Paper Group ANR 175
GANkyoku: a Generative Adversarial Network for Shakuhachi Music. Multi-level Gated Recurrent Neural Network for Dialog Act Classification. Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attacks. TransGaGa: Geometry-Aware Unsupervised Image-to-Image Translation. Context-aware Neural-based Dialog Act Classification on …
GANkyoku: a Generative Adversarial Network for Shakuhachi Music
| Title | GANkyoku: a Generative Adversarial Network for Shakuhachi Music |
| Authors | Omar Peracha, Shawn Head |
| Abstract | A common approach to generating symbolic music using neural networks involves repeated sampling of an autoregressive model until the full output sequence is obtained. While such approaches have shown some promise in generating short sequences of music, this typically has not extended to cases where the final target sequence is significantly longer, for example an entire piece of music. In this work we propose a network trained in an adversarial process to generate entire pieces of solo shakuhachi music, in the form of symbolic notation. The pieces are intended to refer clearly to traditional shakuhachi music, maintaining idiomaticity and key aesthetic qualities, while also adding novel features, ultimately creating worthy additions to the contemporary shakuhachi repertoire. A key subproblem is also addressed, namely the lack of relevant training data readily available, in two steps: firstly, we introduce the PH_Shaku dataset for symbolic traditional shakuhachi music; secondly, we build on previous work using conditioning in generative adversarial networks to introduce a technique for data augmentation. |
| Tasks | Data Augmentation |
| Published | 2019-11-22 |
| URL | https://arxiv.org/abs/1911.10119v1 |
| https://arxiv.org/pdf/1911.10119v1.pdf | |
| PWC | https://paperswithcode.com/paper/gankyoku-a-generative-adversarial-network-for |
| Repo | |
| Framework | |
Multi-level Gated Recurrent Neural Network for Dialog Act Classification
| Title | Multi-level Gated Recurrent Neural Network for Dialog Act Classification |
| Authors | Wei Li, Yunfang Wu |
| Abstract | In this paper we focus on the problem of dialog act (DA) labelling. This problem has recently attracted a lot of attention as it is an important sub-part of an automatic question answering system, which is currently in great demand. Traditional methods tend to see this problem as a sequence labelling task and deals with it by applying classifiers with rich features. Most of the current neural network models still omit the sequential information in the conversation. Henceforth, we apply a novel multi-level gated recurrent neural network (GRNN) with non-textual information to predict the DA tag. Our model not only utilizes textual information, but also makes use of non-textual and contextual information. In comparison, our model has shown significant improvement over previous works on Switchboard Dialog Act (SWDA) task by over 6%. |
| Tasks | Dialog Act Classification, Question Answering |
| Published | 2019-10-04 |
| URL | https://arxiv.org/abs/1910.01822v1 |
| https://arxiv.org/pdf/1910.01822v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-level-gated-recurrent-neural-network-1 |
| Repo | |
| Framework | |
Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attacks
| Title | Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attacks |
| Authors | Yinpeng Dong, Tianyu Pang, Hang Su, Jun Zhu |
| Abstract | Deep neural networks are vulnerable to adversarial examples, which can mislead classifiers by adding imperceptible perturbations. An intriguing property of adversarial examples is their good transferability, making black-box attacks feasible in real-world applications. Due to the threat of adversarial attacks, many methods have been proposed to improve the robustness. Several state-of-the-art defenses are shown to be robust against transferable adversarial examples. In this paper, we propose a translation-invariant attack method to generate more transferable adversarial examples against the defense models. By optimizing a perturbation over an ensemble of translated images, the generated adversarial example is less sensitive to the white-box model being attacked and has better transferability. To improve the efficiency of attacks, we further show that our method can be implemented by convolving the gradient at the untranslated image with a pre-defined kernel. Our method is generally applicable to any gradient-based attack method. Extensive experiments on the ImageNet dataset validate the effectiveness of the proposed method. Our best attack fools eight state-of-the-art defenses at an 82% success rate on average based only on the transferability, demonstrating the insecurity of the current defense techniques. |
