Paper Group ANR 601
An Anchor-Free Region Proposal Network for Faster R-CNN based Text Detection Approaches. Model-based active learning to detect isometric deformable objects in the wild with deep architectures. Reservoir Computing Universality With Stochastic Inputs. Learning Paths from Signature Tensors. Tourist Navigation in Android Smartphone by using Emotion Gen …
An Anchor-Free Region Proposal Network for Faster R-CNN based Text Detection Approaches
| Title | An Anchor-Free Region Proposal Network for Faster R-CNN based Text Detection Approaches |
| Authors | Zhuoyao Zhong, Lei Sun, Qiang Huo |
| Abstract | The anchor mechanism of Faster R-CNN and SSD framework is considered not effective enough to scene text detection, which can be attributed to its IoU based matching criterion between anchors and ground-truth boxes. In order to better enclose scene text instances of various shapes, it requires to design anchors of various scales, aspect ratios and even orientations manually, which makes anchor-based methods sophisticated and inefficient. In this paper, we propose a novel anchor-free region proposal network (AF-RPN) to replace the original anchor-based RPN in the Faster R-CNN framework to address the above problem. Compared with a vanilla RPN and FPN-RPN, AF-RPN can get rid of complicated anchor design and achieve higher recall rate on large-scale COCO-Text dataset. Owing to the high-quality text proposals, our Faster R-CNN based two-stage text detection approach achieves state-of-the-art results on ICDAR-2017 MLT, ICDAR-2015 and ICDAR-2013 text detection benchmarks when using single-scale and single-model (ResNet50) testing only. |
| Tasks | Scene Text Detection |
| Published | 2018-04-24 |
| URL | http://arxiv.org/abs/1804.09003v1 |
| http://arxiv.org/pdf/1804.09003v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-anchor-free-region-proposal-network-for |
| Repo | |
| Framework | |
Model-based active learning to detect isometric deformable objects in the wild with deep architectures
| Title | Model-based active learning to detect isometric deformable objects in the wild with deep architectures |
| Authors | Shrinivasan Sankar, Adrien Bartoli |
| Abstract | In the recent past, algorithms based on Convolutional Neural Networks (CNNs) have achieved significant milestones in object recognition. With large examples of each object class, standard datasets train well for inter-class variability. However, gathering sufficient data to train for a particular instance of an object within a class is impractical. Furthermore, quantitatively assessing the imaging conditions for each image in a given dataset is not feasible. By generating sufficient images with known imaging conditions, we study to what extent CNNs can cope with hard imaging conditions for instance-level recognition in an active learning regime. Leveraging powerful rendering techniques to achieve instance-level detection, we present results of training three state-of-the-art object detection algorithms namely, Fast R-CNN, Faster R-CNN and YOLO9000, for hard imaging conditions imposed into the scene by rendering. Our extensive experiments produce a mean Average Precision score of 0.92 on synthetic images and 0.83 on real images using the best performing Faster R-CNN. We show for the first time how well detection algorithms based on deep architectures fare for each hard imaging condition studied. |
| Tasks | Active Learning, Object Detection, Object Recognition |
| Published | 2018-06-07 |
| URL | http://arxiv.org/abs/1806.02850v1 |
| http://arxiv.org/pdf/1806.02850v1.pdf | |
| PWC | https://paperswithcode.com/paper/model-based-active-learning-to-detect |
| Repo | |
| Framework | |
Reservoir Computing Universality With Stochastic Inputs
| Title | Reservoir Computing Universality With Stochastic Inputs |
| Authors | Lukas Gonon, Juan-Pablo Ortega |
