Paper Group ANR 768
Dueling Bandits with Qualitative Feedback. GAN Augmentation: Augmenting Training Data using Generative Adversarial Networks. Parallel Separable 3D Convolution for Video and Volumetric Data Understanding. Beyond Word Embeddings: Learning Entity and Concept Representations from Large Scale Knowledge Bases. FML: Face Model Learning from Videos. The Cl …
Dueling Bandits with Qualitative Feedback
Title | Dueling Bandits with Qualitative Feedback |
Authors | Liyuan Xu, Junya Honda, Masashi Sugiyama |
Abstract | We formulate and study a novel multi-armed bandit problem called the qualitative dueling bandit (QDB) problem, where an agent observes not numeric but qualitative feedback by pulling each arm. We employ the same regret as the dueling bandit (DB) problem where the duel is carried out by comparing the qualitative feedback. Although we can naively use classic DB algorithms for solving the QDB problem, this reduction significantly worsens the performance—actually, in the QDB problem, the probability that one arm wins the duel over another arm can be directly estimated without carrying out actual duels. In this paper, we propose such direct algorithms for the QDB problem. Our theoretical analysis shows that the proposed algorithms significantly outperform DB algorithms by incorporating the qualitative feedback, and experimental results also demonstrate vast improvement over the existing DB algorithms. |
Tasks | |
Published | 2018-09-14 |
URL | http://arxiv.org/abs/1809.05274v2 |
http://arxiv.org/pdf/1809.05274v2.pdf | |
PWC | https://paperswithcode.com/paper/dueling-bandits-with-qualitative-feedback |
Repo | |
Framework | |
GAN Augmentation: Augmenting Training Data using Generative Adversarial Networks
Title | GAN Augmentation: Augmenting Training Data using Generative Adversarial Networks |
Authors | Christopher Bowles, Liang Chen, Ricardo Guerrero, Paul Bentley, Roger Gunn, Alexander Hammers, David Alexander Dickie, Maria Valdés Hernández, Joanna Wardlaw, Daniel Rueckert |
Abstract | One of the biggest issues facing the use of machine learning in medical imaging is the lack of availability of large, labelled datasets. The annotation of medical images is not only expensive and time consuming but also highly dependent on the availability of expert observers. The limited amount of training data can inhibit the performance of supervised machine learning algorithms which often need very large quantities of data on which to train to avoid overfitting. So far, much effort has been directed at extracting as much information as possible from what data is available. Generative Adversarial Networks (GANs) offer a novel way to unlock additional information from a dataset by generating synthetic samples with the appearance of real images. This paper demonstrates the feasibility of introducing GAN derived synthetic data to the training datasets in two brain segmentation tasks, leading to improvements in Dice Similarity Coefficient (DSC) of between 1 and 5 percentage points under different conditions, with the strongest effects seen fewer than ten training image stacks are available. |
Tasks | Brain Segmentation |
Published | 2018-10-25 |
URL | http://arxiv.org/abs/1810.10863v1 |
http://arxiv.org/pdf/1810.10863v1.pdf | |
PWC | https://paperswithcode.com/paper/gan-augmentation-augmenting-training-data |
Repo | |
Framework | |
Parallel Separable 3D Convolution for Video and Volumetric Data Understanding
Title | Parallel Separable 3D Convolution for Video and Volumetric Data Understanding |
Authors | Felix Gonda, Donglai Wei, Toufiq Parag, Hanspeter Pfister |
Abstract | For video and volumetric data understanding, 3D convolution layers are widely used in deep learning, however, at the cost of increasing computation and training time. Recent works seek to replace the 3D convolution layer with convolution blocks, e.g. structured combinations of 2D and 1D convolution layers. In this paper, we propose a novel convolution block, Parallel Separable 3D Convolution (PmSCn), which applies m parallel streams of n 2D and one 1D convolution layers along different dimensions. We first mathematically justify the need of parallel streams (Pm) to replace a single 3D convolution layer through tensor decomposition. Then we jointly replace consecutive 3D convolution layers, common in modern network architectures, with the multiple 2D convolution layers (Cn). Lastly, we empirically show that PmSCn is applicable to different backbone architectures, such as ResNet, DenseNet, and UNet, for different applications, such as video action recognition, MRI brain segmentation, and electron microscopy segmentation. In all three applications, we replace the 3D convolution layers in state-of-the art models with PmSCn and achieve around 14% improvement in test performance and 40% reduction in model size and on average. |
