Paper Group ANR 443
Predictive Embeddings for Hate Speech Detection on Twitter. A corpus of precise natural textual entailment problems. Learning Hierarchical Visual Representations in Deep Neural Networks Using Hierarchical Linguistic Labels. The Relevance of Text and Speech Features in Automatic Non-native English Accent Identification. Forward Amortized Inference f …
Predictive Embeddings for Hate Speech Detection on Twitter
| Title | Predictive Embeddings for Hate Speech Detection on Twitter |
| Authors | Rohan Kshirsagar, Tyus Cukuvac, Kathleen McKeown, Susan McGregor |
| Abstract | We present a neural-network based approach to classifying online hate speech in general, as well as racist and sexist speech in particular. Using pre-trained word embeddings and max/mean pooling from simple, fully-connected transformations of these embeddings, we are able to predict the occurrence of hate speech on three commonly used publicly available datasets. Our models match or outperform state of the art F1 performance on all three datasets using significantly fewer parameters and minimal feature preprocessing compared to previous methods. |
| Tasks | Hate Speech Detection, Word Embeddings |
| Published | 2018-09-27 |
| URL | http://arxiv.org/abs/1809.10644v1 |
| http://arxiv.org/pdf/1809.10644v1.pdf | |
| PWC | https://paperswithcode.com/paper/predictive-embeddings-for-hate-speech |
| Repo | |
| Framework | |
A corpus of precise natural textual entailment problems
| Title | A corpus of precise natural textual entailment problems |
| Authors | Jean-Philippe Bernardy, Stergios Chatzikyriakidis |
| Abstract | In this paper, we present a new corpus of entailment problems. This corpus combines the following characteristics: 1. it is precise (does not leave out implicit hypotheses) 2. it is based on “real-world” texts (i.e. most of the premises were written for purposes other than testing textual entailment). 3. its size is 150. The corpus was constructed by taking problems from the Real Text Entailment and discovering missing hypotheses using a crowd of experts. We believe that this corpus constitutes a first step towards wide-coverage testing of precise natural-language inference systems. |
| Tasks | Natural Language Inference |
| Published | 2018-12-14 |
| URL | http://arxiv.org/abs/1812.05813v1 |
| http://arxiv.org/pdf/1812.05813v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-corpus-of-precise-natural-textual |
| Repo | |
| Framework | |
Learning Hierarchical Visual Representations in Deep Neural Networks Using Hierarchical Linguistic Labels
| Title | Learning Hierarchical Visual Representations in Deep Neural Networks Using Hierarchical Linguistic Labels |
| Authors | Joshua C. Peterson, Paul Soulos, Aida Nematzadeh, Thomas L. Griffiths |
| Abstract | Modern convolutional neural networks (CNNs) are able to achieve human-level object classification accuracy on specific tasks, and currently outperform competing models in explaining complex human visual representations. However, the categorization problem is posed differently for these networks than for humans: the accuracy of these networks is evaluated by their ability to identify single labels assigned to each image. These labels often cut arbitrarily across natural psychological taxonomies (e.g., dogs are separated into breeds, but never jointly categorized as “dogs”), and bias the resulting representations. By contrast, it is common for children to hear both “dog” and “Dalmatian” to describe the same stimulus, helping to group perceptually disparate objects (e.g., breeds) into a common mental class. In this work, we train CNN classifiers with multiple labels for each image that correspond to different levels of abstraction, and use this framework to reproduce classic patterns that appear in human generalization behavior. |
| Tasks | Object Classification |
| Published | 2018-05-19 |
| URL | http://arxiv.org/abs/1805.07647v1 |
| http://arxiv.org/pdf/1805.07647v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-hierarchical-visual-representations |
| Repo | |
| Framework | |
The Relevance of Text and Speech Features in Automatic Non-native English Accent Identification
| Title | The Relevance of Text and Speech Features in Automatic Non-native English Accent Identification |
| Authors | Sowmya Vajjala, Ziwei Zhou |