| Abstract | The universal approximation properties with respect to $L ^p $-type criteria of three important families of reservoir computers with stochastic discrete-time semi-infinite inputs is shown. First, it is proved that linear reservoir systems with either polynomial or neural network readout maps are universal. More importantly, it is proved that the same property holds for two families with linear readouts, namely, trigonometric state-affine systems and echo state networks, which are the most widely used reservoir systems in applications. The linearity in the readouts is a key feature in supervised machine learning applications. It guarantees that these systems can be used in high-dimensional situations and in the presence of large datasets. The $L ^p $ criteria used in this paper allow the formulation of universality results that do not necessarily impose almost sure uniform boundedness in the inputs or the fading memory property in the filter that needs to be approximated. |
| Tasks | |
| Published | 2018-07-07 |
| URL | http://arxiv.org/abs/1807.02621v1 |
| http://arxiv.org/pdf/1807.02621v1.pdf | |
| PWC | https://paperswithcode.com/paper/reservoir-computing-universality-with |
| Repo | |
| Framework | |
Learning Paths from Signature Tensors
| Title | Learning Paths from Signature Tensors |
| Authors | Max Pfeffer, Anna Seigal, Bernd Sturmfels |
| Abstract | Matrix congruence extends naturally to the setting of tensors. We apply methods from tensor decomposition, algebraic geometry and numerical optimization to this group action. Given a tensor in the orbit of another tensor, we compute a matrix which transforms one to the other. Our primary application is an inverse problem from stochastic analysis: the recovery of paths from their third order signature tensors. We establish identifiability results, both exact and numerical, for piecewise linear paths, polynomial paths, and generic dictionaries. Numerical optimization is applied for recovery from inexact data. We also compute the shortest path with a given signature tensor. |
| Tasks | |
| Published | 2018-09-05 |
| URL | http://arxiv.org/abs/1809.01588v2 |
| http://arxiv.org/pdf/1809.01588v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-paths-from-signature-tensors |
| Repo | |
| Framework | |
Tourist Navigation in Android Smartphone by using Emotion Generating Calculations and Mental State Transition Networks
| Title | Tourist Navigation in Android Smartphone by using Emotion Generating Calculations and Mental State Transition Networks |
| Authors | Takumi Ichimura, Kosuke Tanabe, Issei Tachibana |
| Abstract | Mental State Transition Network which consists of mental states connected to each other is a basic concept of approximating to human psychological and mental responses. It can represent transition from an emotional state to other one with stimulus by calculating Emotion Generating Calculations method. A computer agent can transit a mental state in MSTN based on analysis of emotion by EGC method. In this paper, the Andorid EGC which the agent works in Android smartphone can evaluate the feelings in the conversation. The tourist navigation system with the proposed technique in this paper will be expected to be an emotional oriented interface in Android smartphone. |
| Tasks | |
| Published | 2018-04-08 |
| URL | http://arxiv.org/abs/1805.00307v1 |
| http://arxiv.org/pdf/1805.00307v1.pdf | |
| PWC | https://paperswithcode.com/paper/tourist-navigation-in-android-smartphone-by |
| Repo | |
| Framework | |
Generative Adversarial Networks for Recovering Missing Spectral Information
| Title | Generative Adversarial Networks for Recovering Missing Spectral Information |
| Authors | Dung N. Tran, Trac D. Tran, Lam Nguyen |
| Abstract | Ultra-wideband (UWB) radar systems nowadays typical operate in the low frequency spectrum to achieve penetration capability. However, this spectrum is also shared by many others communication systems, which causes missing information in the frequency bands. To recover this missing spectral information, we propose a generative adversarial network, called SARGAN, that learns the relationship between original and missing band signals by observing these training pairs in a clever way. Initial results shows that this approach is promising in tackling this challenging missing band problem. |
| Tasks | |
| Published | 2018-12-11 |
| URL | http://arxiv.org/abs/1812.04744v2 |
| http://arxiv.org/pdf/1812.04744v2.pdf | |
| PWC | https://paperswithcode.com/paper/generative-adversarial-networks-for |
| Repo | |
| Framework | |
Goldbach’s Function Approximation Using Deep Learning
| Title | Goldbach’s Function Approximation Using Deep Learning |
| Authors | Avigail Stekel, Merav Chkroun, Amos Azaria |