Tasks | Brain Segmentation, Temporal Action Localization |
Published | 2018-09-11 |
URL | http://arxiv.org/abs/1809.04096v1 |
http://arxiv.org/pdf/1809.04096v1.pdf | |
PWC | https://paperswithcode.com/paper/parallel-separable-3d-convolution-for-video |
Repo | |
Framework | |
Beyond Word Embeddings: Learning Entity and Concept Representations from Large Scale Knowledge Bases
Title | Beyond Word Embeddings: Learning Entity and Concept Representations from Large Scale Knowledge Bases |
Authors | Walid Shalaby, Wlodek Zadrozny, Hongxia Jin |
Abstract | Text representations using neural word embeddings have proven effective in many NLP applications. Recent researches adapt the traditional word embedding models to learn vectors of multiword expressions (concepts/entities). However, these methods are limited to textual knowledge bases (e.g., Wikipedia). In this paper, we propose a novel and simple technique for integrating the knowledge about concepts from two large scale knowledge bases of different structure (Wikipedia and Probase) in order to learn concept representations. We adapt the efficient skip-gram model to seamlessly learn from the knowledge in Wikipedia text and Probase concept graph. We evaluate our concept embedding models on two tasks: (1) analogical reasoning, where we achieve a state-of-the-art performance of 91% on semantic analogies, (2) concept categorization, where we achieve a state-of-the-art performance on two benchmark datasets achieving categorization accuracy of 100% on one and 98% on the other. Additionally, we present a case study to evaluate our model on unsupervised argument type identification for neural semantic parsing. We demonstrate the competitive accuracy of our unsupervised method and its ability to better generalize to out of vocabulary entity mentions compared to the tedious and error prone methods which depend on gazetteers and regular expressions. |
Tasks | Semantic Parsing, Word Embeddings |
Published | 2018-01-01 |
URL | http://arxiv.org/abs/1801.00388v2 |
http://arxiv.org/pdf/1801.00388v2.pdf | |
PWC | https://paperswithcode.com/paper/beyond-word-embeddings-learning-entity-and |
Repo | |
Framework | |
FML: Face Model Learning from Videos
Title | FML: Face Model Learning from Videos |
Authors | Ayush Tewari, Florian Bernard, Pablo Garrido, Gaurav Bharaj, Mohamed Elgharib, Hans-Peter Seidel, Patrick Pérez, Michael Zollhöfer, Christian Theobalt |
Abstract | Monocular image-based 3D reconstruction of faces is a long-standing problem in computer vision. Since image data is a 2D projection of a 3D face, the resulting depth ambiguity makes the problem ill-posed. Most existing methods rely on data-driven priors that are built from limited 3D face scans. In contrast, we propose multi-frame video-based self-supervised training of a deep network that (i) learns a face identity model both in shape and appearance while (ii) jointly learning to reconstruct 3D faces. Our face model is learned using only corpora of in-the-wild video clips collected from the Internet. This virtually endless source of training data enables learning of a highly general 3D face model. In order to achieve this, we propose a novel multi-frame consistency loss that ensures consistent shape and appearance across multiple frames of a subject’s face, thus minimizing depth ambiguity. At test time we can use an arbitrary number of frames, so that we can perform both monocular as well as multi-frame reconstruction. |
Tasks | 3D Reconstruction |
Published | 2018-12-18 |
URL | http://arxiv.org/abs/1812.07603v2 |
http://arxiv.org/pdf/1812.07603v2.pdf | |
PWC | https://paperswithcode.com/paper/fml-face-model-learning-from-videos |
Repo | |
Framework | |
The Clickbait Challenge 2017: Towards a Regression Model for Clickbait Strength
Title | The Clickbait Challenge 2017: Towards a Regression Model for Clickbait Strength |
Authors | Martin Potthast, Tim Gollub, Matthias Hagen, Benno Stein |
Abstract | Clickbait has grown to become a nuisance to social media users and social media operators alike. Malicious content publishers misuse social media to manipulate as many users as possible to visit their websites using clickbait messages. Machine learning technology may help to handle this problem, giving rise to automatic clickbait detection. To accelerate progress in this direction, we organized the Clickbait Challenge 2017, a shared task inviting the submission of clickbait detectors for a comparative evaluation. A total of 13 detectors have been submitted, achieving significant improvements over the previous state of the art in terms of detection performance. Also, many of the submitted approaches have been published open source, rendering them reproducible, and a good starting point for newcomers. While the 2017 challenge has passed, we maintain the evaluation system and answer to new registrations in support of the ongoing research on better clickbait detectors. |