| Abstract | This paper describes our experiments with automatically identifying native accents from speech samples of non-native English speakers using low level audio features, and n-gram features from manual transcriptions. Using a publicly available non-native speech corpus and simple audio feature representations that do not perform word/phoneme recognition, we show that it is possible to achieve close to 90% classification accuracy for this task. While character n-grams perform similar to speech features, we show that speech features are not affected by prompt variation, whereas ngrams are. Since the approach followed can be easily adapted to any language provided we have enough training data, we believe these results will provide useful insights for the development of accent recognition systems and for the study of accents in the context of language learning. |
| Tasks | |
| Published | 2018-04-16 |
| URL | http://arxiv.org/abs/1804.05689v1 |
| http://arxiv.org/pdf/1804.05689v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-relevance-of-text-and-speech-features-in |
| Repo | |
| Framework | |
Forward Amortized Inference for Likelihood-Free Variational Marginalization
| Title | Forward Amortized Inference for Likelihood-Free Variational Marginalization |
| Authors | Luca Ambrogioni, Umut Güçlü, Julia Berezutskaya, Eva W. P. van den Borne, Yağmur Güçlütürk, Max Hinne, Eric Maris, Marcel A. J. van Gerven |
| Abstract | In this paper, we introduce a new form of amortized variational inference by using the forward KL divergence in a joint-contrastive variational loss. The resulting forward amortized variational inference is a likelihood-free method as its gradient can be sampled without bias and without requiring any evaluation of either the model joint distribution or its derivatives. We prove that our new variational loss is optimized by the exact posterior marginals in the fully factorized mean-field approximation, a property that is not shared with the more conventional reverse KL inference. Furthermore, we show that forward amortized inference can be easily marginalized over large families of latent variables in order to obtain a marginalized variational posterior. We consider two examples of variational marginalization. In our first example we train a Bayesian forecaster for predicting a simplified chaotic model of atmospheric convection. In the second example we train an amortized variational approximation of a Bayesian optimal classifier by marginalizing over the model space. The result is a powerful meta-classification network that can solve arbitrary classification problems without further training. |
| Tasks | |
| Published | 2018-05-29 |
| URL | http://arxiv.org/abs/1805.11542v1 |
| http://arxiv.org/pdf/1805.11542v1.pdf | |
| PWC | https://paperswithcode.com/paper/forward-amortized-inference-for-likelihood |
| Repo | |
| Framework | |
Fast and accurate approximation of the full conditional for gamma shape parameters
| Title | Fast and accurate approximation of the full conditional for gamma shape parameters |
| Authors | Jeffrey W. Miller |
| Abstract | The gamma distribution arises frequently in Bayesian models, but there is not an easy-to-use conjugate prior for the shape parameter of a gamma. This inconvenience is usually dealt with by using either Metropolis-Hastings moves, rejection sampling methods, or numerical integration. However, in models with a large number of shape parameters, these existing methods are slower or more complicated than one would like, making them burdensome in practice. It turns out that the full conditional distribution of the gamma shape parameter is well approximated by a gamma distribution, even for small sample sizes, when the prior on the shape parameter is also a gamma distribution. This article introduces a quick and easy algorithm for finding a gamma distribution that approximates the full conditional distribution of the shape parameter. We empirically demonstrate the speed and accuracy of the approximation across a wide range of conditions. If exactness is required, the approximation can be used as a proposal distribution for Metropolis-Hastings. |
| Tasks | |
| Published | 2018-02-05 |
| URL | http://arxiv.org/abs/1802.01610v2 |
| http://arxiv.org/pdf/1802.01610v2.pdf | |
| PWC | https://paperswithcode.com/paper/fast-and-accurate-approximation-of-the-full |
| Repo | |
| Framework | |
“Double-DIP”: Unsupervised Image Decomposition via Coupled Deep-Image-Priors
| Title | “Double-DIP”: Unsupervised Image Decomposition via Coupled Deep-Image-Priors |
| Authors | Yossi Gandelsman, Assaf Shocher, Michal Irani |