| Tasks | |
| Published | 2019-04-05 |
| URL | http://arxiv.org/abs/1904.02884v1 |
| http://arxiv.org/pdf/1904.02884v1.pdf | |
| PWC | https://paperswithcode.com/paper/evading-defenses-to-transferable-adversarial |
| Repo | |
| Framework | |
TransGaGa: Geometry-Aware Unsupervised Image-to-Image Translation
| Title | TransGaGa: Geometry-Aware Unsupervised Image-to-Image Translation |
| Authors | Wayne Wu, Kaidi Cao, Cheng Li, Chen Qian, Chen Change Loy |
| Abstract | Unsupervised image-to-image translation aims at learning a mapping between two visual domains. However, learning a translation across large geometry variations always ends up with failure. In this work, we present a novel disentangle-and-translate framework to tackle the complex objects image-to-image translation task. Instead of learning the mapping on the image space directly, we disentangle image space into a Cartesian product of the appearance and the geometry latent spaces. Specifically, we first introduce a geometry prior loss and a conditional VAE loss to encourage the network to learn independent but complementary representations. The translation is then built on appearance and geometry space separately. Extensive experiments demonstrate the superior performance of our method to other state-of-the-art approaches, especially in the challenging near-rigid and non-rigid objects translation tasks. In addition, by taking different exemplars as the appearance references, our method also supports multimodal translation. Project page: https://wywu.github.io/projects/TGaGa/TGaGa.html |
| Tasks | Image-to-Image Translation, Unsupervised Image-To-Image Translation |
| Published | 2019-04-21 |
| URL | http://arxiv.org/abs/1904.09571v1 |
| http://arxiv.org/pdf/1904.09571v1.pdf | |
| PWC | https://paperswithcode.com/paper/transgaga-geometry-aware-unsupervised-image |
| Repo | |
| Framework | |
Context-aware Neural-based Dialog Act Classification on Automatically Generated Transcriptions
| Title | Context-aware Neural-based Dialog Act Classification on Automatically Generated Transcriptions |
| Authors | Daniel Ortega, Chia-Yu Li, Gisela Vallejo, Pavel Denisov, Ngoc Thang Vu |
| Abstract | This paper presents our latest investigations on dialog act (DA) classification on automatically generated transcriptions. We propose a novel approach that combines convolutional neural networks (CNNs) and conditional random fields (CRFs) for context modeling in DA classification. We explore the impact of transcriptions generated from different automatic speech recognition systems such as hybrid TDNN/HMM and End-to-End systems on the final performance. Experimental results on two benchmark datasets (MRDA and SwDA) show that the combination CNN and CRF improves consistently the accuracy. Furthermore, they show that although the word error rates are comparable, End-to-End ASR system seems to be more suitable for DA classification. |
| Tasks | Dialog Act Classification, End-To-End Speech Recognition, Speech Recognition |
| Published | 2019-02-28 |
| URL | http://arxiv.org/abs/1902.11060v1 |
| http://arxiv.org/pdf/1902.11060v1.pdf | |
| PWC | https://paperswithcode.com/paper/context-aware-neural-based-dialog-act |
| Repo | |
| Framework | |
Generalizing Complex Hypotheses on Product Distributions: Auctions, Prophet Inequalities, and Pandora’s Problem
| Title | Generalizing Complex Hypotheses on Product Distributions: Auctions, Prophet Inequalities, and Pandora’s Problem |
| Authors | Chenghao Guo, Zhiyi Huang, Zhihao Gavin Tang, Xinzhi Zhang |
| Abstract | This paper explores a theory of generalization for learning problems on product distributions, complementing the existing learning theories in the sense that it does not rely on any complexity measures of the hypothesis classes. The main contributions are two general sample complexity bounds: (1) $\tilde{O} \big( \frac{nk}{\epsilon^2} \big)$ samples are sufficient and necessary for learning an $\epsilon$-optimal hypothesis in any problem on an $n$-dimensional product distribution, whose marginals have finite supports of sizes at most $k$; (2) $\tilde{O} \big( \frac{n}{\epsilon^2} \big)$ samples are sufficient and necessary for any problem on $n$-dimensional product distributions if it satisfies a notion of strong monotonicity from the algorithmic game theory literature. As applications of these theories, we match the optimal sample complexity for single-parameter revenue maximization (Guo et al., STOC 2019), improve the state-of-the-art for multi-parameter revenue maximization (Gonczarowski and Weinberg, FOCS 2018) and prophet inequality (Correa et al., EC 2019), and provide the first and tight sample complexity bound for Pandora’s problem. |