Tasks | Clickbait Detection |
Published | 2018-12-27 |
URL | http://arxiv.org/abs/1812.10847v1 |
http://arxiv.org/pdf/1812.10847v1.pdf | |
PWC | https://paperswithcode.com/paper/the-clickbait-challenge-2017-towards-a |
Repo | |
Framework | |
From Deep to Physics-Informed Learning of Turbulence: Diagnostics
Title | From Deep to Physics-Informed Learning of Turbulence: Diagnostics |
Authors | Ryan King, Oliver Hennigh, Arvind Mohan, Michael Chertkov |
Abstract | We describe tests validating progress made toward acceleration and automation of hydrodynamic codes in the regime of developed turbulence by three Deep Learning (DL) Neural Network (NN) schemes trained on Direct Numerical Simulations of turbulence. Even the bare DL solutions, which do not take into account any physics of turbulence explicitly, are impressively good overall when it comes to qualitative description of important features of turbulence. However, the early tests have also uncovered some caveats of the DL approaches. We observe that the static DL scheme, implementing Convolutional GAN and trained on spatial snapshots of turbulence, fails to reproduce intermittency of turbulent fluctuations at small scales and details of the turbulence geometry at large scales. We show that the dynamic NN schemes, namely LAT-NET and Compressed Convolutional LSTM, trained on a temporal sequence of turbulence snapshots are capable to correct for the caveats of the static NN. We suggest a path forward towards improving reproducibility of the large-scale geometry of turbulence with NN. |
Tasks | |
Published | 2018-10-16 |
URL | http://arxiv.org/abs/1810.07785v2 |
http://arxiv.org/pdf/1810.07785v2.pdf | |
PWC | https://paperswithcode.com/paper/from-deep-to-physics-informed-learning-of |
Repo | |
Framework | |
Deep Learning from Label Proportions for Emphysema Quantification
Title | Deep Learning from Label Proportions for Emphysema Quantification |
Authors | Gerda Bortsova, Florian Dubost, Silas Ørting, Ioannis Katramados, Laurens Hogeweg, Laura Thomsen, Mathilde Wille, Marleen de Bruijne |
Abstract | We propose an end-to-end deep learning method that learns to estimate emphysema extent from proportions of the diseased tissue. These proportions were visually estimated by experts using a standard grading system, in which grades correspond to intervals (label example: 1-5% of diseased tissue). The proposed architecture encodes the knowledge that the labels represent a volumetric proportion. A custom loss is designed to learn with intervals. Thus, during training, our network learns to segment the diseased tissue such that its proportions fit the ground truth intervals. Our architecture and loss combined improve the performance substantially (8% ICC) compared to a more conventional regression network. We outperform traditional lung densitometry and two recently published methods for emphysema quantification by a large margin (at least 7% AUC and 15% ICC), and achieve near-human-level performance. Moreover, our method generates emphysema segmentations that predict the spatial distribution of emphysema at human level. |
Tasks | |
Published | 2018-07-23 |
URL | http://arxiv.org/abs/1807.08601v1 |
http://arxiv.org/pdf/1807.08601v1.pdf | |
PWC | https://paperswithcode.com/paper/deep-learning-from-label-proportions-for |
Repo | |
Framework | |
Newton-ADMM: A Distributed GPU-Accelerated Optimizer for Multiclass Classification Problems
Title | Newton-ADMM: A Distributed GPU-Accelerated Optimizer for Multiclass Classification Problems |
Authors | Chih-Hao Fang, Sudhir B Kylasa, Fred Roosta, Michael W. Mahoney, Ananth Grama |
Abstract | First-order optimization methods, such as stochastic gradient descent (SGD) and its variants, are widely used in machine learning applications due to their simplicity and low per-iteration costs. However, they often require larger numbers of iterations, with associated communication costs in distributed environments. In contrast, Newton-type methods, while having higher per-iteration costs, typically require a significantly smaller number of iterations, which directly translates to reduced communication costs. In this paper, we present a novel distributed optimizer for classification problems, which integrates a GPU-accelerated Newton-type solver with the global consensus formulation of Alternating Direction of Method Multipliers (ADMM). By leveraging the communication efficiency of ADMM, GPU-accelerated inexact-Newton solver, and an effective spectral penalty parameter selection strategy, we show that our proposed method (i) yields better generalization performance on several classification problems; (ii) significantly outperforms state-of-the-art methods in distributed time to solution; and (iii) offers better scaling on large distributed platforms. |
