Paper Group AWR 145
Lessons learned in multilingual grounded language learning. BSN: Boundary Sensitive Network for Temporal Action Proposal Generation. UNIQUE: Unsupervised Image Quality Estimation. Jointly Multiple Events Extraction via Attention-based Graph Information Aggregation. Typeface Completion with Generative Adversarial Networks. Graph Capsule Convolutiona …
Lessons learned in multilingual grounded language learning
Title | Lessons learned in multilingual grounded language learning |
Authors | Ákos Kádár, Desmond Elliott, Marc-Alexandre Côté, Grzegorz Chrupała, Afra Alishahi |
Abstract | Recent work has shown how to learn better visual-semantic embeddings by leveraging image descriptions in more than one language. Here, we investigate in detail which conditions affect the performance of this type of grounded language learning model. We show that multilingual training improves over bilingual training, and that low-resource languages benefit from training with higher-resource languages. We demonstrate that a multilingual model can be trained equally well on either translations or comparable sentence pairs, and that annotating the same set of images in multiple language enables further improvements via an additional caption-caption ranking objective. |
Tasks | |
Published | 2018-09-20 |
URL | http://arxiv.org/abs/1809.07615v1 |
http://arxiv.org/pdf/1809.07615v1.pdf | |
PWC | https://paperswithcode.com/paper/lessons-learned-in-multilingual-grounded |
Repo | https://github.com/kadarakos/mulisera |
Framework | pytorch |
BSN: Boundary Sensitive Network for Temporal Action Proposal Generation
Title | BSN: Boundary Sensitive Network for Temporal Action Proposal Generation |
Authors | Tianwei Lin, Xu Zhao, Haisheng Su, Chongjing Wang, Ming Yang |
Abstract | Temporal action proposal generation is an important yet challenging problem, since temporal proposals with rich action content are indispensable for analysing real-world videos with long duration and high proportion irrelevant content. This problem requires methods not only generating proposals with precise temporal boundaries, but also retrieving proposals to cover truth action instances with high recall and high overlap using relatively fewer proposals. To address these difficulties, we introduce an effective proposal generation method, named Boundary-Sensitive Network (BSN), which adopts “local to global” fashion. Locally, BSN first locates temporal boundaries with high probabilities, then directly combines these boundaries as proposals. Globally, with Boundary-Sensitive Proposal feature, BSN retrieves proposals by evaluating the confidence of whether a proposal contains an action within its region. We conduct experiments on two challenging datasets: ActivityNet-1.3 and THUMOS14, where BSN outperforms other state-of-the-art temporal action proposal generation methods with high recall and high temporal precision. Finally, further experiments demonstrate that by combining existing action classifiers, our method significantly improves the state-of-the-art temporal action detection performance. |
Tasks | Action Detection, Temporal Action Localization, Temporal Action Proposal Generation |
Published | 2018-06-08 |
URL | http://arxiv.org/abs/1806.02964v3 |
http://arxiv.org/pdf/1806.02964v3.pdf | |
PWC | https://paperswithcode.com/paper/bsn-boundary-sensitive-network-for-temporal |
Repo | https://github.com/wzmsltw/BSN-boundary-sensitive-network |
Framework | pytorch |
UNIQUE: Unsupervised Image Quality Estimation
Title | UNIQUE: Unsupervised Image Quality Estimation |
Authors | D. Temel, M. Prabhushankar, G. AlRegib |
Abstract | In this paper, we estimate perceived image quality using sparse representations obtained from generic image databases through an unsupervised learning approach. A color space transformation, a mean subtraction, and a whitening operation are used to enhance descriptiveness of images by reducing spatial redundancy; a linear decoder is used to obtain sparse representations; and a thresholding stage is used to formulate suppression mechanisms in a visual system. A linear decoder is trained with 7 GB worth of data, which corresponds to 100,000 8x8 image patches randomly obtained from nearly 1,000 images in the ImageNet 2013 database. A patch-wise training approach is preferred to maintain local information. The proposed quality estimator UNIQUE is tested on the LIVE, the Multiply Distorted LIVE, and the TID 2013 databases and compared with thirteen quality estimators. Experimental results show that UNIQUE is generally a top performing quality estimator in terms of accuracy, consistency, linearity, and monotonic behavior. |
Tasks | Image Quality Estimation |
Published | 2018-10-15 |
URL | http://arxiv.org/abs/1810.06631v2 |
http://arxiv.org/pdf/1810.06631v2.pdf | |
PWC | https://paperswithcode.com/paper/unique-unsupervised-image-quality-estimation |
