Paper Group ANR 665
Measurement-based Online Available Bandwidth Estimation employing Reinforcement Learning. HGC: Hierarchical Group Convolution for Highly Efficient Neural Network. Research Report on Automatic Synthesis of Local Search Neighborhood Operators. An Empirical Evaluation Study on the Training of SDC Features for Dense Pixel Matching. A Language-Agnostic …
Measurement-based Online Available Bandwidth Estimation employing Reinforcement Learning
| Title | Measurement-based Online Available Bandwidth Estimation employing Reinforcement Learning |
| Authors | Sukhpreet Kaur Khangura, Sami Akın |
| Abstract | An accurate and fast estimation of the available bandwidth in a network with varying cross-traffic is a challenging task. The accepted probing tools, based on the fluid-flow model of a bottleneck link with first-in, first-out multiplexing, estimate the available bandwidth by measuring packet dispersions. The estimation becomes more difficult if packet dispersions deviate from the assumptions of the fluid-flow model in the presence of non-fluid bursty cross-traffic, multiple bottleneck links, and inaccurate time-stamping. This motivates us to explore the use of machine learning tools for available bandwidth estimation. Hence, we consider reinforcement learning and implement the single-state multi-armed bandit technique, which follows the $\epsilon$-greedy algorithm to find the available bandwidth. Our measurements and tests reveal that our proposed method identifies the available bandwidth with high precision. Furthermore, our method converges to the available bandwidth under a variety of notoriously difficult conditions, such as heavy traffic burstiness, different cross-traffic intensities, multiple bottleneck links, and in networks where the tight link and the bottleneck link are not same. Compared to the piece-wise linear network a model-based direct probing technique that employs a Kalman filter, our method shows more accurate estimates and faster convergence in certain network scenarios and does not require measurement noise statistics. |
| Tasks | |
| Published | 2019-06-05 |
| URL | https://arxiv.org/abs/1906.07095v1 |
| https://arxiv.org/pdf/1906.07095v1.pdf | |
| PWC | https://paperswithcode.com/paper/measurement-based-online-available-bandwidth |
| Repo | |
| Framework | |
HGC: Hierarchical Group Convolution for Highly Efficient Neural Network
| Title | HGC: Hierarchical Group Convolution for Highly Efficient Neural Network |
| Authors | Xukai Xie, Yuan Zhou, Sun-Yuan Kung |
| Abstract | Group convolution works well with many deep convolutional neural networks (CNNs) that can effectively compress the model by reducing the number of parameters and computational cost. Using this operation, feature maps of different group cannot communicate, which restricts their representation capability. To address this issue, in this work, we propose a novel operation named Hierarchical Group Convolution (HGC) for creating computationally efficient neural networks. Different from standard group convolution which blocks the inter-group information exchange and induces the severe performance degradation, HGC can hierarchically fuse the feature maps from each group and leverage the inter-group information effectively. Taking advantage of the proposed method, we introduce a family of compact networks called HGCNets. Compared to networks using standard group convolution, HGCNets have a huge improvement in accuracy at the same model size and complexity level. Extensive experimental results on the CIFAR dataset demonstrate that HGCNets obtain significant reduction of parameters and computational cost to achieve comparable performance over the prior CNN architectures designed for mobile devices such as MobileNet and ShuffleNet. |
| Tasks | |
| Published | 2019-06-09 |
| URL | https://arxiv.org/abs/1906.03657v1 |
| https://arxiv.org/pdf/1906.03657v1.pdf | |
| PWC | https://paperswithcode.com/paper/hgc-hierarchical-group-convolution-for-highly |
| Repo | |
| Framework | |
Research Report on Automatic Synthesis of Local Search Neighborhood Operators
| Title | Research Report on Automatic Synthesis of Local Search Neighborhood Operators |
| Authors | Mateusz Ślażyński |
| Abstract | Constraint Programming (CP) and Local Search (LS) are different paradigms for dealing with combinatorial search and optimization problems. Their complementary features motivated researchers to create hybrid CP/LS solutions, maintaining both the modeling capabilities of CP and the computational advantages of the heuristic-based LS approach. Research presented in this report is focused on developing a novel method to infer an efficient LS neighborhood operator based on the problem structure, as modeled in the CP paradigm. We consider a limited formal language that we call a Neighborhood Definition Language, used to specify the neighborhood operators in a fine-grained and declarative manner. Together with Logic Programming runtime called Noodle, it allows to automatically synthesize complex operators using a Grammar Evolution algorithm. |
| Tasks | |
| Published | 2019-09-18 |
| URL | https://arxiv.org/abs/1909.08261v1 |
| https://arxiv.org/pdf/1909.08261v1.pdf | |
