Paper Group ANR 21
Non-parametric clustering over user features and latent behavioral functions with dual-view mixture models. Fully Convolutional Model for Variable Bit Length and Lossy High Density Compression of Mammograms. A Canonical Image Set for Examining and Comparing Image Processing Algorithms. Exploring Adversarial Examples: Patterns of One-Pixel Attacks. …
Non-parametric clustering over user features and latent behavioral functions with dual-view mixture models
| Title | Non-parametric clustering over user features and latent behavioral functions with dual-view mixture models |
| Authors | Alberto Lumbreras, Julien Velcin, Marie Guégan, Bertrand Jouve |
| Abstract | We present a dual-view mixture model to cluster users based on their features and latent behavioral functions. Every component of the mixture model represents a probability density over a feature view for observed user attributes and a behavior view for latent behavioral functions that are indirectly observed through user actions or behaviors. Our task is to infer the groups of users as well as their latent behavioral functions. We also propose a non-parametric version based on a Dirichlet Process to automatically infer the number of clusters. We test the properties and performance of the model on a synthetic dataset that represents the participation of users in the threads of an online forum. Experiments show that dual-view models outperform single-view ones when one of the views lacks information. |
| Tasks | |
| Published | 2018-12-18 |
| URL | http://arxiv.org/abs/1812.07360v1 |
| http://arxiv.org/pdf/1812.07360v1.pdf | |
| PWC | https://paperswithcode.com/paper/non-parametric-clustering-over-user-features |
| Repo | |
| Framework | |
Fully Convolutional Model for Variable Bit Length and Lossy High Density Compression of Mammograms
| Title | Fully Convolutional Model for Variable Bit Length and Lossy High Density Compression of Mammograms |
| Authors | Aupendu Kar, Sri Phani Krishna Karri, Nirmalya Ghosh, Ramanathan Sethuraman, Debdoot Sheet |
| Abstract | Early works on medical image compression date to the 1980’s with the impetus on deployment of teleradiology systems for high-resolution digital X-ray detectors. Commercially deployed systems during the period could compress 4,096 x 4,096 sized images at 12 bpp to 2 bpp using lossless arithmetic coding, and over the years JPEG and JPEG2000 were imbibed reaching upto 0.1 bpp. Inspired by the reprise of deep learning based compression for natural images over the last two years, we propose a fully convolutional autoencoder for diagnostically relevant feature preserving lossy compression. This is followed by leveraging arithmetic coding for encapsulating high redundancy of features for further high-density code packing leading to variable bit length. We demonstrate performance on two different publicly available digital mammography datasets using peak signal-to-noise ratio (pSNR), structural similarity (SSIM) index and domain adaptability tests between datasets. At high density compression factors of >300x (~0.04 bpp), our approach rivals JPEG and JPEG2000 as evaluated through a Radiologist’s visual Turing test. |
| Tasks | Image Compression |
| Published | 2018-05-17 |
| URL | http://arxiv.org/abs/1805.06909v1 |
| http://arxiv.org/pdf/1805.06909v1.pdf | |
| PWC | https://paperswithcode.com/paper/fully-convolutional-model-for-variable-bit |
| Repo | |
| Framework | |
A Canonical Image Set for Examining and Comparing Image Processing Algorithms
| Title | A Canonical Image Set for Examining and Comparing Image Processing Algorithms |
| Authors | Jeffrey Uhlmann |
| Abstract | The purpose of this paper is to introduce a set of four test images containing features and structures that can facilitate effective examination and comparison of image processing algorithms. More specifically, the images are designed to more explicitly expose the characteristic properties of algorithms for image compression, virtual resolution adjustment, and enhancement. This set was developed at the Naval Research Laboratory (NRL) in the late 1990s as a more rigorous alternative to Lena and other images that have come into common use for purely ad hoc reasons with little or no rigorous consideration of their suitability. The increasing number of test images appearing in the literature not only makes it more difficult to compare results from different papers, it also introduces the potential for cherry-picking to influence results. The key contribution of this paper is the proposal to establish {\em some} canonical set to ensure that published results can be analyzed and compared in a rigorous way from one paper to another, and consideration of the four NRL images is proposed for this purpose. |
| Tasks | Image Compression |
| Published | 2018-04-30 |
| URL | http://arxiv.org/abs/1805.00116v1 |
| http://arxiv.org/pdf/1805.00116v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-canonical-image-set-for-examining-and |