Repo | https://github.com/olivesgatech/UNIQUE-Unsupervised-Image-Quality-Estimation |
Framework | none |
Jointly Multiple Events Extraction via Attention-based Graph Information Aggregation
Title | Jointly Multiple Events Extraction via Attention-based Graph Information Aggregation |
Authors | Xiao Liu, Zhunchen Luo, Heyan Huang |
Abstract | Event extraction is of practical utility in natural language processing. In the real world, it is a common phenomenon that multiple events existing in the same sentence, where extracting them are more difficult than extracting a single event. Previous works on modeling the associations between events by sequential modeling methods suffer a lot from the low efficiency in capturing very long-range dependencies. In this paper, we propose a novel Jointly Multiple Events Extraction (JMEE) framework to jointly extract multiple event triggers and arguments by introducing syntactic shortcut arcs to enhance information flow and attention-based graph convolution networks to model graph information. The experiment results demonstrate that our proposed framework achieves competitive results compared with state-of-the-art methods. |
Tasks | |
Published | 2018-09-24 |
URL | http://arxiv.org/abs/1809.09078v2 |
http://arxiv.org/pdf/1809.09078v2.pdf | |
PWC | https://paperswithcode.com/paper/jointly-multiple-events-extraction-via |
Repo | https://github.com/lx865712528/JMEE |
Framework | pytorch |
Typeface Completion with Generative Adversarial Networks
Title | Typeface Completion with Generative Adversarial Networks |
Authors | Yonggyu Park, Junhyun Lee, Yookyung Koh, Inyeop Lee, Jinhyuk Lee, Jaewoo Kang |
Abstract | The mood of a text and the intention of the writer can be reflected in the typeface. However, in designing a typeface, it is difficult to keep the style of various characters consistent, especially for languages with lots of morphological variations such as Chinese. In this paper, we propose a Typeface Completion Network (TCN) which takes one character as an input, and automatically completes the entire set of characters in the same style as the input characters. Unlike existing models proposed for image-to-image translation, TCN embeds a character image into two separate vectors representing typeface and content. Combined with a reconstruction loss from the latent space, and with other various losses, TCN overcomes the inherent difficulty in designing a typeface. Also, compared to previous image-to-image translation models, TCN generates high quality character images of the same typeface with a much smaller number of model parameters. We validate our proposed model on the Chinese and English character datasets, which is paired data, and the CelebA dataset, which is unpaired data. In these datasets, TCN outperforms recently proposed state-of-the-art models for image-to-image translation. The source code of our model is available at https://github.com/yongqyu/TCN. |
Tasks | Image-to-Image Translation, Typeface Completion |
Published | 2018-11-09 |
URL | http://arxiv.org/abs/1811.03762v2 |
http://arxiv.org/pdf/1811.03762v2.pdf | |
PWC | https://paperswithcode.com/paper/typeface-completion-with-generative |
Repo | https://github.com/yongqyu/TCN |
Framework | pytorch |
Graph Capsule Convolutional Neural Networks
Title | Graph Capsule Convolutional Neural Networks |
Authors | Saurabh Verma, Zhi-Li Zhang |
Abstract | Graph Convolutional Neural Networks (GCNNs) are the most recent exciting advancement in deep learning field and their applications are quickly spreading in multi-cross-domains including bioinformatics, chemoinformatics, social networks, natural language processing and computer vision. In this paper, we expose and tackle some of the basic weaknesses of a GCNN model with a capsule idea presented in \cite{hinton2011transforming} and propose our Graph Capsule Network (GCAPS-CNN) model. In addition, we design our GCAPS-CNN model to solve especially graph classification problem which current GCNN models find challenging. Through extensive experiments, we show that our proposed Graph Capsule Network can significantly outperforms both the existing state-of-art deep learning methods and graph kernels on graph classification benchmark datasets. |
Tasks | Graph Classification |
Published | 2018-05-21 |
URL | http://arxiv.org/abs/1805.08090v4 |
http://arxiv.org/pdf/1805.08090v4.pdf | |
PWC | https://paperswithcode.com/paper/graph-capsule-convolutional-neural-networks |
Repo | https://github.com/vermaMachineLearning/Graph-Capsule-CNN-Networks |
Framework | none |
Data augmentation using synthetic data for time series classification with deep residual networks
Title | Data augmentation using synthetic data for time series classification with deep residual networks |
Authors | Hassan Ismail Fawaz, Germain Forestier, Jonathan Weber, Lhassane Idoumghar, Pierre-Alain Muller |
