Paper Group ANR 1123
Brain Tumor Type Classification via Capsule Networks. Personalizing Intervention Probabilities By Pooling. A shortest-path based clustering algorithm for joint human-machine analysis of complex datasets. Pairwise Body-Part Attention for Recognizing Human-Object Interactions. Deep Reinforcement Learning for Resource Management in Network Slicing. De …
Brain Tumor Type Classification via Capsule Networks
| Title | Brain Tumor Type Classification via Capsule Networks |
| Authors | Parnian Afshar, Arash Mohammadi, Konstantinos N. Plataniotis |
| Abstract | Brain tumor is considered as one of the deadliest and most common form of cancer both in children and in adults. Consequently, determining the correct type of brain tumor in early stages is of significant importance to devise a precise treatment plan and predict patient’s response to the adopted treatment. In this regard, there has been a recent surge of interest in designing Convolutional Neural Networks (CNNs) for the problem of brain tumor type classification. However, CNNs typically require large amount of training data and can not properly handle input transformations. Capsule networks (referred to as CapsNets) are brand new machine learning architectures proposed very recently to overcome these shortcomings of CNNs, and posed to revolutionize deep learning solutions. Of particular interest to this work is that Capsule networks are robust to rotation and affine transformation, and require far less training data, which is the case for processing medical image datasets including brain Magnetic Resonance Imaging (MRI) images. In this paper, we focus to achieve the following four objectives: (i) Adopt and incorporate CapsNets for the problem of brain tumor classification to design an improved architecture which maximizes the accuracy of the classification problem at hand; (ii) Investigate the over-fitting problem of CapsNets based on a real set of MRI images; (iii) Explore whether or not CapsNets are capable of providing better fit for the whole brain images or just the segmented tumor, and; (iv) Develop a visualization paradigm for the output of the CapsNet to better explain the learned features. Our results show that the proposed approach can successfully overcome CNNs for the brain tumor classification problem. |
| Tasks | |
| Published | 2018-02-27 |
| URL | http://arxiv.org/abs/1802.10200v2 |
| http://arxiv.org/pdf/1802.10200v2.pdf | |
| PWC | https://paperswithcode.com/paper/brain-tumor-type-classification-via-capsule |
| Repo | |
| Framework | |
Personalizing Intervention Probabilities By Pooling
| Title | Personalizing Intervention Probabilities By Pooling |
| Authors | Sabina Tomkins, Predrag Klasnja, Susan Murphy |
| Abstract | In many mobile health interventions, treatments should only be delivered in a particular context, for example when a user is currently stressed, walking or sedentary. Even in an optimal context, concerns about user burden can restrict which treatments are sent. To diffuse the treatment delivery over times when a user is in a desired context, it is critical to predict the future number of times the context will occur. The focus of this paper is on whether personalization can improve predictions in these settings. Though the variance between individuals’ behavioral patterns suggest that personalization should be useful, the amount of individual-level data limits its capabilities. Thus, we investigate several methods which pool data across users to overcome these deficiencies and find that pooling lowers the overall error rate relative to both personalized and batch approaches. |
| Tasks | |
| Published | 2018-12-02 |
| URL | http://arxiv.org/abs/1812.00463v1 |
| http://arxiv.org/pdf/1812.00463v1.pdf | |
| PWC | https://paperswithcode.com/paper/personalizing-intervention-probabilities-by |
| Repo | |
| Framework | |
A shortest-path based clustering algorithm for joint human-machine analysis of complex datasets
| Title | A shortest-path based clustering algorithm for joint human-machine analysis of complex datasets |
| Authors | Diego Ulisse Pizzagalli, Santiago Fernandez Gonzalez, Rolf Krause |
