Paper Group ANR 709
Quantum Privacy-Preserving Perceptron. Newton-type Methods for Inference in Higher-Order Markov Random Fields. Multi-Scale Continuous CRFs as Sequential Deep Networks for Monocular Depth Estimation. Sound Event Detection in Synthetic Audio: Analysis of the DCASE 2016 Task Results. Recognizing Textures with Mobile Cameras for Pedestrian Safety Appli …
Quantum Privacy-Preserving Perceptron
| Title | Quantum Privacy-Preserving Perceptron |
| Authors | Shenggang Ying, Mingsheng Ying, Yuan Feng |
| Abstract | With the extensive applications of machine learning, the issue of private or sensitive data in the training examples becomes more and more serious: during the training process, personal information or habits may be disclosed to unexpected persons or organisations, which can cause serious privacy problems or even financial loss. In this paper, we present a quantum privacy-preserving algorithm for machine learning with perceptron. There are mainly two steps to protect original training examples. Firstly when checking the current classifier, quantum tests are employed to detect data user’s possible dishonesty. Secondly when updating the current classifier, private random noise is used to protect the original data. The advantages of our algorithm are: (1) it protects training examples better than the known classical methods; (2) it requires no quantum database and thus is easy to implement. |
| Tasks | |
| Published | 2017-07-31 |
| URL | http://arxiv.org/abs/1707.09893v1 |
| http://arxiv.org/pdf/1707.09893v1.pdf | |
| PWC | https://paperswithcode.com/paper/quantum-privacy-preserving-perceptron |
| Repo | |
| Framework | |
Newton-type Methods for Inference in Higher-Order Markov Random Fields
| Title | Newton-type Methods for Inference in Higher-Order Markov Random Fields |
| Authors | Hariprasad Kannan, Nikos Komodakis, Nikos Paragios |
| Abstract | Linear programming relaxations are central to {\sc map} inference in discrete Markov Random Fields. The ability to properly solve the Lagrangian dual is a critical component of such methods. In this paper, we study the benefit of using Newton-type methods to solve the Lagrangian dual of a smooth version of the problem. We investigate their ability to achieve superior convergence behavior and to better handle the ill-conditioned nature of the formulation, as compared to first order methods. We show that it is indeed possible to efficiently apply a trust region Newton method for a broad range of {\sc map} inference problems. In this paper we propose a provably convergent and efficient framework that includes (i) excellent compromise between computational complexity and precision concerning the Hessian matrix construction, (ii) a damping strategy that aids efficient optimization, (iii) a truncation strategy coupled with a generic pre-conditioner for Conjugate Gradients, (iv) efficient sum-product computation for sparse clique potentials. Results for higher-order Markov Random Fields demonstrate the potential of this approach. |
| Tasks | |
| Published | 2017-09-05 |
| URL | http://arxiv.org/abs/1709.01237v1 |
| http://arxiv.org/pdf/1709.01237v1.pdf | |
| PWC | https://paperswithcode.com/paper/newton-type-methods-for-inference-in-higher |
| Repo | |
| Framework | |
Multi-Scale Continuous CRFs as Sequential Deep Networks for Monocular Depth Estimation
| Title | Multi-Scale Continuous CRFs as Sequential Deep Networks for Monocular Depth Estimation |
| Authors | Dan Xu, Elisa Ricci, Wanli Ouyang, Xiaogang Wang, Nicu Sebe |
| Abstract | This paper addresses the problem of depth estimation from a single still image. Inspired by recent works on multi- scale convolutional neural networks (CNN), we propose a deep model which fuses complementary information derived from multiple CNN side outputs. Different from previous methods, the integration is obtained by means of continuous Conditional Random Fields (CRFs). In particular, we propose two different variations, one based on a cascade of multiple CRFs, the other on a unified graphical model. By designing a novel CNN implementation of mean-field updates for continuous CRFs, we show that both proposed models can be regarded as sequential deep networks and that training can be performed end-to-end. Through extensive experimental evaluation we demonstrate the effective- ness of the proposed approach and establish new state of the art results on publicly available datasets. |
| Tasks | Depth Estimation, Monocular Depth Estimation |