| Abstract | Many seemingly unrelated computer vision tasks can be viewed as a special case of image decomposition into separate layers. For example, image segmentation (separation into foreground and background layers); transparent layer separation (into reflection and transmission layers); Image dehazing (separation into a clear image and a haze map), and more. In this paper we propose a unified framework for unsupervised layer decomposition of a single image, based on coupled “Deep-image-Prior” (DIP) networks. It was shown [Ulyanov et al] that the structure of a single DIP generator network is sufficient to capture the low-level statistics of a single image. We show that coupling multiple such DIPs provides a powerful tool for decomposing images into their basic components, for a wide variety of applications. This capability stems from the fact that the internal statistics of a mixture of layers is more complex than the statistics of each of its individual components. We show the power of this approach for Image-Dehazing, Fg/Bg Segmentation, Watermark-Removal, Transparency Separation in images and video, and more. These capabilities are achieved in a totally unsupervised way, with no training examples other than the input image/video itself. |
| Tasks | Image Dehazing, Semantic Segmentation, Transparency Separation |
| Published | 2018-12-02 |
| URL | http://arxiv.org/abs/1812.00467v2 |
| http://arxiv.org/pdf/1812.00467v2.pdf | |
| PWC | https://paperswithcode.com/paper/double-dip-unsupervised-image-decomposition |
| Repo | |
| Framework | |
Penalizing side effects using stepwise relative reachability
| Title | Penalizing side effects using stepwise relative reachability |
| Authors | Victoria Krakovna, Laurent Orseau, Ramana Kumar, Miljan Martic, Shane Legg |
| Abstract | How can we design safe reinforcement learning agents that avoid unnecessary disruptions to their environment? We show that current approaches to penalizing side effects can introduce bad incentives, e.g. to prevent any irreversible changes in the environment, including the actions of other agents. To isolate the source of such undesirable incentives, we break down side effects penalties into two components: a baseline state and a measure of deviation from this baseline state. We argue that some of these incentives arise from the choice of baseline, and others arise from the choice of deviation measure. We introduce a new variant of the stepwise inaction baseline and a new deviation measure based on relative reachability of states. The combination of these design choices avoids the given undesirable incentives, while simpler baselines and the unreachability measure fail. We demonstrate this empirically by comparing different combinations of baseline and deviation measure choices on a set of gridworld experiments designed to illustrate possible bad incentives. |
| Tasks | |
| Published | 2018-06-04 |
| URL | http://arxiv.org/abs/1806.01186v2 |
| http://arxiv.org/pdf/1806.01186v2.pdf | |
| PWC | https://paperswithcode.com/paper/measuring-and-avoiding-side-effects-using |
| Repo | |
| Framework | |
Class Subset Selection for Transfer Learning using Submodularity
| Title | Class Subset Selection for Transfer Learning using Submodularity |
| Authors | Varun Manjunatha, Srikumar Ramalingam, Tim K. Marks, Larry Davis |
| Abstract | In recent years, it is common practice to extract fully-connected layer (fc) features that were learned while performing image classification on a source dataset, such as ImageNet, and apply them generally to a wide range of other tasks. The general usefulness of some large training datasets for transfer learning is not yet well understood, and raises a number of questions. For example, in the context of transfer learning, what is the role of a specific class in the source dataset, and how is the transferability of fc features affected when they are trained using various subsets of the set of all classes in the source dataset? In this paper, we address the question of how to select an optimal subset of the set of classes, subject to a budget constraint, that will more likely generate good features for other tasks. To accomplish this, we use a submodular set function to model the accuracy achievable on a new task when the features have been learned on a given subset of classes of the source dataset. An optimal subset is identified as the set that maximizes this submodular function. The maximization can be accomplished using an efficient greedy algorithm that comes with guarantees on the optimality of the solution. We empirically validate our submodular model by successfully identifying subsets of classes that produce good features for new tasks. |
| Tasks | Image Classification, Transfer Learning |
| Published | 2018-03-30 |
| URL | http://arxiv.org/abs/1804.00060v1 |
