Paper Group ANR 111
A Machine Learning Framework for Register Placement Optimization in Digital Circuit Design. On balanced clustering with tree-like structures over clusters. Cross-Lingual Approaches to Reference Resolution in Dialogue Systems. Hierarchical Neural Network for Extracting Knowledgeable Snippets and Documents. A Simplified Approach to Deep Learning for …
A Machine Learning Framework for Register Placement Optimization in Digital Circuit Design
| Title | A Machine Learning Framework for Register Placement Optimization in Digital Circuit Design |
| Authors | Karthik Airani, Rohit Guttal |
| Abstract | In modern digital circuit back-end design, designers heavily rely on electronic-design-automoation (EDA) tool to close timing. However, the heuristic algorithms used in the place and route tool usually does not result in optimal solution. Thus, significant design effort is used to tune parameters or provide user constraints or guidelines to improve the tool performance. In this paper, we targeted at those optimization space left behind by the EDA tools and propose a machine learning framework that helps to define what are the guidelines and constraints for registers placement, which can yield better performance and quality for back-end design. In other words, the framework is trying to learn what are the flaws of the existing EDA tools and tries to optimize it by providing additional information. We discuss what is the proper input feature vector to be extracted, and what is metric to be used for reference output. We also develop a scheme to generate perturbed training samples using existing design based on Gaussian randomization. By applying our methodology, we are able to improve the design runtime by up to 36% and timing quality by up to 23%. |
| Tasks | |
| Published | 2018-01-06 |
| URL | http://arxiv.org/abs/1801.02620v1 |
| http://arxiv.org/pdf/1801.02620v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-machine-learning-framework-for-register |
| Repo | |
| Framework | |
On balanced clustering with tree-like structures over clusters
| Title | On balanced clustering with tree-like structures over clusters |
| Authors | Mark Sh. Levin |
| Abstract | The article addresses balanced clustering problems with an additional requirement as a tree-like structure over the obtained balanced clusters. This kind of clustering problems can be useful in some applications (e.g., network design, management and routing). Various types of the initial elements are considered. Four basic greedy-like solving strategies (design framework) are considered: balancing-spanning strategy, spanning-balancing strategy, direct strategy, and design of layered structures with balancing. An extended description of the spanning-balancing strategy is presented including four solving schemes and an illustrative numerical example. |
| Tasks | |
| Published | 2018-12-09 |
| URL | http://arxiv.org/abs/1812.03535v1 |
| http://arxiv.org/pdf/1812.03535v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-balanced-clustering-with-tree-like |
| Repo | |
| Framework | |
Cross-Lingual Approaches to Reference Resolution in Dialogue Systems
| Title | Cross-Lingual Approaches to Reference Resolution in Dialogue Systems |
| Authors | Amr Sharaf, Arpit Gupta, Hancheng Ge, Chetan Naik, Lambert Mathias |
| Abstract | In the slot-filling paradigm, where a user can refer back to slots in the context during the conversation, the goal of the contextual understanding system is to resolve the referring expressions to the appropriate slots in the context. In this paper, we build on the context carryover system~\citep{Naik2018ContextualSC}, which provides a scalable multi-domain framework for resolving references. However, scaling this approach across languages is not a trivial task, due to the large demand on acquisition of annotated data in the target language. Our main focus is on cross-lingual methods for reference resolution as a way to alleviate the need for annotated data in the target language. In the cross-lingual setup, we assume there is access to annotated resources as well as a well trained model in the source language and little to no annotated data in the target language. In this paper, we explore three different approaches for cross-lingual transfer \textemdash~\ delexicalization as data augmentation, multilingual embeddings and machine translation. We compare these approaches both on a low resource setting as well as a large resource setting. Our experiments show that multilingual embeddings and delexicalization via data augmentation have a significant impact in the low resource setting, but the gains diminish as the amount of available data in the target language increases. Furthermore, when combined with machine translation we can get performance very close to actual live data in the target language, with only 25% of the data projected into the target language. |