| Published | 2017-04-07 |
| URL | http://arxiv.org/abs/1704.02157v1 |
| http://arxiv.org/pdf/1704.02157v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-scale-continuous-crfs-as-sequential |
| Repo | |
| Framework | |
Sound Event Detection in Synthetic Audio: Analysis of the DCASE 2016 Task Results
| Title | Sound Event Detection in Synthetic Audio: Analysis of the DCASE 2016 Task Results |
| Authors | Grégoire Lafay, Emmanouil Benetos, Mathieu Lagrange |
| Abstract | As part of the 2016 public evaluation challenge on Detection and Classification of Acoustic Scenes and Events (DCASE 2016), the second task focused on evaluating sound event detection systems using synthetic mixtures of office sounds. This task, which follows the `Event Detection - Office Synthetic’ task of DCASE 2013, studies the behaviour of tested algorithms when facing controlled levels of audio complexity with respect to background noise and polyphony/density, with the added benefit of a very accurate ground truth. This paper presents the task formulation, evaluation metrics, submitted systems, and provides a statistical analysis of the results achieved, with respect to various aspects of the evaluation dataset. | |
| Tasks | Sound Event Detection |
| Published | 2017-11-15 |
| URL | http://arxiv.org/abs/1711.05551v1 |
| http://arxiv.org/pdf/1711.05551v1.pdf | |
| PWC | https://paperswithcode.com/paper/sound-event-detection-in-synthetic-audio |
| Repo | |
| Framework | |
Recognizing Textures with Mobile Cameras for Pedestrian Safety Applications
| Title | Recognizing Textures with Mobile Cameras for Pedestrian Safety Applications |
| Authors | Shubham Jain, Marco Gruteser |
| Abstract | As smartphone rooted distractions become commonplace, the lack of compelling safety measures has led to a rise in the number of injuries to distracted walkers. Various solutions address this problem by sensing a pedestrian’s walking environment. Existing camera-based approaches have been largely limited to obstacle detection and other forms of object detection. Instead, we present TerraFirma, an approach that performs material recognition on the pedestrian’s walking surface. We explore, first, how well commercial off-the-shelf smartphone cameras can learn texture to distinguish among paving materials in uncontrolled outdoor urban settings. Second, we aim at identifying when a distracted user is about to enter the street, which can be used to support safety functions such as warning the user to be cautious. To this end, we gather a unique dataset of street/sidewalk imagery from a pedestrian’s perspective, that spans major cities like New York, Paris, and London. We demonstrate that modern phone cameras can be enabled to distinguish materials of walking surfaces in urban areas with more than 90% accuracy, and accurately identify when pedestrians transition from sidewalk to street. |
| Tasks | Material Recognition, Object Detection |
| Published | 2017-11-01 |
| URL | http://arxiv.org/abs/1711.00558v1 |
| http://arxiv.org/pdf/1711.00558v1.pdf | |
| PWC | https://paperswithcode.com/paper/recognizing-textures-with-mobile-cameras-for |
| Repo | |
| Framework | |
Learning Social Image Embedding with Deep Multimodal Attention Networks
| Title | Learning Social Image Embedding with Deep Multimodal Attention Networks |
| Authors | Feiran Huang, Xiaoming Zhang, Zhoujun Li, Tao Mei, Yueying He, Zhonghua Zhao |
| Abstract | Learning social media data embedding by deep models has attracted extensive research interest as well as boomed a lot of applications, such as link prediction, classification, and cross-modal search. However, for social images which contain both link information and multimodal contents (e.g., text description, and visual content), simply employing the embedding learnt from network structure or data content results in sub-optimal social image representation. In this paper, we propose a novel social image embedding approach called Deep Multimodal Attention Networks (DMAN), which employs a deep model to jointly embed multimodal contents and link information. Specifically, to effectively capture the correlations between multimodal contents, we propose a multimodal attention network to encode the fine-granularity relation between image regions and textual words. To leverage the network structure for embedding learning, a novel Siamese-Triplet neural network is proposed to model the links among images. With the joint deep model, the learnt embedding can capture both the multimodal contents and the nonlinear network information. Extensive experiments are conducted to investigate the effectiveness of our approach in the applications of multi-label classification and cross-modal search. Compared to state-of-the-art image embeddings, our proposed DMAN achieves significant improvement in the tasks of multi-label classification and cross-modal search. |