| PWC | https://paperswithcode.com/paper/research-report-on-automatic-synthesis-of |
| Repo | |
| Framework | |
An Empirical Evaluation Study on the Training of SDC Features for Dense Pixel Matching
| Title | An Empirical Evaluation Study on the Training of SDC Features for Dense Pixel Matching |
| Authors | René Schuster, Oliver Wasenmüller, Christian Unger, Didier Stricker |
| Abstract | Training a deep neural network is a non-trivial task. Not only the tuning of hyperparameters, but also the gathering and selection of training data, the design of the loss function, and the construction of training schedules is important to get the most out of a model. In this study, we perform a set of experiments all related to these issues. The model for which different training strategies are investigated is the recently presented SDC descriptor network (stacked dilated convolution). It is used to describe images on pixel-level for dense matching tasks. Our work analyzes SDC in more detail, validates some best practices for training deep neural networks, and provides insights into training with multiple domain data. |
| Tasks | |
| Published | 2019-04-12 |
| URL | http://arxiv.org/abs/1904.06167v1 |
| http://arxiv.org/pdf/1904.06167v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-empirical-evaluation-study-on-the-training |
| Repo | |
| Framework | |
A Language-Agnostic Model for Semantic Source Code Labeling
| Title | A Language-Agnostic Model for Semantic Source Code Labeling |
| Authors | Ben Gelman, Bryan Hoyle, Jessica Moore, Joshua Saxe, David Slater |
| Abstract | Code search and comprehension have become more difficult in recent years due to the rapid expansion of available source code. Current tools lack a way to label arbitrary code at scale while maintaining up-to-date representations of new programming languages, libraries, and functionalities. Comprehensive labeling of source code enables users to search for documents of interest and obtain a high-level understanding of their contents. We use Stack Overflow code snippets and their tags to train a language-agnostic, deep convolutional neural network to automatically predict semantic labels for source code documents. On Stack Overflow code snippets, we demonstrate a mean area under ROC of 0.957 over a long-tailed list of 4,508 tags. We also manually validate the model outputs on a diverse set of unlabeled source code documents retrieved from Github, and we obtain a top-1 accuracy of 86.6%. This strongly indicates that the model successfully transfers its knowledge from Stack Overflow snippets to arbitrary source code documents. |
| Tasks | Code Search |
| Published | 2019-06-03 |
| URL | https://arxiv.org/abs/1906.01032v1 |
| https://arxiv.org/pdf/1906.01032v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-language-agnostic-model-for-semantic-source |
| Repo | |
| Framework | |
A Search-based Neural Model for Biomedical Nested and Overlapping Event Detection
| Title | A Search-based Neural Model for Biomedical Nested and Overlapping Event Detection |
| Authors | Kurt Espinosa, Makoto Miwa, Sophia Ananiadou |
| Abstract | We tackle the nested and overlapping event detection task and propose a novel search-based neural network (SBNN) structured prediction model that treats the task as a search problem on a relation graph of trigger-argument structures. Unlike existing structured prediction tasks such as dependency parsing, the task targets to detect DAG structures, which constitute events, from the relation graph. We define actions to construct events and use all the beams in a beam search to detect all event structures that may be overlapping and nested. The search process constructs events in a bottom-up manner while modelling the global properties for nested and overlapping structures simultaneously using neural networks. We show that the model achieves performance comparable to the state-of-the-art model Turku Event Extraction System (TEES) on the BioNLP Cancer Genetics (CG) Shared Task 2013 without the use of any syntactic and hand-engineered features. Further analyses on the development set show that our model is more computationally efficient while yielding higher F1-score performance. |
| Tasks | Dependency Parsing, Structured Prediction |
| Published | 2019-10-22 |
| URL | https://arxiv.org/abs/1910.10281v2 |
| https://arxiv.org/pdf/1910.10281v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-search-based-neural-model-for-biomedical |
| Repo | |
| Framework | |
A Divide-and-Conquer Approach towards Understanding Deep Networks
| Title | A Divide-and-Conquer Approach towards Understanding Deep Networks |
| Authors | Weilin Fu, Katharina Breininger, Roman Schaffert, Nishant Ravikumar, Andreas Maier |
