of the image content and to human biological learning. Thus, recent works have attempted to increase the shape bias in CNNs in order to train more robust and accurate networks on tasks. One such approach uses style-transfer in order to remove texture clues from the data. This work reproduces this methodology on four image classification datasets, as well as extends the method to use domain-adversarial training in order to further increase the shape bias in the learned representation. The results show the proposed method increases the robustness and shape bias of the CNNs, while it does not provide a gain in accuracy. |
| Tasks | Image Classification, Style Transfer, Transfer Learning |
| Published | 2019-07-30 |
| URL | https://arxiv.org/abs/1907.12892v1 |
| https://arxiv.org/pdf/1907.12892v1.pdf | |
| PWC | https://paperswithcode.com/paper/increasing-shape-bias-in-imagenet-trained |
| Repo | |
| Framework | |
Controlling for Biasing Signals in Images for Prognostic Models: Survival Predictions for Lung Cancer with Deep Learning
| Title | Controlling for Biasing Signals in Images for Prognostic Models: Survival Predictions for Lung Cancer with Deep Learning |
| Authors | Wouter A. C. van Amsterdam, Marinus J. C. Eijkemans |
| Abstract | Deep learning has shown remarkable results for image analysis and is expected to aid individual treatment decisions in health care. To achieve this, deep learning methods need to be promoted from the level of mere associations to being able to answer causal questions. We present a scenario with real-world medical images (CT-scans of lung cancers) and simulated outcome data. Through the sampling scheme, the images contain two distinct factors of variation that represent a collider and a prognostic factor. We show that when this collider can be quantified, unbiased individual prognosis predictions are attainable with deep learning. This is achieved by (1) setting a dual task for the network to predict both the outcome and the collider and (2) enforcing independence of the activation distributions of the last layer with ordinary least squares. Our method provides an example of combining deep learning and structural causal models for unbiased individual prognosis predictions. |
| Tasks | |
| Published | 2019-04-01 |
| URL | http://arxiv.org/abs/1904.00942v1 |
| http://arxiv.org/pdf/1904.00942v1.pdf | |
| PWC | https://paperswithcode.com/paper/controlling-for-biasing-signals-in-images-for |
| Repo | |
| Framework | |
On the Limits of Learning to Actively Learn Semantic Representations
| Title | On the Limits of Learning to Actively Learn Semantic Representations |
| Authors | Omri Koshorek, Gabriel Stanovsky, Yichu Zhou, Vivek Srikumar, Jonathan Berant |
| Abstract | One of the goals of natural language understanding is to develop models that map sentences into meaning representations. However, training such models requires expensive annotation of complex structures, which hinders their adoption. Learning to actively-learn (LTAL) is a recent paradigm for reducing the amount of labeled data by learning a policy that selects which samples should be labeled. In this work, we examine LTAL for learning semantic representations, such as QA-SRL. We show that even an oracle policy that is allowed to pick examples that maximize performance on the test set (and constitutes an upper bound on the potential of LTAL), does not substantially improve performance compared to a random policy. We investigate factors that could explain this finding and show that a distinguishing characteristic of successful applications of LTAL is the interaction between optimization and the oracle policy selection process. In successful applications of LTAL, the examples selected by the oracle policy do not substantially depend on the optimization procedure, while in our setup the stochastic nature of optimization strongly affects the examples selected by the oracle. We conclude that the current applicability of LTAL for improving data efficiency in learning semantic meaning representations is limited. |
| Tasks | Learning Semantic Representations |
| Published | 2019-10-05 |
| URL | https://arxiv.org/abs/1910.02228v1 |
| https://arxiv.org/pdf/1910.02228v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-limits-of-learning-to-actively-learn |
| Repo | |
| Framework | |