| Tasks | Link Prediction, Multi-Label Classification |
| Published | 2017-10-18 |
| URL | http://arxiv.org/abs/1710.06582v1 |
| http://arxiv.org/pdf/1710.06582v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-social-image-embedding-with-deep |
| Repo | |
| Framework | |
Data-driven Feature Sampling for Deep Hyperspectral Classification and Segmentation
| Title | Data-driven Feature Sampling for Deep Hyperspectral Classification and Segmentation |
| Authors | William M. Severa, Jerilyn A. Timlin, Suraj Kholwadwala, Conrad D. James, James B. Aimone |
| Abstract | The high dimensionality of hyperspectral imaging forces unique challenges in scope, size and processing requirements. Motivated by the potential for an in-the-field cell sorting detector, we examine a $\textit{Synechocystis sp.}$ PCC 6803 dataset wherein cells are grown alternatively in nitrogen rich or deplete cultures. We use deep learning techniques to both successfully classify cells and generate a mask segmenting the cells/condition from the background. Further, we use the classification accuracy to guide a data-driven, iterative feature selection method, allowing the design neural networks requiring 90% fewer input features with little accuracy degradation. |
| Tasks | Feature Selection |
| Published | 2017-10-26 |
| URL | http://arxiv.org/abs/1710.09934v1 |
| http://arxiv.org/pdf/1710.09934v1.pdf | |
| PWC | https://paperswithcode.com/paper/data-driven-feature-sampling-for-deep |
| Repo | |
| Framework | |
Stable Recovery Of Sparse Vectors From Random Sinusoidal Feature Maps
| Title | Stable Recovery Of Sparse Vectors From Random Sinusoidal Feature Maps |
| Authors | Mohammadreza Soltani, Chinmay Hegde |
| Abstract | Random sinusoidal features are a popular approach for speeding up kernel-based inference in large datasets. Prior to the inference stage, the approach suggests performing dimensionality reduction by first multiplying each data vector by a random Gaussian matrix, and then computing an element-wise sinusoid. Theoretical analysis shows that collecting a sufficient number of such features can be reliably used for subsequent inference in kernel classification and regression. In this work, we demonstrate that with a mild increase in the dimension of the embedding, it is also possible to reconstruct the data vector from such random sinusoidal features, provided that the underlying data is sparse enough. In particular, we propose a numerically stable algorithm for reconstructing the data vector given the nonlinear features, and analyze its sample complexity. Our algorithm can be extended to other types of structured inverse problems, such as demixing a pair of sparse (but incoherent) vectors. We support the efficacy of our approach via numerical experiments. |
| Tasks | Dimensionality Reduction |
| Published | 2017-01-23 |
| URL | http://arxiv.org/abs/1701.06607v2 |
| http://arxiv.org/pdf/1701.06607v2.pdf | |
| PWC | https://paperswithcode.com/paper/stable-recovery-of-sparse-vectors-from-random |
| Repo | |
| Framework | |
Material Recognition CNNs and Hierarchical Planning for Biped Robot Locomotion on Slippery Terrain
| Title | Material Recognition CNNs and Hierarchical Planning for Biped Robot Locomotion on Slippery Terrain |
| Authors | Martim Brandao, Yukitoshi Minami Shiguematsu, Kenji Hashimoto, Atsuo Takanishi |
| Abstract | In this paper we tackle the problem of visually predicting surface friction for environments with diverse surfaces, and integrating this knowledge into biped robot locomotion planning. The problem is essential for autonomous robot locomotion since diverse surfaces with varying friction abound in the real world, from wood to ceramic tiles, grass or ice, which may cause difficulties or huge energy costs for robot locomotion if not considered. We propose to estimate friction and its uncertainty from visual estimation of material classes using convolutional neural networks, together with probability distribution functions of friction associated with each material. We then robustly integrate the friction predictions into a hierarchical (footstep and full-body) planning method using chance constraints, and optimize the same trajectory costs at both levels of the planning method for consistency. Our solution achieves fully autonomous perception and locomotion on slippery terrain, which considers not only friction and its uncertainty, but also collision, stability and trajectory cost. We show promising friction prediction results in real pictures of outdoor scenarios, and planning experiments on a real robot facing surfaces with different friction. |