| Abstract | Clustering is a technique for the analysis of datasets obtained by empirical studies in several disciplines with a major application for biomedical research. Essentially, clustering algorithms are executed by machines aiming at finding groups of related points in a dataset. However, the result of grouping depends on both metrics for point-to-point similarity and rules for point-to-group association. Indeed, non-appropriate metrics and rules can lead to undesirable clustering artifacts. This is especially relevant for datasets, where groups with heterogeneous structures co-exist. In this work, we propose an algorithm that achieves clustering by exploring the paths between points. This allows both, to evaluate the properties of the path (such as gaps, density variations, etc.), and expressing the preference for certain paths. Moreover, our algorithm supports the integration of existing knowledge about admissible and non-admissible clusters by training a path classifier. We demonstrate the accuracy of the proposed method on challenging datasets including points from synthetic shapes in publicly available benchmarks and microscopy data. |
| Tasks | |
| Published | 2018-12-31 |
| URL | http://arxiv.org/abs/1812.11850v1 |
| http://arxiv.org/pdf/1812.11850v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-shortest-path-based-clustering-algorithm |
| Repo | |
| Framework | |
Pairwise Body-Part Attention for Recognizing Human-Object Interactions
| Title | Pairwise Body-Part Attention for Recognizing Human-Object Interactions |
| Authors | Hao-Shu Fang, Jinkun Cao, Yu-Wing Tai, Cewu Lu |
| Abstract | In human-object interactions (HOI) recognition, conventional methods consider the human body as a whole and pay a uniform attention to the entire body region. They ignore the fact that normally, human interacts with an object by using some parts of the body. In this paper, we argue that different body parts should be paid with different attention in HOI recognition, and the correlations between different body parts should be further considered. This is because our body parts always work collaboratively. We propose a new pairwise body-part attention model which can learn to focus on crucial parts, and their correlations for HOI recognition. A novel attention based feature selection method and a feature representation scheme that can capture pairwise correlations between body parts are introduced in the model. Our proposed approach achieved 4% improvement over the state-of-the-art results in HOI recognition on the HICO dataset. We will make our model and source codes publicly available. |
| Tasks | Feature Selection, Human-Object Interaction Detection |
| Published | 2018-07-28 |
| URL | http://arxiv.org/abs/1807.10889v1 |
| http://arxiv.org/pdf/1807.10889v1.pdf | |
| PWC | https://paperswithcode.com/paper/pairwise-body-part-attention-for-recognizing |
| Repo | |
| Framework | |
Deep Reinforcement Learning for Resource Management in Network Slicing
| Title | Deep Reinforcement Learning for Resource Management in Network Slicing |
| Authors | Rongpeng Li, Zhifeng Zhao, Qi Sun, Chi-Lin I, Chenyang Yang, Xianfu Chen, Minjian Zhao, Honggang Zhang |
| Abstract | Network slicing is born as an emerging business to operators, by allowing them to sell the customized slices to various tenants at different prices. In order to provide better-performing and cost-efficient services, network slicing involves challenging technical issues and urgently looks forward to intelligent innovations to make the resource management consistent with users’ activities per slice. In that regard, deep reinforcement learning (DRL), which focuses on how to interact with the environment by trying alternative actions and reinforcing the tendency actions producing more rewarding consequences, is assumed to be a promising solution. In this paper, after briefly reviewing the fundamental concepts of DRL, we investigate the application of DRL in solving some typical resource management for network slicing scenarios, which include radio resource slicing and priority-based core network slicing, and demonstrate the advantage of DRL over several competing schemes through extensive simulations. Finally, we also discuss the possible challenges to apply DRL in network slicing from a general perspective. |
| Tasks | |
| Published | 2018-05-17 |
| URL | http://arxiv.org/abs/1805.06591v3 |
| http://arxiv.org/pdf/1805.06591v3.pdf | |
| PWC | https://paperswithcode.com/paper/deep-reinforcement-learning-for-resource |
| Repo | |
| Framework | |
Deep Active Learning with a Neural Architecture Search
| Title | Deep Active Learning with a Neural Architecture Search |
| Authors | Yonatan Geifman, Ran El-Yaniv |