Tasks | |
Published | 2018-07-18 |
URL | https://arxiv.org/abs/1807.07132v3 |
https://arxiv.org/pdf/1807.07132v3.pdf | |
PWC | https://paperswithcode.com/paper/distributed-second-order-convex-optimization |
Repo | |
Framework | |
Imagining the Unseen: Learning a Distribution over Incomplete Images with Dense Latent Trees
Title | Imagining the Unseen: Learning a Distribution over Incomplete Images with Dense Latent Trees |
Authors | Sebastian Kaltwang, Sina Samangooei, John Redford, Andrew Blake |
Abstract | Images are composed as a hierarchy of object parts. We use this insight to create a generative graphical model that defines a hierarchical distribution over image parts. Typically, this leads to intractable inference due to loops in the graph. We propose an alternative model structure, the Dense Latent Tree (DLT), which avoids loops and allows for efficient exact inference, while maintaining a dense connectivity between parts of the hierarchy. The usefulness of DLTs is shown for the example task of image completion on partially observed MNIST and Fashion-MNIST data. We verify having successfully learned a hierarchical model of images by visualising its latent states. |
Tasks | |
Published | 2018-08-14 |
URL | http://arxiv.org/abs/1808.04745v1 |
http://arxiv.org/pdf/1808.04745v1.pdf | |
PWC | https://paperswithcode.com/paper/imagining-the-unseen-learning-a-distribution |
Repo | |
Framework | |
Pose Estimation for Objects with Rotational Symmetry
Title | Pose Estimation for Objects with Rotational Symmetry |
Authors | Enric Corona, Kaustav Kundu, Sanja Fidler |
Abstract | Pose estimation is a widely explored problem, enabling many robotic tasks such as grasping and manipulation. In this paper, we tackle the problem of pose estimation for objects that exhibit rotational symmetry, which are common in man-made and industrial environments. In particular, our aim is to infer poses for objects not seen at training time, but for which their 3D CAD models are available at test time. Previous work has tackled this problem by learning to compare captured views of real objects with the rendered views of their 3D CAD models, by embedding them in a joint latent space using neural networks. We show that sidestepping the issue of symmetry in this scenario during training leads to poor performance at test time. We propose a model that reasons about rotational symmetry during training by having access to only a small set of symmetry-labeled objects, whereby exploiting a large collection of unlabeled CAD models. We demonstrate that our approach significantly outperforms a naively trained neural network on a new pose dataset containing images of tools and hardware. |
Tasks | Pose Estimation |
Published | 2018-10-13 |
URL | http://arxiv.org/abs/1810.05780v1 |
http://arxiv.org/pdf/1810.05780v1.pdf | |
PWC | https://paperswithcode.com/paper/pose-estimation-for-objects-with-rotational |
Repo | |
Framework | |
Connectivity-Driven Brain Parcellation via Consensus Clustering
Title | Connectivity-Driven Brain Parcellation via Consensus Clustering |
Authors | Anvar Kurmukov, Ayagoz Mussabayeva, Yulia Denisova, Daniel Moyer, Boris Gutman |
Abstract | We present two related methods for deriving connectivity-based brain atlases from individual connectomes. The proposed methods exploit a previously proposed dense connectivity representation, termed continuous connectivity, by first performing graph-based hierarchical clustering of individual brains, and subsequently aggregating the individual parcellations into a consensus parcellation. The search for consensus minimizes the sum of cluster membership distances, effectively estimating a pseudo-Karcher mean of individual parcellations. We assess the quality of our parcellations using (1) Kullback-Liebler and Jensen-Shannon divergence with respect to the dense connectome representation, (2) inter-hemispheric symmetry, and (3) performance of the simplified connectome in a biological sex classification task. We find that the parcellation based-atlas computed using a greedy search at a hierarchical depth 3 outperforms all other parcellation-based atlases as well as the standard Dessikan-Killiany anatomical atlas in all three assessments. |
Tasks | |
Published | 2018-08-10 |
URL | http://arxiv.org/abs/1808.04262v1 |
http://arxiv.org/pdf/1808.04262v1.pdf | |