| Abstract | Deep neural networks have achieved tremendous success in various fields including medical image segmentation. However, they have long been criticized for being a black-box, in that interpretation, understanding and correcting architectures is difficult as there is no general theory for deep neural network design. Previously, precision learning was proposed to fuse deep architectures and traditional approaches. Deep networks constructed in this way benefit from the original known operator, have fewer parameters, and improved interpretability. However, they do not yield state-of-the-art performance in all applications. In this paper, we propose to analyze deep networks using known operators, by adopting a divide-and-conquer strategy to replace network components, whilst retaining its performance. The task of retinal vessel segmentation is investigated for this purpose. We start with a high-performance U-Net and show by step-by-step conversion that we are able to divide the network into modules of known operators. The results indicate that a combination of a trainable guided filter and a trainable version of the Frangi filter yields a performance at the level of U-Net (AUC 0.974 vs. 0.972) with a tremendous reduction in parameters (111,536 vs. 9,575). In addition, the trained layers can be mapped back into their original algorithmic interpretation and analyzed using standard tools of signal processing. |
| Tasks | Medical Image Segmentation, Retinal Vessel Segmentation, Semantic Segmentation |
| Published | 2019-07-14 |
| URL | https://arxiv.org/abs/1907.06194v1 |
| https://arxiv.org/pdf/1907.06194v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-divide-and-conquer-approach-towards |
| Repo | |
| Framework | |
Breathing deformation model – application to multi-resolution abdominal MRI
| Title | Breathing deformation model – application to multi-resolution abdominal MRI |
| Authors | Chompunuch Sarasaen, Soumick Chatterjee, Mario Breitkopf, Domenico Iuso, Georg Rose, Oliver Speck |
| Abstract | Dynamic MRI is a technique of acquiring a series of images continuously to follow the physiological changes over time. However, such fast imaging results in low resolution images. In this work, abdominal deformation model computed from dynamic low resolution images have been applied to high resolution image, acquired previously, to generate dynamic high resolution MRI. Dynamic low resolution images were simulated into different breathing phases (inhale and exhale). Then, the image registration between breathing time points was performed using the B-spline SyN deformable model and using cross-correlation as a similarity metric. The deformation model between different breathing phases were estimated from highly undersampled data. This deformation model was then applied to the high resolution images to obtain high resolution images of different breathing phases. The results indicated that the deformation model could be computed from relatively very low resolution images. |
| Tasks | Image Registration |
| Published | 2019-10-10 |
| URL | https://arxiv.org/abs/1910.04456v1 |
| https://arxiv.org/pdf/1910.04456v1.pdf | |
| PWC | https://paperswithcode.com/paper/breathing-deformation-model-application-to |
| Repo | |
| Framework | |
NeurReg: Neural Registration and Its Application to Image Segmentation
| Title | NeurReg: Neural Registration and Its Application to Image Segmentation |
| Authors | Wentao Zhu, Andriy Myronenko, Ziyue Xu, Wenqi Li, Holger Roth, Yufang Huang, Fausto Milletari, Daguang Xu |
| Abstract | Registration is a fundamental task in medical image analysis which can be applied to several tasks including image segmentation, intra-operative tracking, multi-modal image alignment, and motion analysis. Popular registration tools such as ANTs and NiftyReg optimize an objective function for each pair of images from scratch which is time-consuming for large images with complicated deformation. Facilitated by the rapid progress of deep learning, learning-based approaches such as VoxelMorph have been emerging for image registration. These approaches can achieve competitive performance in a fraction of a second on advanced GPUs. In this work, we construct a neural registration framework, called NeurReg, with a hybrid loss of displacement fields and data similarity, which substantially improves the current state-of-the-art of registrations. Within the framework, we simulate various transformations by a registration simulator which generates fixed image and displacement field ground truth for training. Furthermore, we design three segmentation frameworks based on the proposed registration framework: 1) atlas-based segmentation, 2) joint learning of both segmentation and registration tasks, and 3) multi-task learning with atlas-based segmentation as an intermediate feature. Extensive experimental results validate the effectiveness of the proposed NeurReg framework based on various metrics: the endpoint error (EPE) of the predicted displacement field, mean square error (MSE), normalized local cross-correlation (NLCC), mutual information (MI), Dice coefficient, uncertainty estimation, and the interpretability of the segmentation. The proposed NeurReg improves registration accuracy with fast inference speed, which can greatly accelerate related medical image analysis tasks. |
| Tasks | Image Registration, Multi-Task Learning, Semantic Segmentation |
| Published | 2019-10-04 |
| URL | https://arxiv.org/abs/1910.01763v1 |
| https://arxiv.org/pdf/1910.01763v1.pdf | |
| PWC | https://paperswithcode.com/paper/neurreg-neural-registration-and-its |