| Tasks | Cross-Lingual Transfer, Data Augmentation, Machine Translation, Slot Filling |
| Published | 2018-11-27 |
| URL | http://arxiv.org/abs/1811.11161v1 |
| http://arxiv.org/pdf/1811.11161v1.pdf | |
| PWC | https://paperswithcode.com/paper/cross-lingual-approaches-to-reference |
| Repo | |
| Framework | |
Hierarchical Neural Network for Extracting Knowledgeable Snippets and Documents
| Title | Hierarchical Neural Network for Extracting Knowledgeable Snippets and Documents |
| Authors | Ganbin Zhou, Rongyu Cao, Xiang Ao, Ping Luo, Fen Lin, Leyu Lin, Qing He |
| Abstract | In this study, we focus on extracting knowledgeable snippets and annotating knowledgeable documents from Web corpus, consisting of the documents from social media and We-media. Informally, knowledgeable snippets refer to the text describing concepts, properties of entities, or relations among entities, while knowledgeable documents are the ones with enough knowledgeable snippets. These knowledgeable snippets and documents could be helpful in multiple applications, such as knowledge base construction and knowledge-oriented service. Previous studies extracted the knowledgeable snippets using the pattern-based method. Here, we propose the semantic-based method for this task. Specifically, a CNN based model is developed to extract knowledgeable snippets and annotate knowledgeable documents simultaneously. Additionally, a “low-level sharing, high-level splitting” structure of CNN is designed to handle the documents from different content domains. Compared with building multiple domain-specific CNNs, this joint model not only critically saves the training time, but also improves the prediction accuracy visibly. The superiority of the proposed method is demonstrated in a real dataset from Wechat public platform. |
| Tasks | |
| Published | 2018-08-22 |
| URL | http://arxiv.org/abs/1808.07228v1 |
| http://arxiv.org/pdf/1808.07228v1.pdf | |
| PWC | https://paperswithcode.com/paper/hierarchical-neural-network-for-extracting |
| Repo | |
| Framework | |
A Simplified Approach to Deep Learning for Image Segmentation
| Title | A Simplified Approach to Deep Learning for Image Segmentation |
| Authors | Ishtar Nyawira, Kristi Bushman |
| Abstract | Leaping into the rapidly developing world of deep learning is an exciting and sometimes confusing adventure. All of the advice and tutorials available can be hard to organize and work through, especially when training specific models on specific datasets, different from those originally used to train the network. In this short guide, we aim to walk the reader through the techniques that we have used to successfully train two deep neural networks for pixel-wise classification, including some data management and augmentation approaches for working with image data that may be insufficiently annotated or relatively homogenous. |
| Tasks | Semantic Segmentation |
| Published | 2018-08-31 |
| URL | http://arxiv.org/abs/1809.00085v1 |
| http://arxiv.org/pdf/1809.00085v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-simplified-approach-to-deep-learning-for |
| Repo | |
| Framework | |
Neural Task Representations as Weak Supervision for Model Agnostic Cross-Lingual Transfer
| Title | Neural Task Representations as Weak Supervision for Model Agnostic Cross-Lingual Transfer |
| Authors | Sujay Kumar Jauhar, Michael Gamon, Patrick Pantel |
| Abstract | Natural language processing is heavily Anglo-centric, while the demand for models that work in languages other than English is greater than ever. Yet, the task of transferring a model from one language to another can be expensive in terms of annotation costs, engineering time and effort. In this paper, we present a general framework for easily and effectively transferring neural models from English to other languages. The framework, which relies on task representations as a form of weak supervision, is model and task agnostic, meaning that many existing neural architectures can be ported to other languages with minimal effort. The only requirement is unlabeled parallel data, and a loss defined over task representations. We evaluate our framework by transferring an English sentiment classifier to three different languages. On a battery of tests, we show that our models outperform a number of strong baselines and rival state-of-the-art results, which rely on more complex approaches and significantly more resources and data. Additionally, we find that the framework proposed in this paper is able to capture semantically rich and meaningful representations across languages, despite the lack of direct supervision. |