| Tasks | |
| Published | 2019-11-27 |
| URL | https://arxiv.org/abs/1911.11936v1 |
| https://arxiv.org/pdf/1911.11936v1.pdf | |
| PWC | https://paperswithcode.com/paper/generalizing-complex-hypotheses-on-product |
| Repo | |
| Framework | |
PosNeg-Balanced Anchors with Aligned Features for Single-Shot Object Detection
| Title | PosNeg-Balanced Anchors with Aligned Features for Single-Shot Object Detection |
| Authors | Qiankun Tang, Shice Liu, Jie Li, Yu Hu |
| Abstract | We introduce a novel single-shot object detector to ease the imbalance of foreground-background class by suppressing the easy negatives while increasing the positives. To achieve this, we propose an Anchor Promotion Module (APM) which predicts the probability of each anchor as positive and adjusts their initial locations and shapes to promote both the quality and quantity of positive anchors. In addition, we design an efficient Feature Alignment Module (FAM) to extract aligned features for fitting the promoted anchors with the help of both the location and shape transformation information from the APM. We assemble the two proposed modules to the backbone of VGG-16 and ResNet-101 network with an encoder-decoder architecture. Extensive experiments on MS COCO well demonstrate our model performs competitively with alternative methods (40.0% mAP on \textit{test-dev} set) and runs faster (28.6 \textit{fps}). |
| Tasks | Object Detection |
| Published | 2019-08-09 |
| URL | https://arxiv.org/abs/1908.03295v1 |
| https://arxiv.org/pdf/1908.03295v1.pdf | |
| PWC | https://paperswithcode.com/paper/posneg-balanced-anchors-with-aligned-features |
| Repo | |
| Framework | |
Randomly Projected Additive Gaussian Processes for Regression
| Title | Randomly Projected Additive Gaussian Processes for Regression |
| Authors | Ian A. Delbridge, David S. Bindel, Andrew Gordon Wilson |
| Abstract | Gaussian processes (GPs) provide flexible distributions over functions, with inductive biases controlled by a kernel. However, in many applications Gaussian processes can struggle with even moderate input dimensionality. Learning a low dimensional projection can help alleviate this curse of dimensionality, but introduces many trainable hyperparameters, which can be cumbersome, especially in the small data regime. We use additive sums of kernels for GP regression, where each kernel operates on a different random projection of its inputs. Surprisingly, we find that as the number of random projections increases, the predictive performance of this approach quickly converges to the performance of a kernel operating on the original full dimensional inputs, over a wide range of data sets, even if we are projecting into a single dimension. As a consequence, many problems can remarkably be reduced to one dimensional input spaces, without learning a transformation. We prove this convergence and its rate, and additionally propose a deterministic approach that converges more quickly than purely random projections. Moreover, we demonstrate our approach can achieve faster inference and improved predictive accuracy for high-dimensional inputs compared to kernels in the original input space. |
| Tasks | Gaussian Processes |
| Published | 2019-12-30 |
| URL | https://arxiv.org/abs/1912.12834v1 |
| https://arxiv.org/pdf/1912.12834v1.pdf | |
| PWC | https://paperswithcode.com/paper/randomly-projected-additive-gaussian |
| Repo | |
| Framework | |
Exploring the Daschle Collection using Text Mining
| Title | Exploring the Daschle Collection using Text Mining |
| Authors | Damon Bayer, Semhar Michael |
| Abstract | A U.S. Senator from South Dakota donated documents that were accumulated during his service as a house representative and senator to be housed at the Bridges library at South Dakota State University. This project investigated the utility of quantitative statistical methods to explore some portions of this vast document collection. The available scanned documents and emails from constituents are analyzed using natural language processing methods including the Latent Dirichlet Allocation (LDA) model. This model identified major topics being discussed in a given collection of documents. Important events and popular issues from the Senator Daschles career are reflected in the changing topics from the model. These quantitative statistical methods provide a summary of the massive amount of text without requiring significant human effort or time and can be applied to similar collections. |
| Tasks | |
| Published | 2019-04-23 |
| URL | http://arxiv.org/abs/1904.12623v1 |
| http://arxiv.org/pdf/1904.12623v1.pdf | |