| Abstract | Goldbach conjecture is one of the most famous open mathematical problems. It states that every even number, bigger than two, can be presented as a sum of 2 prime numbers. % In this work we present a deep learning based model that predicts the number of Goldbach partitions for a given even number. Surprisingly, our model outperforms all state-of-the-art analytically derived estimations for the number of couples, while not requiring prime factorization of the given number. We believe that building a model that can accurately predict the number of couples brings us one step closer to solving one of the world most famous open problems. To the best of our knowledge, this is the first attempt to consider machine learning based data-driven methods to approximate open mathematical problems in the field of number theory, and hope that this work will encourage such attempts. |
| Tasks | |
| Published | 2018-03-25 |
| URL | http://arxiv.org/abs/1803.09237v1 |
| http://arxiv.org/pdf/1803.09237v1.pdf | |
| PWC | https://paperswithcode.com/paper/goldbachs-function-approximation-using-deep |
| Repo | |
| Framework | |
Characterizing Audio Adversarial Examples Using Temporal Dependency
| Title | Characterizing Audio Adversarial Examples Using Temporal Dependency |
| Authors | Zhuolin Yang, Bo Li, Pin-Yu Chen, Dawn Song |
| Abstract | Recent studies have highlighted adversarial examples as a ubiquitous threat to different neural network models and many downstream applications. Nonetheless, as unique data properties have inspired distinct and powerful learning principles, this paper aims to explore their potentials towards mitigating adversarial inputs. In particular, our results reveal the importance of using the temporal dependency in audio data to gain discriminate power against adversarial examples. Tested on the automatic speech recognition (ASR) tasks and three recent audio adversarial attacks, we find that (i) input transformation developed from image adversarial defense provides limited robustness improvement and is subtle to advanced attacks; (ii) temporal dependency can be exploited to gain discriminative power against audio adversarial examples and is resistant to adaptive attacks considered in our experiments. Our results not only show promising means of improving the robustness of ASR systems, but also offer novel insights in exploiting domain-specific data properties to mitigate negative effects of adversarial examples. |
| Tasks | Adversarial Defense, Speech Recognition |
| Published | 2018-09-28 |
| URL | https://arxiv.org/abs/1809.10875v2 |
| https://arxiv.org/pdf/1809.10875v2.pdf | |
| PWC | https://paperswithcode.com/paper/characterizing-audio-adversarial-examples |
| Repo | |
| Framework | |
Adversarial Defense via Data Dependent Activation Function and Total Variation Minimization
| Title | Adversarial Defense via Data Dependent Activation Function and Total Variation Minimization |
| Authors | Bao Wang, Alex T. Lin, Zuoqiang Shi, Wei Zhu, Penghang Yin, Andrea L. Bertozzi, Stanley J. Osher |
| Abstract | We improve the robustness of deep neural nets to adversarial attacks by using an interpolating function as the output activation. This data-dependent activation remarkably improves both generalization and robustness towards adversarial attacks. In the CIFAR10 benchmark, we raise the accuracy of the Projected Gradient Descent adversarial training from $\sim 46%$ to $\sim 69%$ for ResNet20. When we combine this data-dependent activation with total variation minimization on adversarial images and training data augmentation, we achieve an improvement in accuracy by 38.9$%$ for ResNet56 under the strongest attack of the Iterative Fast Gradient Sign Method. We further provide an intuitive explanation of our defense by analyzing the geometry of the feature space. For reproducibility, the code is made available at \url{https://github.com/BaoWangMath/DNN-DataDependentActivation}. |
| Tasks | Adversarial Defense, Data Augmentation |
| Published | 2018-09-23 |
| URL | http://arxiv.org/abs/1809.08516v2 |
| http://arxiv.org/pdf/1809.08516v2.pdf | |
| PWC | https://paperswithcode.com/paper/adversarial-defense-via-data-dependent |
| Repo | |
| Framework | |
Defense Against Adversarial Attacks with Saak Transform