| Tasks | Cross-Lingual Transfer |
| Published | 2018-11-02 |
| URL | http://arxiv.org/abs/1811.01115v1 |
| http://arxiv.org/pdf/1811.01115v1.pdf | |
| PWC | https://paperswithcode.com/paper/neural-task-representations-as-weak |
| Repo | |
| Framework | |
EDF: Ensemble, Distill, and Fuse for Easy Video Labeling
| Title | EDF: Ensemble, Distill, and Fuse for Easy Video Labeling |
| Authors | Giulio Zhou, Subramanya Dulloor, David G. Andersen, Michael Kaminsky |
| Abstract | We present a way to rapidly bootstrap object detection on unseen videos using minimal human annotations. We accomplish this by combining two complementary sources of knowledge (one generic and the other specific) using bounding box merging and model distillation. The first (generic) knowledge source is obtained from ensembling pre-trained object detectors using a novel bounding box merging and confidence reweighting scheme. We make the observation that model distillation with data augmentation can train a specialized detector that outperforms the noisy labels it was trained on, and train a Student Network on the ensemble detections that obtains higher mAP than the ensemble itself. The second (specialized) knowledge source comes from training a detector (which we call the Supervised Labeler) on a labeled subset of the video to generate detections on the unlabeled portion. We demonstrate on two popular vehicular datasets that these techniques work to emit bounding boxes for all vehicles in the frame with higher mean average precision (mAP) than any of the reference networks used, and that the combination of ensembled and human-labeled data produces object detections that outperform either alone. |
| Tasks | Data Augmentation, Object Detection |
| Published | 2018-12-10 |
| URL | http://arxiv.org/abs/1812.03626v1 |
| http://arxiv.org/pdf/1812.03626v1.pdf | |
| PWC | https://paperswithcode.com/paper/edf-ensemble-distill-and-fuse-for-easy-video |
| Repo | |
| Framework | |
Unsupervised Image Super-Resolution using Cycle-in-Cycle Generative Adversarial Networks
| Title | Unsupervised Image Super-Resolution using Cycle-in-Cycle Generative Adversarial Networks |
| Authors | Yuan Yuan, Siyuan Liu, Jiawei Zhang, Yongbing Zhang, Chao Dong, Liang Lin |
| Abstract | We consider the single image super-resolution problem in a more general case that the low-/high-resolution pairs and the down-sampling process are unavailable. Different from traditional super-resolution formulation, the low-resolution input is further degraded by noises and blurring. This complicated setting makes supervised learning and accurate kernel estimation impossible. To solve this problem, we resort to unsupervised learning without paired data, inspired by the recent successful image-to-image translation applications. With generative adversarial networks (GAN) as the basic component, we propose a Cycle-in-Cycle network structure to tackle the problem within three steps. First, the noisy and blurry input is mapped to a noise-free low-resolution space. Then the intermediate image is up-sampled with a pre-trained deep model. Finally, we fine-tune the two modules in an end-to-end manner to get the high-resolution output. Experiments on NTIRE2018 datasets demonstrate that the proposed unsupervised method achieves comparable results as the state-of-the-art supervised models. |
| Tasks | Image Super-Resolution, Image-to-Image Translation, Super-Resolution |
| Published | 2018-09-03 |
| URL | http://arxiv.org/abs/1809.00437v1 |
| http://arxiv.org/pdf/1809.00437v1.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-image-super-resolution-using |
| Repo | |
| Framework | |
Learning Spatial Common Sense with Geometry-Aware Recurrent Networks
| Title | Learning Spatial Common Sense with Geometry-Aware Recurrent Networks |
| Authors | Hsiao-Yu Fish Tung, Ricson Cheng, Katerina Fragkiadaki |