| Repo | |
| Framework | |
Exploring Adversarial Examples: Patterns of One-Pixel Attacks
| Title | Exploring Adversarial Examples: Patterns of One-Pixel Attacks |
| Authors | David Kügler, Alexander Distergoft, Arjan Kuijper, Anirban Mukhopadhyay |
| Abstract | Failure cases of black-box deep learning, e.g. adversarial examples, might have severe consequences in healthcare. Yet such failures are mostly studied in the context of real-world images with calibrated attacks. To demystify the adversarial examples, rigorous studies need to be designed. Unfortunately, complexity of the medical images hinders such study design directly from the medical images. We hypothesize that adversarial examples might result from the incorrect mapping of image space to the low dimensional generation manifold by deep networks. To test the hypothesis, we simplify a complex medical problem namely pose estimation of surgical tools into its barest form. An analytical decision boundary and exhaustive search of the one-pixel attack across multiple image dimensions let us localize the regions of frequent successful one-pixel attacks at the image space. |
| Tasks | Pose Estimation |
| Published | 2018-06-25 |
| URL | http://arxiv.org/abs/1806.09410v2 |
| http://arxiv.org/pdf/1806.09410v2.pdf | |
| PWC | https://paperswithcode.com/paper/exploring-adversarial-examples-patterns-of |
| Repo | |
| Framework | |
LS-Net: Learning to Solve Nonlinear Least Squares for Monocular Stereo
| Title | LS-Net: Learning to Solve Nonlinear Least Squares for Monocular Stereo |
| Authors | Ronald Clark, Michael Bloesch, Jan Czarnowski, Stefan Leutenegger, Andrew J. Davison |
| Abstract | Sum-of-squares objective functions are very popular in computer vision algorithms. However, these objective functions are not always easy to optimize. The underlying assumptions made by solvers are often not satisfied and many problems are inherently ill-posed. In this paper, we propose LS-Net, a neural nonlinear least squares optimization algorithm which learns to effectively optimize these cost functions even in the presence of adversities. Unlike traditional approaches, the proposed solver requires no hand-crafted regularizers or priors as these are implicitly learned from the data. We apply our method to the problem of motion stereo ie. jointly estimating the motion and scene geometry from pairs of images of a monocular sequence. We show that our learned optimizer is able to efficiently and effectively solve this challenging optimization problem. |
| Tasks | |
| Published | 2018-09-09 |
| URL | http://arxiv.org/abs/1809.02966v1 |
| http://arxiv.org/pdf/1809.02966v1.pdf | |
| PWC | https://paperswithcode.com/paper/ls-net-learning-to-solve-nonlinear-least |
| Repo | |
| Framework | |
Comparing Dependencies in Probability Theory and General Rough Sets: Part-A
| Title | Comparing Dependencies in Probability Theory and General Rough Sets: Part-A |
| Authors | A Mani |
| Abstract | The problem of comparing concepts of dependence in general rough sets with those in probability theory had been initiated by the present author in some of her recent papers. This problem relates to the identification of the limitations of translating between the methodologies and possibilities in the identification of concepts. Comparison of ideas of dependence in the approaches had been attempted from a set-valuation based minimalist perspective by the present author. The deviant probability framework has been the result of such an approach. Other Bayesian reasoning perspectives (involving numeric valuations) and frequentist approaches are also known. In this research, duality results are adapted to demonstrate the possibility of improved comparisons across implications between ontologically distinct concepts in a common logic-based framework by the present author. Both positive and negative results are proved that delimit possible comparisons in a clearer way by her. |
| Tasks | |
| Published | 2018-04-06 |
| URL | http://arxiv.org/abs/1804.02322v1 |
| http://arxiv.org/pdf/1804.02322v1.pdf | |
| PWC | https://paperswithcode.com/paper/comparing-dependencies-in-probability-theory |
| Repo | |
| Framework | |
Improving Native Ads CTR Prediction by Large Scale Event Embedding and Recurrent Networks
| Title | Improving Native Ads CTR Prediction by Large Scale Event Embedding and Recurrent Networks |
| Authors | Mehul Parsana, Krishna Poola, Yajun Wang, Zhiguang Wang |
| Abstract | Click through rate (CTR) prediction is very important for Native advertisement but also hard as there is no direct query intent. In this paper we propose a large-scale event embedding scheme to encode the each user browsing event by training a Siamese network with weak supervision on the users’ consecutive events. The CTR prediction problem is modeled as a supervised recurrent neural network, which naturally model the user history as a sequence of events. Our proposed recurrent models utilizing pretrained event embedding vectors and an attention layer to model the user history. Our experiments demonstrate that our model significantly outperforms the baseline and some variants. |