| PWC | https://paperswithcode.com/paper/190412623 |
| Repo | |
| Framework | |
Matrix sketching for supervised classification with imbalanced classes
| Title | Matrix sketching for supervised classification with imbalanced classes |
| Authors | Roberta Falcone, Angela Montanari, Laura Anderlucci |
| Abstract | Matrix sketching is a recently developed data compression technique. An input matrix A is efficiently approximated with a smaller matrix B, so that B preserves most of the properties of A up to some guaranteed approximation ratio. In so doing numerical operations on big data sets become faster. Sketching algorithms generally use random projections to compress the original dataset and this stochastic generation process makes them amenable to statistical analysis. The statistical properties of sketching algorithms have been widely studied in the context of multiple linear regression. In this paper we propose matrix sketching as a tool for rebalancing class sizes in supervised classification with imbalanced classes. It is well-known in fact that class imbalance may lead to poor classification performances especially as far as the minority class is concerned. |
| Tasks | |
| Published | 2019-12-02 |
| URL | https://arxiv.org/abs/1912.00905v1 |
| https://arxiv.org/pdf/1912.00905v1.pdf | |
| PWC | https://paperswithcode.com/paper/matrix-sketching-for-supervised |
| Repo | |
| Framework | |
Certified Adversarial Robustness for Deep Reinforcement Learning
| Title | Certified Adversarial Robustness for Deep Reinforcement Learning |
| Authors | Björn Lütjens, Michael Everett, Jonathan P. How |
| Abstract | Deep Neural Network-based systems are now the state-of-the-art in many robotics tasks, but their application in safety-critical domains remains dangerous without formal guarantees on network robustness. Small perturbations to sensor inputs (from noise or adversarial examples) are often enough to change network-based decisions, which was already shown to cause an autonomous vehicle to swerve into oncoming traffic. In light of these dangers, numerous algorithms have been developed as defensive mechanisms from these adversarial inputs, some of which provide formal robustness guarantees or certificates. This work leverages research on certified adversarial robustness to develop an online certified defense for deep reinforcement learning algorithms. The proposed defense computes guaranteed lower bounds on state-action values during execution to identify and choose the optimal action under a worst-case deviation in input space due to possible adversaries or noise. The approach is demonstrated on a Deep Q-Network policy and is shown to increase robustness to noise and adversaries in pedestrian collision avoidance scenarios and a classic control task. |
| Tasks | |
| Published | 2019-10-28 |
| URL | https://arxiv.org/abs/1910.12908v3 |
| https://arxiv.org/pdf/1910.12908v3.pdf | |
| PWC | https://paperswithcode.com/paper/certified-adversarial-robustness-for-deep |
| Repo | |
| Framework | |
Comparison of object detection methods for crop damage assessment using deep learning
| Title | Comparison of object detection methods for crop damage assessment using deep learning |
| Authors | Ali HamidiSepehr, Seyed Vahid Mirnezami, James Ward |
| Abstract | Severe weather events can cause large financial losses to farmers. Detailed information on the location and severity of damage will assist farmers, insurance companies, and disaster response agencies in making wise post-damage decisions. The goal of this study was a proof-of-concept to detect damaged crop areas from aerial imagery using computer vision and deep learning techniques. A specific objective was to compare existing object detection algorithms to determine which was best suited for crop damage detection. Two modes of crop damage common in maize (corn) production were simulated: stalk lodging at the lowest ear and stalk lodging at ground level. Simulated damage was used to create a training and analysis data set. An unmanned aerial system (UAS) equipped with a RGB camera was used for image acquisition. Three popular object detectors (Faster R-CNN, YOLOv2, and RetinaNet) were assessed for their ability to detect damaged regions in a field. Average precision was used to compare object detectors. YOLOv2 and RetinaNet were able to detect crop damage across multiple late-season growth stages. Faster R-CNN was not successful as the other two advanced detectors. Detecting crop damage at later growth stages was more difficult for all tested object detectors. Weed pressure in simulated damage plots and increased target density added additional complexity. |
| Tasks | Object Detection |
| Published | 2019-12-31 |