Caching as an Image Characterization Problem using Deep Convolutional Neural Networks
| Title | Caching as an Image Characterization Problem using Deep Convolutional Neural Networks |
| Authors | Yantong Wang, Vasilis Friderikos |
| Abstract | Optimizing caching locations of popular content has received significant research attention over the last few years. This paper targets the optimization of the caching locations by proposing a novel transformation of the optimization problem to a grey-scale image that is applied to a deep convolutional neural network (CNN). The rational for the proposed modeling comes from CNN’s superiority to capture features in gray-scale images reaching human level performance in image recognition problems. The CNN has been trained with optimal solutions and the numerical investigations and analyses demonstrate the promising performance of the proposed method. Therefore, for enabling real-time decision making we moving away from a strictly optimization based framework to an amalgamation of optimization with a data driven approach. |
| Tasks | Decision Making |
| Published | 2019-07-16 |
| URL | https://arxiv.org/abs/1907.07263v1 |
| https://arxiv.org/pdf/1907.07263v1.pdf | |
| PWC | https://paperswithcode.com/paper/caching-as-an-image-characterization-problem |
| Repo | |
| Framework | |
AVID: Learning Multi-Stage Tasks via Pixel-Level Translation of Human Videos
| Title | AVID: Learning Multi-Stage Tasks via Pixel-Level Translation of Human Videos |
| Authors | Laura Smith, Nikita Dhawan, Marvin Zhang, Pieter Abbeel, Sergey Levine |
| Abstract | Robotic reinforcement learning (RL) holds the promise of enabling robots to learn complex behaviors through experience. However, realizing this promise requires not only effective and scalable RL algorithms, but also mechanisms to reduce human burden in terms of defining the task and resetting the environment. In this paper, we study how these challenges can be alleviated with an automated robotic learning framework, in which multi-stage tasks are defined simply by providing videos of a human demonstrator and then learned autonomously by the robot from raw image observations. A central challenge in imitating human videos is the difference in morphology between the human and robot, which typically requires manual correspondence. We instead take an automated approach and perform pixel-level image translation via CycleGAN to convert the human demonstration into a video of a robot, which can then be used to construct a reward function for a model-based RL algorithm. The robot then learns the task one stage at a time, automatically learning how to reset each stage to retry it multiple times without human-provided resets. This makes the learning process largely automatic, from intuitive task specification via a video to automated training with minimal human intervention. We demonstrate that our approach is capable of learning complex tasks, such as operating a coffee machine, directly from raw image observations, requiring only 20 minutes to provide human demonstrations and about 180 minutes of robot interaction with the environment. A supplementary video depicting the experimental setup, learning process, and our method’s final performance is available from https://sites.google.com/view/icra20avid |
| Tasks | |
| Published | 2019-12-10 |
| URL | https://arxiv.org/abs/1912.04443v1 |
| https://arxiv.org/pdf/1912.04443v1.pdf | |
| PWC | https://paperswithcode.com/paper/avid-learning-multi-stage-tasks-via-pixel |
| Repo | |
| Framework | |
Exposing GAN-synthesized Faces Using Landmark Locations
| Title | Exposing GAN-synthesized Faces Using Landmark Locations |
| Authors | Xin Yang, Yuezun Li, Honggang Qi, Siwei Lyu |
| Abstract | Generative adversary networks (GANs) have recently led to highly realistic image synthesis results. In this work, we describe a new method to expose GAN-synthesized images using the locations of the facial landmark points. Our method is based on the observations that the facial parts configuration generated by GAN models are different from those of the real faces, due to the lack of global constraints. We perform experiments demonstrating this phenomenon, and show that an SVM classifier trained using the locations of facial landmark points is sufficient to achieve good classification performance for GAN-synthesized faces. |