| Repo | |
| Framework | |
When Deep Learning Met Code Search
| Title | When Deep Learning Met Code Search |
| Authors | Jose Cambronero, Hongyu Li, Seohyun Kim, Koushik Sen, Satish Chandra |
| Abstract | There have been multiple recent proposals on using deep neural networks for code search using natural language. Common across these proposals is the idea of $\mathit{embedding}$ code and natural language queries, into real vectors and then using vector distance to approximate semantic correlation between code and the query. Multiple approaches exist for learning these embeddings, including $\mathit{unsupervised}$ techniques, which rely only on a corpus of code examples, and $\mathit{supervised}$ techniques, which use an $\mathit{aligned}$ corpus of paired code and natural language descriptions. The goal of this supervision is to produce embeddings that are more similar for a query and the corresponding desired code snippet. Clearly, there are choices in whether to use supervised techniques at all, and if one does, what sort of network and training to use for supervision. This paper is the first to evaluate these choices systematically. To this end, we assembled implementations of state-of-the-art techniques to run on a common platform, training and evaluation corpora. To explore the design space in network complexity, we also introduced a new design point that is a $\mathit{minimal}$ supervision extension to an existing unsupervised technique. Our evaluation shows that: 1. adding supervision to an existing unsupervised technique can improve performance, though not necessarily by much; 2. simple networks for supervision can be more effective that more sophisticated sequence-based networks for code search; 3. while it is common to use docstrings to carry out supervision, there is a sizeable gap between the effectiveness of docstrings and a more query-appropriate supervision corpus. The evaluation dataset is now available at arXiv:1908.09804 |
| Tasks | Code Search |
| Published | 2019-05-09 |
| URL | https://arxiv.org/abs/1905.03813v4 |
| https://arxiv.org/pdf/1905.03813v4.pdf | |
| PWC | https://paperswithcode.com/paper/when-deep-learning-met-code-search |
| Repo | |
| Framework | |
Searching for Apparel Products from Images in the Wild
| Title | Searching for Apparel Products from Images in the Wild |
| Authors | Son Tran, Ming Du, Sampath Chanda, R. Manmatha, Cj Taylor |
| Abstract | In this age of social media, people often look at what others are wearing. In particular, Instagram and Twitter influencers often provide images of themselves wearing different outfits and their followers are often inspired to buy similar clothes.We propose a system to automatically find the closest visually similar clothes in the online Catalog (street-to-shop searching). The problem is challenging since the original images are taken under different pose and lighting conditions. The system initially localizes high-level descriptive regions (top, bottom, wristwear. . . ) using multiple CNN detectors such as YOLO and SSD that are trained specifically for apparel domain. It then classifies these regions into more specific regions such as t-shirts, tunic or dresses. Finally, a feature embedding learned using a multi-task function is recovered for every item and then compared with corresponding items in the online Catalog database and ranked according to distance. We validate our approach component-wise using benchmark datasets and end-to-end using human evaluation. |
| Tasks | |
| Published | 2019-07-04 |
| URL | https://arxiv.org/abs/1907.02244v1 |
| https://arxiv.org/pdf/1907.02244v1.pdf | |
| PWC | https://paperswithcode.com/paper/searching-for-apparel-products-from-images-in |
| Repo | |
| Framework | |
Poincaré Recurrence, Cycles and Spurious Equilibria in Gradient-Descent-Ascent for Non-Convex Non-Concave Zero-Sum Games
| Title | Poincaré Recurrence, Cycles and Spurious Equilibria in Gradient-Descent-Ascent for Non-Convex Non-Concave Zero-Sum Games |
| Authors | Lampros Flokas, Emmanouil-Vasileios Vlatakis-Gkaragkounis, Georgios Piliouras |
| Abstract | We study a wide class of non-convex non-concave min-max games that generalizes over standard bilinear zero-sum games. In this class, players control the inputs of a smooth function whose output is being applied to a bilinear zero-sum game. This class of games is motivated by the indirect nature of the competition in Generative Adversarial Networks, where players control the parameters of a neural network while the actual competition happens between the distributions that the generator and discriminator capture. We establish theoretically, that depending on the specific instance of the problem gradient-descent-ascent dynamics can exhibit a variety of behaviors antithetical to convergence to the game theoretically meaningful min-max solution. Specifically, different forms of recurrent behavior (including periodicity and Poincar'e recurrence) are possible as well as convergence to spurious (non-min-max) equilibria for a positive measure of initial conditions. At the technical level, our analysis combines tools from optimization theory, game theory and dynamical systems. |
| Tasks | |