| Title | Defense Against Adversarial Attacks with Saak Transform |
| Authors | Sibo Song, Yueru Chen, Ngai-Man Cheung, C. -C. Jay Kuo |
| Abstract | Deep neural networks (DNNs) are known to be vulnerable to adversarial perturbations, which imposes a serious threat to DNN-based decision systems. In this paper, we propose to apply the lossy Saak transform to adversarially perturbed images as a preprocessing tool to defend against adversarial attacks. Saak transform is a recently-proposed state-of-the-art for computing the spatial-spectral representations of input images. Empirically, we observe that outputs of the Saak transform are very discriminative in differentiating adversarial examples from clean ones. Therefore, we propose a Saak transform based preprocessing method with three steps: 1) transforming an input image to a joint spatial-spectral representation via the forward Saak transform, 2) apply filtering to its high-frequency components, and, 3) reconstructing the image via the inverse Saak transform. The processed image is found to be robust against adversarial perturbations. We conduct extensive experiments to investigate various settings of the Saak transform and filtering functions. Without harming the decision performance on clean images, our method outperforms state-of-the-art adversarial defense methods by a substantial margin on both the CIFAR-10 and ImageNet datasets. Importantly, our results suggest that adversarial perturbations can be effectively and efficiently defended using state-of-the-art frequency analysis. |
| Tasks | Adversarial Defense |
| Published | 2018-08-06 |
| URL | http://arxiv.org/abs/1808.01785v1 |
| http://arxiv.org/pdf/1808.01785v1.pdf | |
| PWC | https://paperswithcode.com/paper/defense-against-adversarial-attacks-with-saak |
| Repo | |
| Framework | |
Off the Beaten Track: Using Deep Learning to Interpolate Between Music Genres
| Title | Off the Beaten Track: Using Deep Learning to Interpolate Between Music Genres |
| Authors | Tijn Borghuis, Alessandro Tibo, Simone Conforti, Luca Canciello, Lorenzo Brusci, Paolo Frasconi |
| Abstract | We describe a system based on deep learning that generates drum patterns in the electronic dance music domain. Experimental results reveal that generated patterns can be employed to produce musically sound and creative transitions between different genres, and that the process of generation is of interest to practitioners in the field. |
| Tasks | |
| Published | 2018-04-25 |
| URL | http://arxiv.org/abs/1804.09808v2 |
| http://arxiv.org/pdf/1804.09808v2.pdf | |
| PWC | https://paperswithcode.com/paper/off-the-beaten-track-using-deep-learning-to |
| Repo | |
| Framework | |
Fast Locality Sensitive Hashing for Beam Search on GPU
| Title | Fast Locality Sensitive Hashing for Beam Search on GPU |
| Authors | Xing Shi, Shizhen Xu, Kevin Knight |
| Abstract | We present a GPU-based Locality Sensitive Hashing (LSH) algorithm to speed up beam search for sequence models. We utilize the winner-take-all (WTA) hash, which is based on relative ranking order of hidden dimensions and thus resilient to perturbations in numerical values. Our algorithm is designed by fully considering the underling architecture of CUDA-enabled GPUs (Algorithm/Architecture Co-design): 1) A parallel Cuckoo hash table is applied for LSH code lookup (guaranteed O(1) lookup time); 2) Candidate lists are shared across beams to maximize the parallelism; 3) Top frequent words are merged into candidate lists to improve performance. Experiments on 4 large-scale neural machine translation models demonstrate that our algorithm can achieve up to 4x speedup on softmax module, and 2x overall speedup without hurting BLEU on GPU. |
| Tasks | Machine Translation |
| Published | 2018-06-02 |
| URL | http://arxiv.org/abs/1806.00588v1 |
| http://arxiv.org/pdf/1806.00588v1.pdf | |
| PWC | https://paperswithcode.com/paper/fast-locality-sensitive-hashing-for-beam |
| Repo | |
| Framework | |
Generative Adversarial Networks for Realistic Synthesis of Hyperspectral Samples
| Title | Generative Adversarial Networks for Realistic Synthesis of Hyperspectral Samples |
| Authors | Nicolas Audebert, Bertrand Le Saux, Sébastien Lefèvre |