| Tasks | Image Generation |
| Published | 2019-03-30 |
| URL | http://arxiv.org/abs/1904.00167v1 |
| http://arxiv.org/pdf/1904.00167v1.pdf | |
| PWC | https://paperswithcode.com/paper/exposing-gan-synthesized-faces-using-landmark |
| Repo | |
| Framework | |
Compressed domain image classification using a multi-rate neural network
| Title | Compressed domain image classification using a multi-rate neural network |
| Authors | Yibo Xu, Kevin F. Kelly |
| Abstract | Compressed domain image classification aims to directly perform classification on compressive measurements generated from the single-pixel camera. While neural network approaches have achieved state-of-the-art performance, previous methods require training a dedicated network for each different measurement rate which is computationally costly. In this work, we present a general approach that endows a single neural network with multi-rate property for compressed domain classification where a single network is capable of classifying over an arbitrary number of measurements using dataset-independent fixed binary sensing patterns. We demonstrate the multi-rate neural network performance on MNIST and grayscale CIFAR-10 datasets. We also show that using the Partial Complete binary sensing matrix, the multi-rate network outperforms previous methods especially in the case of very few measurements. |
| Tasks | Image Classification |
| Published | 2019-01-28 |
| URL | http://arxiv.org/abs/1901.09983v1 |
| http://arxiv.org/pdf/1901.09983v1.pdf | |
| PWC | https://paperswithcode.com/paper/compressed-domain-image-classification-using |
| Repo | |
| Framework | |
Learning Wear Patterns on Footwear Outsoles Using Convolutional Neural Networks
| Title | Learning Wear Patterns on Footwear Outsoles Using Convolutional Neural Networks |
| Authors | Xavier Francis, Hamid Sharifzadeh, Angus Newton, Nilufar Baghaei, Soheil Varastehpour |
| Abstract | Footwear outsoles acquire characteristics unique to the individual wearing them over time. Forensic scientists largely rely on their skills and knowledge, gained through years of experience, to analyse such characteristics on a shoeprint. In this work, we present a convolutional neural network model that can predict the wear pattern on a unique dataset of shoeprints that captures the life and wear of a pair of shoes. We present an additional architecture able to reconstruct the outsole back to its original state on a given week, and provide empirical evaluations of the performance of both models. |
| Tasks | |
| Published | 2019-07-28 |
| URL | https://arxiv.org/abs/1907.12005v1 |
| https://arxiv.org/pdf/1907.12005v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-wear-patterns-on-footwear-outsoles |
| Repo | |
| Framework | |
Embeddings of Persistence Diagrams into Hilbert Spaces
| Title | Embeddings of Persistence Diagrams into Hilbert Spaces |
| Authors | Peter Bubenik, Alexander Wagner |
| Abstract | Since persistence diagrams do not admit an inner product structure, a map into a Hilbert space is needed in order to use kernel methods. It is natural to ask if such maps necessarily distort the metric on persistence diagrams. We show that persistence diagrams with the bottleneck distance do not even admit a coarse embedding into a Hilbert space. As part of our proof, we show that any separable, bounded metric space isometrically embeds into the space of persistence diagrams with the bottleneck distance. As corollaries, we obtain the generalized roundness, negative type, and asymptotic dimension of this space. |
| Tasks | |
| Published | 2019-05-11 |
| URL | https://arxiv.org/abs/1905.05604v3 |
| https://arxiv.org/pdf/1905.05604v3.pdf | |
| PWC | https://paperswithcode.com/paper/embeddings-of-persistence-diagrams-into |
| Repo | |
| Framework | |
Searching for Stage-wise Neural Graphs In the Limit
| Title | Searching for Stage-wise Neural Graphs In the Limit |
| Authors | Xin Zhou, Dejing Dou, Boyang Li |