| Tasks | Click-Through Rate Prediction |
| Published | 2018-04-24 |
| URL | http://arxiv.org/abs/1804.09133v2 |
| http://arxiv.org/pdf/1804.09133v2.pdf | |
| PWC | https://paperswithcode.com/paper/improving-native-ads-ctr-prediction-by-large |
| Repo | |
| Framework | |
You Must Have Clicked on this Ad by Mistake! Data-Driven Identification of Accidental Clicks on Mobile Ads with Applications to Advertiser Cost Discounting and Click-Through Rate Prediction
| Title | You Must Have Clicked on this Ad by Mistake! Data-Driven Identification of Accidental Clicks on Mobile Ads with Applications to Advertiser Cost Discounting and Click-Through Rate Prediction |
| Authors | Gabriele Tolomei, Mounia Lalmas, Ayman Farahat, Andrew Haines |
| Abstract | In the cost per click (CPC) pricing model, an advertiser pays an ad network only when a user clicks on an ad; in turn, the ad network gives a share of that revenue to the publisher where the ad was impressed. Still, advertisers may be unsatisfied with ad networks charging them for “valueless” clicks, or so-called accidental clicks. […] Charging advertisers for such clicks is detrimental in the long term as the advertiser may decide to run their campaigns on other ad networks. In addition, machine-learned click models trained to predict which ad will bring the highest revenue may overestimate an ad click-through rate, and as a consequence negatively impacting revenue for both the ad network and the publisher. In this work, we propose a data-driven method to detect accidental clicks from the perspective of the ad network. We collect observations of time spent by users on a large set of ad landing pages - i.e., dwell time. We notice that the majority of per-ad distributions of dwell time fit to a mixture of distributions, where each component may correspond to a particular type of clicks, the first one being accidental. We then estimate dwell time thresholds of accidental clicks from that component. Using our method to identify accidental clicks, we then propose a technique that smoothly discounts the advertiser’s cost of accidental clicks at billing time. Experiments conducted on a large dataset of ads served on Yahoo mobile apps confirm that our thresholds are stable over time, and revenue loss in the short term is marginal. We also compare the performance of an existing machine-learned click model trained on all ad clicks with that of the same model trained only on non-accidental clicks. There, we observe an increase in both ad click-through rate (+3.9%) and revenue (+0.2%) on ads served by the Yahoo Gemini network when using the latter. […] |
| Tasks | Click-Through Rate Prediction |
| Published | 2018-04-03 |
| URL | http://arxiv.org/abs/1804.06912v1 |
| http://arxiv.org/pdf/1804.06912v1.pdf | |
| PWC | https://paperswithcode.com/paper/you-must-have-clicked-on-this-ad-by-mistake |
| Repo | |
| Framework | |
Thompson Sampling for Dynamic Pricing
| Title | Thompson Sampling for Dynamic Pricing |
| Authors | Ravi Ganti, Matyas Sustik, Quoc Tran, Brian Seaman |
| Abstract | In this paper we apply active learning algorithms for dynamic pricing in a prominent e-commerce website. Dynamic pricing involves changing the price of items on a regular basis, and uses the feedback from the pricing decisions to update prices of the items. Most popular approaches to dynamic pricing use a passive learning approach, where the algorithm uses historical data to learn various parameters of the pricing problem, and uses the updated parameters to generate a new set of prices. We show that one can use active learning algorithms such as Thompson sampling to more efficiently learn the underlying parameters in a pricing problem. We apply our algorithms to a real e-commerce system and show that the algorithms indeed improve revenue compared to pricing algorithms that use passive learning. |
| Tasks | Active Learning |
| Published | 2018-02-08 |
| URL | http://arxiv.org/abs/1802.03050v1 |
| http://arxiv.org/pdf/1802.03050v1.pdf | |
| PWC | https://paperswithcode.com/paper/thompson-sampling-for-dynamic-pricing |
| Repo | |
| Framework | |
PAC-learning in the presence of evasion adversaries
| Title | PAC-learning in the presence of evasion adversaries |
| Authors | Daniel Cullina, Arjun Nitin Bhagoji, Prateek Mittal |