| Tasks | Material Recognition |
| Published | 2017-06-27 |
| URL | http://arxiv.org/abs/1706.08685v1 |
| http://arxiv.org/pdf/1706.08685v1.pdf | |
| PWC | https://paperswithcode.com/paper/material-recognition-cnns-and-hierarchical |
| Repo | |
| Framework | |
A Challenge Set Approach to Evaluating Machine Translation
| Title | A Challenge Set Approach to Evaluating Machine Translation |
| Authors | Pierre Isabelle, Colin Cherry, George Foster |
| Abstract | Neural machine translation represents an exciting leap forward in translation quality. But what longstanding weaknesses does it resolve, and which remain? We address these questions with a challenge set approach to translation evaluation and error analysis. A challenge set consists of a small set of sentences, each hand-designed to probe a system’s capacity to bridge a particular structural divergence between languages. To exemplify this approach, we present an English-French challenge set, and use it to analyze phrase-based and neural systems. The resulting analysis provides not only a more fine-grained picture of the strengths of neural systems, but also insight into which linguistic phenomena remain out of reach. |
| Tasks | Machine Translation |
| Published | 2017-04-24 |
| URL | http://arxiv.org/abs/1704.07431v5 |
| http://arxiv.org/pdf/1704.07431v5.pdf | |
| PWC | https://paperswithcode.com/paper/a-challenge-set-approach-to-evaluating |
| Repo | |
| Framework | |
Lat-Net: Compressing Lattice Boltzmann Flow Simulations using Deep Neural Networks
| Title | Lat-Net: Compressing Lattice Boltzmann Flow Simulations using Deep Neural Networks |
| Authors | Oliver Hennigh |
| Abstract | Computational Fluid Dynamics (CFD) is a hugely important subject with applications in almost every engineering field, however, fluid simulations are extremely computationally and memory demanding. Towards this end, we present Lat-Net, a method for compressing both the computation time and memory usage of Lattice Boltzmann flow simulations using deep neural networks. Lat-Net employs convolutional autoencoders and residual connections in a fully differentiable scheme to compress the state size of a simulation and learn the dynamics on this compressed form. The result is a computationally and memory efficient neural network that can be iterated and queried to reproduce a fluid simulation. We show that once Lat-Net is trained, it can generalize to large grid sizes and complex geometries while maintaining accuracy. We also show that Lat-Net is a general method for compressing other Lattice Boltzmann based simulations such as Electromagnetism. |
| Tasks | |
| Published | 2017-05-25 |
| URL | http://arxiv.org/abs/1705.09036v1 |
| http://arxiv.org/pdf/1705.09036v1.pdf | |
| PWC | https://paperswithcode.com/paper/lat-net-compressing-lattice-boltzmann-flow |
| Repo | |
| Framework | |
The Active Atlas: Combining 3D Anatomical Models with Texture Detectors
| Title | The Active Atlas: Combining 3D Anatomical Models with Texture Detectors |
| Authors | Yuncong Chen, Lauren McElvain, Alex Tolpygo, Daniel Ferrante, Harvey Karten, Partha Mitra, David Kleinfeld, Yoav Freund |
| Abstract | While modern imaging technologies such as fMRI have opened exciting new possibilities for studying the brain in vivo, histological sections remain the best way to study the anatomy of the brain at the level of single neurons. The histological atlas changed little since 1909 and localizing brain regions is a still a labor intensive process performed only by experienced neuro-anatomists. Existing digital atlases such as the Allen Brain atlas are limited to low resolution images which cannot identify the detailed structure of the neurons. We have developed a digital atlas methodology that combines information about the 3D organization of the brain and the detailed texture of neurons in different structures. Using the methodology we developed an atlas for the mouse brainstem and mid-brain, two regions for which there are currently no good atlases. Our atlas is “active” in that it can be used to automatically align a histological stack to the atlas, thus reducing the work of the neuroanatomist. |