| Abstract | We consider active learning of deep neural networks. Most active learning works in this context have focused on studying effective querying mechanisms and assumed that an appropriate network architecture is a priori known for the problem at hand. We challenge this assumption and propose a novel active strategy whereby the learning algorithm searches for effective architectures on the fly, while actively learning. We apply our strategy using three known querying techniques (softmax response, MC-dropout, and coresets) and show that the proposed approach overwhelmingly outperforms active learning using fixed architectures. |
| Tasks | Active Learning, Neural Architecture Search |
| Published | 2018-11-19 |
| URL | https://arxiv.org/abs/1811.07579v2 |
| https://arxiv.org/pdf/1811.07579v2.pdf | |
| PWC | https://paperswithcode.com/paper/deep-active-learning-with-a-neural |
| Repo | |
| Framework | |
On the loss landscape of a class of deep neural networks with no bad local valleys
| Title | On the loss landscape of a class of deep neural networks with no bad local valleys |
| Authors | Quynh Nguyen, Mahesh Chandra Mukkamala, Matthias Hein |
| Abstract | We identify a class of over-parameterized deep neural networks with standard activation functions and cross-entropy loss which provably have no bad local valley, in the sense that from any point in parameter space there exists a continuous path on which the cross-entropy loss is non-increasing and gets arbitrarily close to zero. This implies that these networks have no sub-optimal strict local minima. |
| Tasks | |
| Published | 2018-09-27 |
| URL | http://arxiv.org/abs/1809.10749v2 |
| http://arxiv.org/pdf/1809.10749v2.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-loss-landscape-of-a-class-of-deep |
| Repo | |
| Framework | |
Manipulating Attributes of Natural Scenes via Hallucination
| Title | Manipulating Attributes of Natural Scenes via Hallucination |
| Authors | Levent Karacan, Zeynep Akata, Aykut Erdem, Erkut Erdem |
| Abstract | In this study, we explore building a two-stage framework for enabling users to directly manipulate high-level attributes of a natural scene. The key to our approach is a deep generative network which can hallucinate images of a scene as if they were taken at a different season (e.g. during winter), weather condition (e.g. in a cloudy day) or time of the day (e.g. at sunset). Once the scene is hallucinated with the given attributes, the corresponding look is then transferred to the input image while preserving the semantic details intact, giving a photo-realistic manipulation result. As the proposed framework hallucinates what the scene will look like, it does not require any reference style image as commonly utilized in most of the appearance or style transfer approaches. Moreover, it allows to simultaneously manipulate a given scene according to a diverse set of transient attributes within a single model, eliminating the need of training multiple networks per each translation task. Our comprehensive set of qualitative and quantitative results demonstrate the effectiveness of our approach against the competing methods. |
| Tasks | Style Transfer |
| Published | 2018-08-22 |
| URL | https://arxiv.org/abs/1808.07413v3 |
| https://arxiv.org/pdf/1808.07413v3.pdf | |
| PWC | https://paperswithcode.com/paper/manipulating-attributes-of-natural-scenes-via |
| Repo | |
| Framework | |
Iterative Amortized Inference
| Title | Iterative Amortized Inference |
| Authors | Joseph Marino, Yisong Yue, Stephan Mandt |
| Abstract | Inference models are a key component in scaling variational inference to deep latent variable models, most notably as encoder networks in variational auto-encoders (VAEs). By replacing conventional optimization-based inference with a learned model, inference is amortized over data examples and therefore more computationally efficient. However, standard inference models are restricted to direct mappings from data to approximate posterior estimates. The failure of these models to reach fully optimized approximate posterior estimates results in an amortization gap. We aim toward closing this gap by proposing iterative inference models, which learn to perform inference optimization through repeatedly encoding gradients. Our approach generalizes standard inference models in VAEs and provides insight into several empirical findings, including top-down inference techniques. We demonstrate the inference optimization capabilities of iterative inference models and show that they outperform standard inference models on several benchmark data sets of images and text. |
| Tasks | Latent Variable Models |
| Published | 2018-07-24 |
| URL | http://arxiv.org/abs/1807.09356v1 |
| http://arxiv.org/pdf/1807.09356v1.pdf | |
| PWC | https://paperswithcode.com/paper/iterative-amortized-inference |
| Repo | |