| Abstract | The existence of evasion attacks during the test phase of machine learning algorithms represents a significant challenge to both their deployment and understanding. These attacks can be carried out by adding imperceptible perturbations to inputs to generate adversarial examples and finding effective defenses and detectors has proven to be difficult. In this paper, we step away from the attack-defense arms race and seek to understand the limits of what can be learned in the presence of an evasion adversary. In particular, we extend the Probably Approximately Correct (PAC)-learning framework to account for the presence of an adversary. We first define corrupted hypothesis classes which arise from standard binary hypothesis classes in the presence of an evasion adversary and derive the Vapnik-Chervonenkis (VC)-dimension for these, denoted as the adversarial VC-dimension. We then show that sample complexity upper bounds from the Fundamental Theorem of Statistical learning can be extended to the case of evasion adversaries, where the sample complexity is controlled by the adversarial VC-dimension. We then explicitly derive the adversarial VC-dimension for halfspace classifiers in the presence of a sample-wise norm-constrained adversary of the type commonly studied for evasion attacks and show that it is the same as the standard VC-dimension, closing an open question. Finally, we prove that the adversarial VC-dimension can be either larger or smaller than the standard VC-dimension depending on the hypothesis class and adversary, making it an interesting object of study in its own right. |
| Tasks | |
| Published | 2018-06-05 |
| URL | http://arxiv.org/abs/1806.01471v2 |
| http://arxiv.org/pdf/1806.01471v2.pdf | |
| PWC | https://paperswithcode.com/paper/pac-learning-in-the-presence-of-evasion |
| Repo | |
| Framework | |
Abductive reasoning as the basis to reproduce expert criteria in ECG Atrial Fibrillation identification
| Title | Abductive reasoning as the basis to reproduce expert criteria in ECG Atrial Fibrillation identification |
| Authors | Tomás Teijeiro, Constantino A. García, Daniel Castro, Paulo Félix |
| Abstract | Objective: This work aims at providing a new method for the automatic detection of atrial fibrillation, other arrhythmia and noise on short single lead ECG signals, emphasizing the importance of the interpretability of the classification results. Approach: A morphological and rhythm description of the cardiac behavior is obtained by a knowledge-based interpretation of the signal using the \textit{Construe} abductive framework. Then, a set of meaningful features are extracted for each individual heartbeat and as a summary of the full record. The feature distributions were used to elucidate the expert criteria underlying the labeling of the 2017 Physionet/CinC Challenge dataset, enabling a manual partial relabeling to improve the consistency of the classification rules. Finally, state-of-the-art machine learning methods are combined to provide an answer on the basis of the feature values. Main results: The proposal tied for the first place in the official stage of the Challenge, with a combined $F_1$ score of 0.83, and was even improved in the follow-up stage to 0.85 with a significant simplification of the model. Significance: This approach demonstrates the potential of \textit{Construe} to provide robust and valuable descriptions of temporal data even with significant amounts of noise and artifacts. Also, we discuss the importance of a consistent classification criteria in manually labeled training datasets, and the fundamental advantages of knowledge-based approaches to formalize and validate that criteria. |
| Tasks | |
| Published | 2018-02-16 |
| URL | http://arxiv.org/abs/1802.05998v1 |
| http://arxiv.org/pdf/1802.05998v1.pdf | |
| PWC | https://paperswithcode.com/paper/abductive-reasoning-as-the-basis-to-reproduce |
| Repo | |
| Framework | |
Characterization of Brain Cortical Morphology Using Localized Topology-Encoding Graphs
| Title | Characterization of Brain Cortical Morphology Using Localized Topology-Encoding Graphs |
| Authors | Sevil Maghsadhagh, Mousa Shamsi, Anders Eklund, Hamid Behjat |
| Abstract | The human brain cortical layer has a convoluted morphology that is unique to each individual. Characterization of the cortical morphology is necessary in longitudinal studies of structural brain change, as well as in discriminating individuals in health and disease. A method for encoding the cortical morphology in the form of a graph is presented. The design of graphs that encode the global cerebral hemisphere cortices as well as localized cortical regions is proposed. Spectral features of these graphs are then studied and proposed as descriptors of cortical morphology. As proof-of-concept of their applicability in characterizing cortical morphology, the descriptors are studied in the context of discriminating individuals based on their sex. |
| Tasks | |
| Published | 2018-10-17 |
| URL | http://arxiv.org/abs/1810.10339v1 |
| http://arxiv.org/pdf/1810.10339v1.pdf | |
| PWC | https://paperswithcode.com/paper/characterization-of-brain-cortical-morphology |
| Repo | |
| Framework | |
Measuring Item Similarity in Introductory Programming: Python and Robot Programming Case Studies
| Title | Measuring Item Similarity in Introductory Programming: Python and Robot Programming Case Studies |