| Tasks | |
| Published | 2017-02-28 |
| URL | http://arxiv.org/abs/1702.08606v3 |
| http://arxiv.org/pdf/1702.08606v3.pdf | |
| PWC | https://paperswithcode.com/paper/the-active-atlas-combining-3d-anatomical |
| Repo | |
| Framework | |
Show, Attend and Interact: Perceivable Human-Robot Social Interaction through Neural Attention Q-Network
| Title | Show, Attend and Interact: Perceivable Human-Robot Social Interaction through Neural Attention Q-Network |
| Authors | Ahmed Hussain Qureshi, Yutaka Nakamura, Yuichiro Yoshikawa, Hiroshi Ishiguro |
| Abstract | For a safe, natural and effective human-robot social interaction, it is essential to develop a system that allows a robot to demonstrate the perceivable responsive behaviors to complex human behaviors. We introduce the Multimodal Deep Attention Recurrent Q-Network using which the robot exhibits human-like social interaction skills after 14 days of interacting with people in an uncontrolled real world. Each and every day during the 14 days, the system gathered robot interaction experiences with people through a hit-and-trial method and then trained the MDARQN on these experiences using end-to-end reinforcement learning approach. The results of interaction based learning indicate that the robot has learned to respond to complex human behaviors in a perceivable and socially acceptable manner. |
| Tasks | Deep Attention |
| Published | 2017-02-28 |
| URL | http://arxiv.org/abs/1702.08626v1 |
| http://arxiv.org/pdf/1702.08626v1.pdf | |
| PWC | https://paperswithcode.com/paper/show-attend-and-interact-perceivable-human |
| Repo | |
| Framework | |
Geometry Guided Adversarial Facial Expression Synthesis
| Title | Geometry Guided Adversarial Facial Expression Synthesis |
| Authors | Lingxiao Song, Zhihe Lu, Ran He, Zhenan Sun, Tieniu Tan |
| Abstract | Facial expression synthesis has drawn much attention in the field of computer graphics and pattern recognition. It has been widely used in face animation and recognition. However, it is still challenging due to the high-level semantic presence of large and non-linear face geometry variations. This paper proposes a Geometry-Guided Generative Adversarial Network (G2-GAN) for photo-realistic and identity-preserving facial expression synthesis. We employ facial geometry (fiducial points) as a controllable condition to guide facial texture synthesis with specific expression. A pair of generative adversarial subnetworks are jointly trained towards opposite tasks: expression removal and expression synthesis. The paired networks form a mapping cycle between neutral expression and arbitrary expressions, which also facilitate other applications such as face transfer and expression invariant face recognition. Experimental results show that our method can generate compelling perceptual results on various facial expression synthesis databases. An expression invariant face recognition experiment is also performed to further show the advantages of our proposed method. |
| Tasks | Face Recognition, Face Transfer, Texture Synthesis |
| Published | 2017-12-10 |
| URL | http://arxiv.org/abs/1712.03474v1 |
| http://arxiv.org/pdf/1712.03474v1.pdf | |
| PWC | https://paperswithcode.com/paper/geometry-guided-adversarial-facial-expression |
| Repo | |
| Framework | |
Global Normalization of Convolutional Neural Networks for Joint Entity and Relation Classification
| Title | Global Normalization of Convolutional Neural Networks for Joint Entity and Relation Classification |
| Authors | Heike Adel, Hinrich Schütze |
| Abstract | We introduce globally normalized convolutional neural networks for joint entity classification and relation extraction. In particular, we propose a way to utilize a linear-chain conditional random field output layer for predicting entity types and relations between entities at the same time. Our experiments show that global normalization outperforms a locally normalized softmax layer on a benchmark dataset. |
| Tasks | Relation Classification, Relation Extraction |
| Published | 2017-07-24 |
| URL | http://arxiv.org/abs/1707.07719v3 |
| http://arxiv.org/pdf/1707.07719v3.pdf | |
| PWC | https://paperswithcode.com/paper/global-normalization-of-convolutional-neural |
| Repo | |
| Framework | |