PWC | https://paperswithcode.com/paper/connectivity-driven-brain-parcellation-via |
Repo | |
Framework | |
Vector Quantized Spectral Clustering applied to Soybean Whole Genome Sequences
Title | Vector Quantized Spectral Clustering applied to Soybean Whole Genome Sequences |
Authors | Aditya A. Shastri, Kapil Ahuja, Milind B. Ratnaparkhe, Aditya Shah, Aishwary Gagrani, Anant Lal |
Abstract | We develop a Vector Quantized Spectral Clustering (VQSC) algorithm that is a combination of Spectral Clustering (SC) and Vector Quantization (VQ) sampling for grouping Soybean genomes. The inspiration here is to use SC for its accuracy and VQ to make the algorithm computationally cheap (the complexity of SC is cubic in-terms of the input size). Although the combination of SC and VQ is not new, the novelty of our work is in developing the crucial similarity matrix in SC as well as use of k-medoids in VQ, both adapted for the Soybean genome data. We compare our approach with commonly used techniques like UPGMA (Un-weighted Pair Graph Method with Arithmetic Mean) and NJ (Neighbour Joining). Experimental results show that our approach outperforms both these techniques significantly in terms of cluster quality (up to 25% better cluster quality) and time complexity (order of magnitude faster). |
Tasks | Quantization |
Published | 2018-09-30 |
URL | http://arxiv.org/abs/1810.00398v1 |
http://arxiv.org/pdf/1810.00398v1.pdf | |
PWC | https://paperswithcode.com/paper/vector-quantized-spectral-clustering-applied |
Repo | |
Framework | |
Hybrid Building/Floor Classification and Location Coordinates Regression Using A Single-Input and Multi-Output Deep Neural Network for Large-Scale Indoor Localization Based on Wi-Fi Fingerprinting
Title | Hybrid Building/Floor Classification and Location Coordinates Regression Using A Single-Input and Multi-Output Deep Neural Network for Large-Scale Indoor Localization Based on Wi-Fi Fingerprinting |
Authors | Kyeong Soo Kim |
Abstract | In this paper, we propose hybrid building/floor classification and floor-level two-dimensional location coordinates regression using a single-input and multi-output (SIMO) deep neural network (DNN) for large-scale indoor localization based on Wi-Fi fingerprinting. The proposed scheme exploits the different nature of the estimation of building/floor and floor-level location coordinates and uses a different estimation framework for each task with a dedicated output and hidden layers enabled by SIMO DNN architecture. We carry out preliminary evaluation of the performance of the hybrid floor classification and floor-level two-dimensional location coordinates regression using new Wi-Fi crowdsourced fingerprinting datasets provided by Tampere University of Technology (TUT), Finland, covering a single building with five floors. Experimental results demonstrate that the proposed SIMO-DNN-based hybrid classification/regression scheme outperforms existing schemes in terms of both floor detection rate and mean positioning errors. |
Tasks | |
Published | 2018-10-13 |
URL | http://arxiv.org/abs/1810.05868v1 |
http://arxiv.org/pdf/1810.05868v1.pdf | |
PWC | https://paperswithcode.com/paper/hybrid-buildingfloor-classification-and |
Repo | |
Framework | |
Adaptive Online Learning in Dynamic Environments
Title | Adaptive Online Learning in Dynamic Environments |
Authors | Lijun Zhang, Shiyin Lu, Zhi-Hua Zhou |
Abstract | In this paper, we study online convex optimization in dynamic environments, and aim to bound the dynamic regret with respect to any sequence of comparators. Existing work have shown that online gradient descent enjoys an $O(\sqrt{T}(1+P_T))$ dynamic regret, where $T$ is the number of iterations and $P_T$ is the path-length of the comparator sequence. However, this result is unsatisfactory, as there exists a large gap from the $\Omega(\sqrt{T(1+P_T)})$ lower bound established in our paper. To address this limitation, we develop a novel online method, namely adaptive learning for dynamic environment (Ader), which achieves an optimal $O(\sqrt{T(1+P_T)})$ dynamic regret. The basic idea is to maintain a set of experts, each attaining an optimal dynamic regret for a specific path-length, and combines them with an expert-tracking algorithm. Furthermore, we propose an improved Ader based on the surrogate loss, and in this way the number of gradient evaluations per round is reduced from $O(\log T)$ to $1$. Finally, we extend Ader to the setting that a sequence of dynamical models is available to characterize the comparators. |
Tasks | |
Published | 2018-10-25 |
URL | http://arxiv.org/abs/1810.10815v1 |
http://arxiv.org/pdf/1810.10815v1.pdf | |
PWC | https://paperswithcode.com/paper/adaptive-online-learning-in-dynamic |
Repo | |
Framework | |