| Published | 2019-10-28 |
| URL | https://arxiv.org/abs/1910.13010v1 |
| https://arxiv.org/pdf/1910.13010v1.pdf | |
| PWC | https://paperswithcode.com/paper/poincare-recurrence-cycles-and-spurious |
| Repo | |
| Framework | |
Deep Dilated Convolutional Nets for the Automatic Segmentation of Retinal Vessels
| Title | Deep Dilated Convolutional Nets for the Automatic Segmentation of Retinal Vessels |
| Authors | Ali Hatamizadeh, Hamid Hosseini, Zhengyuan Liu, Steven D. Schwartz, Demetri Terzopoulos |
| Abstract | The reliable segmentation of retinal vasculature can provide the means to diagnose and monitor the progression of a variety of diseases affecting the blood vessel network, including diabetes and hypertension. We leverage the power of convolutional neural networks to devise a reliable and fully automated method that can accurately detect, segment, and analyze retinal vessels. In particular, we propose a novel, fully convolutional deep neural network with an encoder-decoder architecture that employs dilated spatial pyramid pooling with multiple dilation rates to recover the lost content in the encoder and add multiscale contextual information to the decoder. We also propose a simple yet effective way of quantifying and tracking the widths of retinal vessels through direct use of the segmentation predictions. Unlike previous deep-learning-based approaches to retinal vessel segmentation that mainly rely on patch-wise analysis, our proposed method leverages a whole-image approach during training and inference, resulting in more efficient training and faster inference through the access of global content in the image. We have tested our method on two publicly available datasets, and our state-of-the-art results on both the DRIVE and CHASE-DB1 datasets attest to the effectiveness of our approach. |
| Tasks | Retinal Vessel Segmentation |
| Published | 2019-05-28 |
| URL | https://arxiv.org/abs/1905.12120v2 |
| https://arxiv.org/pdf/1905.12120v2.pdf | |
| PWC | https://paperswithcode.com/paper/deep-dilated-convolutional-nets-for-the |
| Repo | |
| Framework | |
Incremental Adaptation of NMT for Professional Post-editors: A User Study
| Title | Incremental Adaptation of NMT for Professional Post-editors: A User Study |
| Authors | Miguel Domingo, Mercedes García-Martínez, Álvaro Peris, Alexandre Helle, Amando Estela, Laurent Bié, Francisco Casacuberta, Manuel Herranz |
| Abstract | A common use of machine translation in the industry is providing initial translation hypotheses, which are later supervised and post-edited by a human expert. During this revision process, new bilingual data are continuously generated. Machine translation systems can benefit from these new data, incrementally updating the underlying models under an online learning paradigm. We conducted a user study on this scenario, for a neural machine translation system. The experimentation was carried out by professional translators, with a vast experience in machine translation post-editing. The results showed a reduction in the required amount of human effort needed when post-editing the outputs of the system, improvements in the translation quality and a positive perception of the adaptive system by the users. |
| Tasks | Machine Translation |
| Published | 2019-06-21 |
| URL | https://arxiv.org/abs/1906.08996v1 |
| https://arxiv.org/pdf/1906.08996v1.pdf | |
| PWC | https://paperswithcode.com/paper/incremental-adaptation-of-nmt-for |
| Repo | |
| Framework | |
Cross Domain Imitation Learning
| Title | Cross Domain Imitation Learning |
| Authors | Kun Ho Kim, Yihong Gu, Jiaming Song, Shengjia Zhao, Stefano Ermon |
| Abstract | We study the question of how to imitate tasks across domains with discrepancies such as embodiment and viewpoint mismatch. Many prior works require paired, aligned demonstrations and an additional RL procedure for the task. However, paired, aligned demonstrations are seldom obtainable and RL procedures are expensive. In this work, we formalize the Cross Domain Imitation Learning (CDIL) problem, which encompasses imitation learning in the presence of viewpoint and embodiment mismatch. Informally, CDIL is the process of learning how to perform a task optimally, given demonstrations of the task in a distinct domain. We propose a two step approach to CDIL: alignment followed by adaptation. In the alignment step we execute a novel unsupervised MDP alignment algorithm, Generative Adversarial MDP Alignment (GAMA), to learn state and action correspondences from unpaired, unaligned demonstrations. In the adaptation step we leverage the correspondences to zero-shot imitate tasks across domains. To describe when CDIL is feasible via alignment and adaptation, we introduce a theory of MDP alignability. We experimentally evaluate GAMA against baselines in both embodiment and viewpoint mismatch scenarios where aligned demonstrations don’t exist and show the effectiveness of our approach. |
| Tasks | Imitation Learning |
| Published | 2019-09-30 |
| URL | https://arxiv.org/abs/1910.00105v1 |
| https://arxiv.org/pdf/1910.00105v1.pdf | |
| PWC | https://paperswithcode.com/paper/cross-domain-imitation-learning |
| Repo | |
| Framework | |