| Abstract | We integrate two powerful ideas, geometry and deep visual representation learning, into recurrent network architectures for mobile visual scene understanding. The proposed networks learn to “lift” and integrate 2D visual features over time into latent 3D feature maps of the scene. They are equipped with differentiable geometric operations, such as projection, unprojection, egomotion estimation and stabilization, in order to compute a geometrically-consistent mapping between the world scene and their 3D latent feature state. We train the proposed architectures to predict novel camera views given short frame sequences as input. Their predictions strongly generalize to scenes with a novel number of objects, appearances and configurations; they greatly outperform previous works that do not consider egomotion stabilization or a space-aware latent feature state. We train the proposed architectures to detect and segment objects in 3D using the latent 3D feature map as input–as opposed to per frame features. The resulting object detections persist over time: they continue to exist even when an object gets occluded or leaves the field of view. Our experiments suggest the proposed space-aware latent feature memory and egomotion-stabilized convolutions are essential architectural choices for spatial common sense to emerge in artificial embodied visual agents. |
| Tasks | Common Sense Reasoning, Representation Learning, Scene Understanding |
| Published | 2018-12-31 |
| URL | http://arxiv.org/abs/1901.00003v3 |
| http://arxiv.org/pdf/1901.00003v3.pdf | |
| PWC | https://paperswithcode.com/paper/learning-spatial-common-sense-with-geometry |
| Repo | |
| Framework | |
Learning Direct Optimization for Scene Understanding
| Title | Learning Direct Optimization for Scene Understanding |
| Authors | Lukasz Romaszko, Christopher K. I. Williams, John Winn |
| Abstract | We introduce a Learning Direct Optimization method for the refinement of a latent variable model that describes input image x. Our goal is to explain a single image x with a 3D computer graphics model having scene graph latent variables z (such as object appearance, camera position). Given a current estimate of z we can render a prediction of the image g(z), which can be compared to the image x. The standard way to proceed is then to measure the error E(x, g(z)) between the two, and use an optimizer to minimize the error. Our novel Learning Direct Optimization (LiDO) approach trains a Prediction Network to predict an update directly to correct z, rather than minimizing the error with respect to z. Experiments show that our LiDO method converges rapidly as it does not need to perform a search on the error landscape, produces better solutions, and is able to handle the mismatch between the data and the fitted scene model. We apply the LiDO to a realistic synthetic dataset, and show that the method transfers to work well with real images. |
| Tasks | Scene Understanding |
| Published | 2018-12-18 |
| URL | http://arxiv.org/abs/1812.07524v1 |
| http://arxiv.org/pdf/1812.07524v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-direct-optimization-for-scene |
| Repo | |
| Framework | |
GoSGD: Distributed Optimization for Deep Learning with Gossip Exchange
| Title | GoSGD: Distributed Optimization for Deep Learning with Gossip Exchange |
| Authors | Michael Blot, David Picard, Matthieu Cord |
| Abstract | We address the issue of speeding up the training of convolutional neural networks by studying a distributed method adapted to stochastic gradient descent. Our parallel optimization setup uses several threads, each applying individual gradient descents on a local variable. We propose a new way of sharing information between different threads based on gossip algorithms that show good consensus convergence properties. Our method called GoSGD has the advantage to be fully asynchronous and decentralized. |
| Tasks | Distributed Optimization |
| Published | 2018-04-04 |
| URL | http://arxiv.org/abs/1804.01852v2 |
| http://arxiv.org/pdf/1804.01852v2.pdf | |
| PWC | https://paperswithcode.com/paper/gosgd-distributed-optimization-for-deep |
| Repo | |
| Framework | |
Node Centralities and Classification Performance for Characterizing Node Embedding Algorithms
| Title | Node Centralities and Classification Performance for Characterizing Node Embedding Algorithms |
| Authors | Kento Nozawa, Masanari Kimura, Atsunori Kanemura |
| Abstract | Embedding graph nodes into a vector space can allow the use of machine learning to e.g. predict node classes, but the study of node embedding algorithms is immature compared to the natural language processing field because of a diverse nature of graphs. We examine the performance of node embedding algorithms with respect to graph centrality measures that characterize diverse graphs, through systematic experiments with four node embedding algorithms, four or five graph centralities, and six datasets. Experimental results give insights into the properties of node embedding algorithms, which can be a basis for further research on this topic. |
| Tasks | |
| Published | 2018-02-18 |
| URL | http://arxiv.org/abs/1802.06368v1 |
| http://arxiv.org/pdf/1802.06368v1.pdf | |