| http://arxiv.org/pdf/1804.00060v1.pdf | |
| PWC | https://paperswithcode.com/paper/class-subset-selection-for-transfer-learning |
| Repo | |
| Framework | |
Information Assisted Dictionary Learning for fMRI data analysis
| Title | Information Assisted Dictionary Learning for fMRI data analysis |
| Authors | Manuel Morante, Yannis Kopsinis, Sergios Theodoridis, Athanassios Protopapas |
| Abstract | In this paper, the task-related fMRI problem is treated in its matrix factorization formulation, focused on the Dictionary Learning (DL) approach. The new method allows the incorporation of a priori knowledge associated both with the experimental design as well as with available brain Atlases. Moreover, the proposed method can efficiently cope with uncertainties related to the HRF modeling. In addition, the proposed method bypasses one of the major drawbacks that are associated with DL methods; that is, the selection of the sparsity-related regularization parameters. In our formulation, an alternative sparsity promoting constraint is employed, that bears a direct relation to the number of voxels in the spatial maps. Hence, the related parameters can be tuned using information that is available from brain atlases. The proposed method is evaluated against several other popular techniques, including GLM. The obtained performance gains are reported via a novel realistic synthetic fMRI dataset as well as real data that are related to a challenging experimental design. |
| Tasks | Dictionary Learning |
| Published | 2018-02-05 |
| URL | https://arxiv.org/abs/1802.01334v3 |
| https://arxiv.org/pdf/1802.01334v3.pdf | |
| PWC | https://paperswithcode.com/paper/information-assisted-dictionary-learning-for |
| Repo | |
| Framework | |
Attention Incorporate Network: A network can adapt various data size
| Title | Attention Incorporate Network: A network can adapt various data size |
| Authors | Liangbo He, Hao Sun |
| Abstract | In traditional neural networks for image processing, the inputs of the neural networks should be the same size such as 2242243. But how can we train the neural net model with different input size? A common way to do is image deformation which accompany a problem of information loss (e.g. image crop or wrap). Sequence model(RNN, LSTM, etc.) can accept different size of input like text and audio. But one disadvantage for sequence model is that the previous information will become more fragmentary during the transfer in time step, it will make the network hard to train especially for long sequential data. In this paper we propose a new network structure called Attention Incorporate Network(AIN). It solve the problem of different size of inputs including: images, text, audio, and extract the key features of the inputs by attention mechanism, pay different attention depends on the importance of the features not rely on the data size. Experimentally, AIN achieve a higher accuracy, better convergence comparing to the same size of other network structure |
| Tasks | |
| Published | 2018-06-06 |
| URL | http://arxiv.org/abs/1806.03961v1 |
| http://arxiv.org/pdf/1806.03961v1.pdf | |
| PWC | https://paperswithcode.com/paper/attention-incorporate-network-a-network-can |
| Repo | |
| Framework | |
A dataset of 40K naturalistic 6-degree-of-freedom robotic grasp demonstrations
| Title | A dataset of 40K naturalistic 6-degree-of-freedom robotic grasp demonstrations |
| Authors | Rajan Iyengar, Victor Reyes Osorio, Presish Bhattachan, Adrian Ragobar, Bryan Tripp |
| Abstract | Modern approaches to grasp planning often involve deep learning. However, there are only a few large datasets of labelled grasping examples on physical robots, and available datasets involve relatively simple planar grasps with two-fingered grippers. Here we present: 1) a new human grasp demonstration method that facilitates rapid collection of naturalistic grasp examples, with full six-degree-of-freedom gripper positioning; and 2) a dataset of roughly forty thousand successful grasps on 109 different rigid objects with the RightHand Robotics three-fingered ReFlex gripper. |
| Tasks | |
| Published | 2018-12-31 |
| URL | http://arxiv.org/abs/1812.11683v1 |
| http://arxiv.org/pdf/1812.11683v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-dataset-of-40k-naturalistic-6-degree-of |
| Repo | |
| Framework | |
Deep Learning using K-space Based Data Augmentation for Automated Cardiac MR Motion Artefact Detection
| Title | Deep Learning using K-space Based Data Augmentation for Automated Cardiac MR Motion Artefact Detection |