| Framework | |
Surgical Activity Recognition in Robot-Assisted Radical Prostatectomy using Deep Learning
| Title | Surgical Activity Recognition in Robot-Assisted Radical Prostatectomy using Deep Learning |
| Authors | Aneeq Zia, Andrew Hung, Irfan Essa, Anthony Jarc |
| Abstract | Adverse surgical outcomes are costly to patients and hospitals. Approaches to benchmark surgical care are often limited to gross measures across the entire procedure despite the performance of particular tasks being largely responsible for undesirable outcomes. In order to produce metrics from tasks as opposed to the whole procedure, methods to recognize automatically individual surgical tasks are needed. In this paper, we propose several approaches to recognize surgical activities in robot-assisted minimally invasive surgery using deep learning. We collected a clinical dataset of 100 robot-assisted radical prostatectomies (RARP) with 12 tasks each and propose `RP-Net’, a modified version of InceptionV3 model, for image based surgical activity recognition. We achieve an average precision of 80.9% and average recall of 76.7% across all tasks using RP-Net which out-performs all other RNN and CNN based models explored in this paper. Our results suggest that automatic surgical activity recognition during RARP is feasible and can be the foundation for advanced analytics. | |
| Tasks | Activity Recognition |
| Published | 2018-06-01 |
| URL | http://arxiv.org/abs/1806.00466v1 |
| http://arxiv.org/pdf/1806.00466v1.pdf | |
| PWC | https://paperswithcode.com/paper/surgical-activity-recognition-in-robot |
| Repo | |
| Framework | |
Angle constrained path to cluster multiple manifolds
| Title | Angle constrained path to cluster multiple manifolds |
| Authors | Amir Babaeian |
| Abstract | In this paper, we propose a method to cluster multiple intersected manifolds. The algorithm chooses several landmark nodes randomly and then checks whether there is an angle constrained path between each landmark node and every other node in the neighborhood graph. When the points lie on different manifolds with intersection they should not be connected using a smooth path, thus the angle constraint is used to prevent connecting points from one cluster to another one. The resulting algorithm is implemented as a simple variation of Dijkstras algorithm used in Isomap. However, Isomap was specifically designed for dimensionality reduction in the single-manifold setting, and in particular, can-not handle intersections. Our method is simpler than the previous proposals in the literature and performs comparably to the best methods, both on simulated and some real datasets. |
| Tasks | Dimensionality Reduction |
| Published | 2018-02-21 |
| URL | http://arxiv.org/abs/1802.07416v1 |
| http://arxiv.org/pdf/1802.07416v1.pdf | |
| PWC | https://paperswithcode.com/paper/angle-constrained-path-to-cluster-multiple |
| Repo | |
| Framework | |
Static and Dynamic Vector Semantics for Lambda Calculus Models of Natural Language
| Title | Static and Dynamic Vector Semantics for Lambda Calculus Models of Natural Language |
| Authors | Mehrnoosh Sadrzadeh, Reinhard Muskens |
| Abstract | Vector models of language are based on the contextual aspects of language, the distributions of words and how they co-occur in text. Truth conditional models focus on the logical aspects of language, compositional properties of words and how they compose to form sentences. In the truth conditional approach, the denotation of a sentence determines its truth conditions, which can be taken to be a truth value, a set of possible worlds, a context change potential, or similar. In the vector models, the degree of co-occurrence of words in context determines how similar the meanings of words are. In this paper, we put these two models together and develop a vector semantics for language based on the simply typed lambda calculus models of natural language. We provide two types of vector semantics: a static one that uses techniques familiar from the truth conditional tradition and a dynamic one based on a form of dynamic interpretation inspired by Heim’s context change potentials. We show how the dynamic model can be applied to entailment between a corpus and a sentence and we provide examples. |
| Tasks | |
| Published | 2018-10-26 |
| URL | http://arxiv.org/abs/1810.11351v1 |
| http://arxiv.org/pdf/1810.11351v1.pdf | |
| PWC | https://paperswithcode.com/paper/static-and-dynamic-vector-semantics-for |
| Repo | |
| Framework | |
UG18 at SemEval-2018 Task 1: Generating Additional Training Data for Predicting Emotion Intensity in Spanish