| PWC | https://paperswithcode.com/paper/node-centralities-and-classification |
| Repo | |
| Framework | |
Variational Bayesian dropout: pitfalls and fixes
| Title | Variational Bayesian dropout: pitfalls and fixes |
| Authors | Jiri Hron, Alexander G. de G. Matthews, Zoubin Ghahramani |
| Abstract | Dropout, a stochastic regularisation technique for training of neural networks, has recently been reinterpreted as a specific type of approximate inference algorithm for Bayesian neural networks. The main contribution of the reinterpretation is in providing a theoretical framework useful for analysing and extending the algorithm. We show that the proposed framework suffers from several issues; from undefined or pathological behaviour of the true posterior related to use of improper priors, to an ill-defined variational objective due to singularity of the approximating distribution relative to the true posterior. Our analysis of the improper log uniform prior used in variational Gaussian dropout suggests the pathologies are generally irredeemable, and that the algorithm still works only because the variational formulation annuls some of the pathologies. To address the singularity issue, we proffer Quasi-KL (QKL) divergence, a new approximate inference objective for approximation of high-dimensional distributions. We show that motivations for variational Bernoulli dropout based on discretisation and noise have QKL as a limit. Properties of QKL are studied both theoretically and on a simple practical example which shows that the QKL-optimal approximation of a full rank Gaussian with a degenerate one naturally leads to the Principal Component Analysis solution. |
| Tasks | |
| Published | 2018-07-05 |
| URL | http://arxiv.org/abs/1807.01969v1 |
| http://arxiv.org/pdf/1807.01969v1.pdf | |
| PWC | https://paperswithcode.com/paper/variational-bayesian-dropout-pitfalls-and |
| Repo | |
| Framework | |
Random Spiking and Systematic Evaluation of Defenses Against Adversarial Examples
| Title | Random Spiking and Systematic Evaluation of Defenses Against Adversarial Examples |
| Authors | Huangyi Ge, Sze Yiu Chau, Bruno Ribeiro, Ninghui Li |
| Abstract | Image classifiers often suffer from adversarial examples, which are generated by strategically adding a small amount of noise to input images to trick classifiers into misclassification. Over the years, many defense mechanisms have been proposed, and different researchers have made seemingly contradictory claims on their effectiveness. We present an analysis of possible adversarial models, and propose an evaluation framework for comparing different defense mechanisms. As part of the framework, we introduce a more powerful and realistic adversary strategy. Furthermore, we propose a new defense mechanism called Random Spiking (RS), which generalizes dropout and introduces random noises in the training process in a controlled manner. Evaluations under our proposed framework suggest RS delivers better protection against adversarial examples than many existing schemes. |
| Tasks | |
| Published | 2018-12-05 |
| URL | https://arxiv.org/abs/1812.01804v4 |
| https://arxiv.org/pdf/1812.01804v4.pdf | |
| PWC | https://paperswithcode.com/paper/random-spiking-and-systematic-evaluation-of |
| Repo | |
| Framework | |
Noise-tolerant Audio-visual Online Person Verification using an Attention-based Neural Network Fusion
| Title | Noise-tolerant Audio-visual Online Person Verification using an Attention-based Neural Network Fusion |
| Authors | Suwon Shon, Tae-Hyun Oh, James Glass |
| Abstract | In this paper, we present a multi-modal online person verification system using both speech and visual signals. Inspired by neuroscientific findings on the association of voice and face, we propose an attention-based end-to-end neural network that learns multi-sensory associations for the task of person verification. The attention mechanism in our proposed network learns to conditionally select a salient modality between speech and facial representations that provides a balance between complementary inputs. By virtue of this capability, the network is robust to missing or corrupted data from either modality. In the VoxCeleb2 dataset, we show that our method performs favorably against competing multi-modal methods. Even for extreme cases of large corruption or an entirely missing modality, our method demonstrates robustness over other unimodal methods. |
| Tasks | |
| Published | 2018-11-27 |
| URL | http://arxiv.org/abs/1811.10813v1 |
| http://arxiv.org/pdf/1811.10813v1.pdf | |
| PWC | https://paperswithcode.com/paper/noise-tolerant-audio-visual-online-person |
| Repo | |
| Framework | |