| Authors | Ilkay Oksuz, Bram Ruijsink, Esther Puyol-Anton, Aurelien Bustin, Gastao Cruz, Claudia Prieto, Daniel Rueckert, Julia A. Schnabel, Andrew P. King |
| Abstract | Quality assessment of medical images is essential for complete automation of image processing pipelines. For large population studies such as the UK Biobank, artefacts such as those caused by heart motion are problematic and manual identification is tedious and time-consuming. Therefore, there is an urgent need for automatic image quality assessment techniques. In this paper, we propose a method to automatically detect the presence of motion-related artefacts in cardiac magnetic resonance (CMR) images. As this is a highly imbalanced classification problem (due to the high number of good quality images compared to the low number of images with motion artefacts), we propose a novel k-space based training data augmentation approach in order to address this problem. Our method is based on 3D spatio-temporal Convolutional Neural Networks, and is able to detect 2D+time short axis images with motion artefacts in less than 1ms. We test our algorithm on a subset of the UK Biobank dataset consisting of 3465 CMR images and achieve not only high accuracy in detection of motion artefacts, but also high precision and recall. We compare our approach to a range of state-of-the-art quality assessment methods. |
| Tasks | Data Augmentation, Image Quality Assessment |
| Published | 2018-08-15 |
| URL | http://arxiv.org/abs/1808.05130v2 |
| http://arxiv.org/pdf/1808.05130v2.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-using-k-space-based-data |
| Repo | |
| Framework | |
Focal Loss Dense Detector for Vehicle Surveillance
| Title | Focal Loss Dense Detector for Vehicle Surveillance |
| Authors | Xiaoliang Wang, Peng Cheng, Xinchuan Liu, Benedict Uzochukwu |
| Abstract | Deep learning has been widely recognized as a promising approach in different computer vision applications. Specifically, one-stage object detector and two-stage object detector are regarded as the most important two groups of Convolutional Neural Network based object detection methods. One-stage object detector could usually outperform two-stage object detector in speed; However, it normally trails in detection accuracy, compared with two-stage object detectors. In this study, focal loss based RetinaNet, which works as one-stage object detector, is utilized to be able to well match the speed of regular one-stage detectors and also defeat two-stage detectors in accuracy, for vehicle detection. State-of-the-art performance result has been showed on the DETRAC vehicle dataset. |
| Tasks | Object Detection |
| Published | 2018-03-03 |
| URL | http://arxiv.org/abs/1803.01114v1 |
| http://arxiv.org/pdf/1803.01114v1.pdf | |
| PWC | https://paperswithcode.com/paper/focal-loss-dense-detector-for-vehicle |
| Repo | |
| Framework | |
Subset Scanning Over Neural Network Activations
| Title | Subset Scanning Over Neural Network Activations |
| Authors | Skyler Speakman, Srihari Sridharan, Sekou Remy, Komminist Weldemariam, Edward McFowland |
| Abstract | This work views neural networks as data generating systems and applies anomalous pattern detection techniques on that data in order to detect when a network is processing an anomalous input. Detecting anomalies is a critical component for multiple machine learning problems including detecting adversarial noise. More broadly, this work is a step towards giving neural networks the ability to recognize an out-of-distribution sample. This is the first work to introduce “Subset Scanning” methods from the anomalous pattern detection domain to the task of detecting anomalous input of neural networks. Subset scanning treats the detection problem as a search for the most anomalous subset of node activations (i.e., highest scoring subset according to non-parametric scan statistics). Mathematical properties of these scoring functions allow the search to be completed in log-linear rather than exponential time while still guaranteeing the most anomalous subset of nodes in the network is identified for a given input. Quantitative results for detecting and characterizing adversarial noise are provided for CIFAR-10 images on a simple convolutional neural network. We observe an “interference” pattern where anomalous activations in shallow layers suppress the activation structure of the original image in deeper layers. |
| Tasks | |
| Published | 2018-10-19 |
| URL | http://arxiv.org/abs/1810.08676v1 |
| http://arxiv.org/pdf/1810.08676v1.pdf | |
| PWC | https://paperswithcode.com/paper/subset-scanning-over-neural-network |
| Repo | |
| Framework | |