| URL | https://arxiv.org/abs/1912.13199v1 |
| https://arxiv.org/pdf/1912.13199v1.pdf | |
| PWC | https://paperswithcode.com/paper/comparison-of-object-detection-methods-for |
| Repo | |
| Framework | |
An Insight into the Dynamics and State Space Modelling of a 3-D Quadrotor
| Title | An Insight into the Dynamics and State Space Modelling of a 3-D Quadrotor |
| Authors | Rahul Vigneswaran K, Soman KP |
| Abstract | Drones have gained popularity in a wide range of field ranging from aerial photography, aerial mapping, and investigation of electric power lines. Every drone that we know today is carrying out some kind of control algorithm at the low level in order to manoeuvre itself around. For the quadrotor to either control itself autonomously or to develop a high-level user interface for us to control it, we need to understand the basic mathematics behind how it functions. This paper aims to explain the mathematical modelling of the dynamics of a 3 Dimensional quadrotor. As it may seem like a trivial task, it plays a vital role in how we control the drone. Also, additional effort has been taken to explain the transformations of the drone’s frame of reference to the inertial frame of reference. |
| Tasks | |
| Published | 2019-01-04 |
| URL | http://arxiv.org/abs/1901.01051v1 |
| http://arxiv.org/pdf/1901.01051v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-insight-into-the-dynamics-and-state-space |
| Repo | |
| Framework | |
SO(8) Supergravity and the Magic of Machine Learning
| Title | SO(8) Supergravity and the Magic of Machine Learning |
| Authors | Iulia M. Comsa, Moritz Firsching, Thomas Fischbacher |
| Abstract | Using de Wit-Nicolai $D=4;\mathcal{N}=8;SO(8)$ supergravity as an example, we show how modern Machine Learning software libraries such as Google’s TensorFlow can be employed to greatly simplify the analysis of high-dimensional scalar sectors of some M-Theory compactifications. We provide detailed information on the location, symmetries, and particle spectra and charges of 192 critical points on the scalar manifold of SO(8) supergravity, including one newly discovered $\mathcal{N}=1$ vacuum with $SO(3)$ residual symmetry, one new potentially stabilizable non-supersymmetric solution, and examples for “Galois conjugate pairs” of solutions, i.e. solution-pairs that share the same gauge group embedding into~$SO(8)$ and minimal polynomials for the cosmological constant. Where feasible, we give analytic expressions for solution coordinates and cosmological constants. As the authors’ aspiration is to present the discussion in a form that is accessible to both the Machine Learning and String Theory communities and allows adopting our methods towards the study of other models, we provide an introductory overview over the relevant Physics as well as Machine Learning concepts. This includes short pedagogical code examples. In particular, we show how to formulate a requirement for residual Supersymmetry as a Machine Learning loss function and effectively guide the numerical search towards supersymmetric critical points. Numerical investigations suggest that there are no further supersymmetric vacua beyond this newly discovered fifth solution. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://arxiv.org/abs/1906.00207v4 |
| https://arxiv.org/pdf/1906.00207v4.pdf | |
| PWC | https://paperswithcode.com/paper/so8-supergravity-and-the-magic-of-machine |
| Repo | |
| Framework | |
Probabilistic Generative Deep Learning for Molecular Design
| Title | Probabilistic Generative Deep Learning for Molecular Design |
| Authors | Daniel T. Chang |
| Abstract | Probabilistic generative deep learning for molecular design involves the discovery and design of new molecules and analysis of their structure, properties and activities by probabilistic generative models using the deep learning approach. It leverages the existing huge databases and publications of experimental results, and quantum-mechanical calculations, to learn and explore molecular structure, properties and activities. We discuss the major components of probabilistic generative deep learning for molecular design, which include molecular structure, molecular representations, deep generative models, molecular latent representations and latent space, molecular structure-property and structure-activity relationships, molecular similarity and molecular design. We highlight significant recent work using or applicable to this new approach. |
| Tasks | |
| Published | 2019-02-11 |
| URL | http://arxiv.org/abs/1902.05148v1 |
| http://arxiv.org/pdf/1902.05148v1.pdf | |
| PWC | https://paperswithcode.com/paper/probabilistic-generative-deep-learning-for |
| Repo | |
| Framework | |