| Authors | Radek Pelánek, Tomáš Effenberger, Matěj Vaněk, Vojtěch Sassmann, Dominik Gmiterko |
| Abstract | A personalized learning system needs a large pool of items for learners to solve. When working with a large pool of items, it is useful to measure the similarity of items. We outline a general approach to measuring the similarity of items and discuss specific measures for items used in introductory programming. Evaluation of quality of similarity measures is difficult. To this end, we propose an evaluation approach utilizing three levels of abstraction. We illustrate our approach to measuring similarity and provide evaluation using items from three diverse programming environments. |
| Tasks | |
| Published | 2018-05-24 |
| URL | http://arxiv.org/abs/1806.03240v1 |
| http://arxiv.org/pdf/1806.03240v1.pdf | |
| PWC | https://paperswithcode.com/paper/measuring-item-similarity-in-introductory |
| Repo | |
| Framework | |
AI for the Common Good?! Pitfalls, challenges, and Ethics Pen-Testing
| Title | AI for the Common Good?! Pitfalls, challenges, and Ethics Pen-Testing |
| Authors | Bettina Berendt |
| Abstract | Recently, many AI researchers and practitioners have embarked on research visions that involve doing AI for “Good”. This is part of a general drive towards infusing AI research and practice with ethical thinking. One frequent theme in current ethical guidelines is the requirement that AI be good for all, or: contribute to the Common Good. But what is the Common Good, and is it enough to want to be good? Via four lead questions, I will illustrate challenges and pitfalls when determining, from an AI point of view, what the Common Good is and how it can be enhanced by AI. The questions are: What is the problem / What is a problem?, Who defines the problem?, What is the role of knowledge?, and What are important side effects and dynamics? The illustration will use an example from the domain of “AI for Social Good”, more specifically “Data Science for Social Good”. Even if the importance of these questions may be known at an abstract level, they do not get asked sufficiently in practice, as shown by an exploratory study of 99 contributions to recent conferences in the field. Turning these challenges and pitfalls into a positive recommendation, as a conclusion I will draw on another characteristic of computer-science thinking and practice to make these impediments visible and attenuate them: “attacks” as a method for improving design. This results in the proposal of ethics pen-testing as a method for helping AI designs to better contribute to the Common Good. |
| Tasks | |
| Published | 2018-10-30 |
| URL | http://arxiv.org/abs/1810.12847v2 |
| http://arxiv.org/pdf/1810.12847v2.pdf | |
| PWC | https://paperswithcode.com/paper/ai-for-the-common-good-pitfalls-challenges |
| Repo | |
| Framework | |
Fast and Accurate 3D Medical Image Segmentation with Data-swapping Method
| Title | Fast and Accurate 3D Medical Image Segmentation with Data-swapping Method |
| Authors | Haruki Imai, Samuel Matzek, Tung D. Le, Yasushi Negishi, Kiyokuni Kawachiya |
| Abstract | Deep neural network models used for medical image segmentation are large because they are trained with high-resolution three-dimensional (3D) images. Graphics processing units (GPUs) are widely used to accelerate the trainings. However, the memory on a GPU is not large enough to train the models. A popular approach to tackling this problem is patch-based method, which divides a large image into small patches and trains the models with these small patches. However, this method would degrade the segmentation quality if a target object spans multiple patches. In this paper, we propose a novel approach for 3D medical image segmentation that utilizes the data-swapping, which swaps out intermediate data from GPU memory to CPU memory to enlarge the effective GPU memory size, for training high-resolution 3D medical images without patching. We carefully tuned parameters in the data-swapping method to obtain the best training performance for 3D U-Net, a widely used deep neural network model for medical image segmentation. We applied our tuning to train 3D U-Net with full-size images of 192 x 192 x 192 voxels in brain tumor dataset. As a result, communication overhead, which is the most important issue, was reduced by 17.1%. Compared with the patch-based method for patches of 128 x 128 x 128 voxels, our training for full-size images achieved improvement on the mean Dice score by 4.48% and 5.32 % for detecting whole tumor sub-region and tumor core sub-region, respectively. The total training time was reduced from 164 hours to 47 hours, resulting in 3.53 times of acceleration. |
| Tasks | Medical Image Segmentation, Semantic Segmentation |
| Published | 2018-12-19 |
| URL | http://arxiv.org/abs/1812.07816v1 |
| http://arxiv.org/pdf/1812.07816v1.pdf | |
| PWC | https://paperswithcode.com/paper/fast-and-accurate-3d-medical-image |
| Repo | |
| Framework | |