| Title | UG18 at SemEval-2018 Task 1: Generating Additional Training Data for Predicting Emotion Intensity in Spanish |
| Authors | Marloes Kuijper, Mike van Lenthe, Rik van Noord |
| Abstract | The present study describes our submission to SemEval 2018 Task 1: Affect in Tweets. Our Spanish-only approach aimed to demonstrate that it is beneficial to automatically generate additional training data by (i) translating training data from other languages and (ii) applying a semi-supervised learning method. We find strong support for both approaches, with those models outperforming our regular models in all subtasks. However, creating a stepwise ensemble of different models as opposed to simply averaging did not result in an increase in performance. We placed second (EI-Reg), second (EI-Oc), fourth (V-Reg) and fifth (V-Oc) in the four Spanish subtasks we participated in. |
| Tasks | |
| Published | 2018-05-28 |
| URL | http://arxiv.org/abs/1805.10824v1 |
| http://arxiv.org/pdf/1805.10824v1.pdf | |
| PWC | https://paperswithcode.com/paper/ug18-at-semeval-2018-task-1-generating |
| Repo | |
| Framework | |
RegNet: Learning the Optimization of Direct Image-to-Image Pose Registration
| Title | RegNet: Learning the Optimization of Direct Image-to-Image Pose Registration |
| Authors | Lei Han, Mengqi Ji, Lu Fang, Matthias Nießner |
| Abstract | Direct image-to-image alignment that relies on the optimization of photometric error metrics suffers from limited convergence range and sensitivity to lighting conditions. Deep learning approaches has been applied to address this problem by learning better feature representations using convolutional neural networks, yet still require a good initialization. In this paper, we demonstrate that the inaccurate numerical Jacobian limits the convergence range which could be improved greatly using learned approaches. Based on this observation, we propose a novel end-to-end network, RegNet, to learn the optimization of image-to-image pose registration. By jointly learning feature representation for each pixel and partial derivatives that replace handcrafted ones (e.g., numerical differentiation) in the optimization step, the neural network facilitates end-to-end optimization. The energy landscape is constrained on both the feature representation and the learned Jacobian, hence providing more flexibility for the optimization as a consequence leads to more robust and faster convergence. In a series of experiments, including a broad ablation study, we demonstrate that RegNet is able to converge for large-baseline image pairs with fewer iterations. |
| Tasks | |
| Published | 2018-12-26 |
| URL | http://arxiv.org/abs/1812.10212v1 |
| http://arxiv.org/pdf/1812.10212v1.pdf | |
| PWC | https://paperswithcode.com/paper/regnet-learning-the-optimization-of-direct |
| Repo | |
| Framework | |
Towards Unsupervised Speech-to-Text Translation
| Title | Towards Unsupervised Speech-to-Text Translation |
| Authors | Yu-An Chung, Wei-Hung Weng, Schrasing Tong, James Glass |
| Abstract | We present a framework for building speech-to-text translation (ST) systems using only monolingual speech and text corpora, in other words, speech utterances from a source language and independent text from a target language. As opposed to traditional cascaded systems and end-to-end architectures, our system does not require any labeled data (i.e., transcribed source audio or parallel source and target text corpora) during training, making it especially applicable to language pairs with very few or even zero bilingual resources. The framework initializes the ST system with a cross-modal bilingual dictionary inferred from the monolingual corpora, that maps every source speech segment corresponding to a spoken word to its target text translation. For unseen source speech utterances, the system first performs word-by-word translation on each speech segment in the utterance. The translation is improved by leveraging a language model and a sequence denoising autoencoder to provide prior knowledge about the target language. Experimental results show that our unsupervised system achieves comparable BLEU scores to supervised end-to-end models despite the lack of supervision. We also provide an ablation analysis to examine the utility of each component in our system. |
| Tasks | Denoising, Language Modelling |
| Published | 2018-11-04 |
| URL | http://arxiv.org/abs/1811.01307v1 |
| http://arxiv.org/pdf/1811.01307v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-unsupervised-speech-to-text |
| Repo | |
| Framework | |