| Abstract | This work addresses the scarcity of annotated hyperspectral data required to train deep neural networks. Especially, we investigate generative adversarial networks and their application to the synthesis of consistent labeled spectra. By training such networks on public datasets, we show that these models are not only able to capture the underlying distribution, but also to generate genuine-looking and physically plausible spectra. Moreover, we experimentally validate that the synthetic samples can be used as an effective data augmentation strategy. We validate our approach on several public hyper-spectral datasets using a variety of deep classifiers. |
| Tasks | Data Augmentation |
| Published | 2018-06-07 |
| URL | http://arxiv.org/abs/1806.02583v1 |
| http://arxiv.org/pdf/1806.02583v1.pdf | |
| PWC | https://paperswithcode.com/paper/generative-adversarial-networks-for-realistic |
| Repo | |
| Framework | |
Exploring the importance of context and embeddings in neural NER models for task-oriented dialogue systems
| Title | Exploring the importance of context and embeddings in neural NER models for task-oriented dialogue systems |
| Authors | Pratik Jayarao, Chirag Jain, Aman Srivastava |
| Abstract | Named Entity Recognition (NER), a classic sequence labelling task, is an essential component of natural language understanding (NLU) systems in task-oriented dialog systems for slot filling. For well over a decade, different methods from lookup using gazetteers and domain ontology, classifiers over handcrafted features to end-to-end systems involving neural network architectures have been evaluated mostly in language-independent non-conversational settings. In this paper, we evaluate a modified version of the recent state of the art neural architecture in a conversational setting where messages are often short and noisy. We perform an array of experiments with different combinations of including the previous utterance in the dialogue as a source of additional features and using word and character level embeddings trained on a larger external corpus. All methods are evaluated on a combined dataset formed from two public English task-oriented conversational datasets belonging to travel and restaurant domains respectively. For additional evaluation, we also repeat some of our experiments after adding automatically translated and transliterated (from translated) versions to the English only dataset. |
| Tasks | Named Entity Recognition, Slot Filling, Task-Oriented Dialogue Systems |
| Published | 2018-12-06 |
| URL | http://arxiv.org/abs/1812.02370v1 |
| http://arxiv.org/pdf/1812.02370v1.pdf | |
| PWC | https://paperswithcode.com/paper/exploring-the-importance-of-context-and |
| Repo | |
| Framework | |
Customizing an Adversarial Example Generator with Class-Conditional GANs
| Title | Customizing an Adversarial Example Generator with Class-Conditional GANs |
| Authors | Shih-hong Tsai |
| Abstract | Adversarial examples are intentionally crafted data with the purpose of deceiving neural networks into misclassification. When we talk about strategies to create such examples, we usually refer to perturbation-based methods that fabricate adversarial examples by applying invisible perturbations onto normal data. The resulting data reserve their visual appearance to human observers, yet can be totally unrecognizable to DNN models, which in turn leads to completely misleading predictions. In this paper, however, we consider crafting adversarial examples from existing data as a limitation to example diversity. We propose a non-perturbation-based framework that generates native adversarial examples from class-conditional generative adversarial networks.As such, the generated data will not resemble any existing data and thus expand example diversity, raising the difficulty in adversarial defense. We then extend this framework to pre-trained conditional GANs, in which we turn an existing generator into an “adversarial-example generator”. We conduct experiments on our approach for MNIST and CIFAR10 datasets and have satisfactory results, showing that this approach can be a potential alternative to previous attack strategies. |
| Tasks | Adversarial Defense |
| Published | 2018-06-27 |
| URL | http://arxiv.org/abs/1806.10496v1 |
| http://arxiv.org/pdf/1806.10496v1.pdf | |
| PWC | https://paperswithcode.com/paper/customizing-an-adversarial-example-generator |
| Repo | |
| Framework | |