| Abstract | Search space is a key consideration for neural architecture search. Recently, Xie et al. (2019) found that randomly generated networks from the same distribution perform similarly, which suggests we should search for random graph distributions instead of graphs. We propose graphon as a new search space. A graphon is the limit of Cauchy sequence of graphs and a scale-free probabilistic distribution, from which graphs of different number of nodes can be drawn. By utilizing properties of the graphon space and the associated cut-distance metric, we develop theoretically motivated techniques that search for and scale up small-capacity stage-wise graphs found on small datasets to large-capacity graphs that can handle ImageNet. The scaled stage-wise graphs outperform DenseNet and randomly wired Watts-Strogatz networks, indicating the benefits of graphon theory in NAS applications. |
| Tasks | Neural Architecture Search |
| Published | 2019-12-30 |
| URL | https://arxiv.org/abs/1912.12860v1 |
| https://arxiv.org/pdf/1912.12860v1.pdf | |
| PWC | https://paperswithcode.com/paper/searching-for-stage-wise-neural-graphs-in-the-1 |
| Repo | |
| Framework | |
Push and Pull Search Embedded in an M2M Framework for Solving Constrained Multi-objective Optimization Problems
| Title | Push and Pull Search Embedded in an M2M Framework for Solving Constrained Multi-objective Optimization Problems |
| Authors | Zhun Fan, Zhaojun Wang, Wenji Li, Yutong Yuan, Yugen You, Zhi Yang, Fuzan Sun, Jie Ruan, Zhaocheng Li |
| Abstract | In dealing with constrained multi-objective optimization problems (CMOPs), a key issue of multi-objective evolutionary algorithms (MOEAs) is to balance the convergence and diversity of working populations. |
| Tasks | |
| Published | 2019-06-02 |
| URL | https://arxiv.org/abs/1906.00402v1 |
| https://arxiv.org/pdf/1906.00402v1.pdf | |
| PWC | https://paperswithcode.com/paper/190600402 |
| Repo | |
| Framework | |
Optimality and limitations of audio-visual integration for cognitive systems
| Title | Optimality and limitations of audio-visual integration for cognitive systems |
| Authors | W. Paul Boyce, Tony Lindsay, Arkady Zgonnikov, Ignacio Rano, KongFatt Wong-Lin |
| Abstract | Multimodal integration is an important process in perceptual decision-making. In humans, this process has often been shown to be statistically optimal, or near optimal: sensory information is combined in a fashion that minimises the average error in perceptual representation of stimuli. However, sometimes there are costs that come with the optimization, manifesting as illusory percepts. We review audio-visual facilitations and illusions that are products of multisensory integration, and the computational models that account for these phenomena. In particular, the same optimal computational model can lead to illusory percepts, and we suggest that more studies should be needed to detect and mitigate these illusions, as artefacts in artificial cognitive systems. We provide cautionary considerations when designing artificial cognitive systems with the view of avoiding such artefacts. Finally, we suggest avenues of research towards solutions to potential pitfalls in system design. We conclude that detailed understanding of multisensory integration and the mechanisms behind audio-visual illusions can benefit the design of artificial cognitive systems. |
| Tasks | Decision Making |
| Published | 2019-12-02 |
| URL | https://arxiv.org/abs/1912.00581v2 |
| https://arxiv.org/pdf/1912.00581v2.pdf | |
| PWC | https://paperswithcode.com/paper/optimality-and-limitations-of-audio-visual |
| Repo | |
| Framework | |
Change point detection for graphical models in presence of missing values
| Title | Change point detection for graphical models in presence of missing values |
| Authors | Malte Londschien, Solt Kovács, Peter Bühlmann |
| Abstract | We propose estimation methods for change points in high-dimensional covariance structures with an emphasis on challenging scenarios with missing values. We advocate three imputation like methods and investigate their implications on common losses used for change point detection. We also discuss how model selection methods have to be adapted to the setting of incomplete data. The methods are compared in a simulation study and applied to real data examples from environmental monitoring systems as well as financial time series. |
| Tasks | Change Point Detection, Imputation, Model Selection, Time Series |
| Published | 2019-07-11 |
| URL | https://arxiv.org/abs/1907.05409v1 |
| https://arxiv.org/pdf/1907.05409v1.pdf | |
| PWC | https://paperswithcode.com/paper/change-point-detection-for-graphical-models |
| Repo | |
| Framework | |