Abstract | Data augmentation in deep neural networks is the process of generating artificial data in order to reduce the variance of the classifier with the goal to reduce the number of errors. This idea has been shown to improve deep neural network’s generalization capabilities in many computer vision tasks such as image recognition and object localization. Apart from these applications, deep Convolutional Neural Networks (CNNs) have also recently gained popularity in the Time Series Classification (TSC) community. However, unlike in image recognition problems, data augmentation techniques have not yet been investigated thoroughly for the TSC task. This is surprising as the accuracy of deep learning models for TSC could potentially be improved, especially for small datasets that exhibit overfitting, when a data augmentation method is adopted. In this paper, we fill this gap by investigating the application of a recently proposed data augmentation technique based on the Dynamic Time Warping distance, for a deep learning model for TSC. To evaluate the potential of augmenting the training set, we performed extensive experiments using the UCR TSC benchmark. Our preliminary experiments reveal that data augmentation can drastically increase deep CNN’s accuracy on some datasets and significantly improve the deep model’s accuracy when the method is used in an ensemble approach. |
Tasks | Data Augmentation, Time Series, Time Series Classification |
Published | 2018-08-07 |
URL | http://arxiv.org/abs/1808.02455v1 |
http://arxiv.org/pdf/1808.02455v1.pdf | |
PWC | https://paperswithcode.com/paper/data-augmentation-using-synthetic-data-for |
Repo | https://github.com/hfawaz/aaltd18 |
Framework | tf |
T-CGAN: Conditional Generative Adversarial Network for Data Augmentation in Noisy Time Series with Irregular Sampling
Title | T-CGAN: Conditional Generative Adversarial Network for Data Augmentation in Noisy Time Series with Irregular Sampling |
Authors | Giorgia Ramponi, Pavlos Protopapas, Marco Brambilla, Ryan Janssen |
Abstract | In this paper we propose a data augmentation method for time series with irregular sampling, Time-Conditional Generative Adversarial Network (T-CGAN). Our approach is based on Conditional Generative Adversarial Networks (CGAN), where the generative step is implemented by a deconvolutional NN and the discriminative step by a convolutional NN. Both the generator and the discriminator are conditioned on the sampling timestamps, to learn the hidden relationship between data and timestamps, and consequently to generate new time series. We evaluate our model with synthetic and real-world datasets. For the synthetic data, we compare the performance of a classifier trained with T-CGAN-generated data, against the performance of the same classifier trained on the original data. Results show that classifiers trained on T-CGAN-generated data perform the same as classifiers trained on real data, even with very short time series and small training sets. For the real world datasets, we compare our method with other techniques of data augmentation for time series, such as time slicing and time warping, over a classification problem with unbalanced datasets. Results show that our method always outperforms the other approaches, both in case of regularly sampled and irregularly sampled time series. We achieve particularly good performance in case with a small training set and short, noisy, irregularly-sampled time series. |
Tasks | Data Augmentation, Time Series |
Published | 2018-11-20 |
URL | http://arxiv.org/abs/1811.08295v2 |
http://arxiv.org/pdf/1811.08295v2.pdf | |
PWC | https://paperswithcode.com/paper/t-cgan-conditional-generative-adversarial |
Repo | https://github.com/gioramponi/GAN_Time_Series |
Framework | tf |
Complex Gated Recurrent Neural Networks
Title | Complex Gated Recurrent Neural Networks |
Authors | Moritz Wolter, Angela Yao |
Abstract | Complex numbers have long been favoured for digital signal processing, yet complex representations rarely appear in deep learning architectures. RNNs, widely used to process time series and sequence information, could greatly benefit from complex representations. We present a novel complex gated recurrent cell, which is a hybrid cell combining complex-valued and norm-preserving state transitions with a gating mechanism. The resulting RNN exhibits excellent stability and convergence properties and performs competitively on the synthetic memory and adding task, as well as on the real-world tasks of human motion prediction. |
Tasks | motion prediction, Time Series |
Published | 2018-06-21 |
URL | http://arxiv.org/abs/1806.08267v2 |
http://arxiv.org/pdf/1806.08267v2.pdf | |
PWC | https://paperswithcode.com/paper/complex-gated-recurrent-neural-networks |
Repo | https://github.com/v0lta/Complex-gated-recurrent-neural-networks |
Framework | tf |
Scalable Private Learning with PATE
Title | Scalable Private Learning with PATE |
Authors | Nicolas Papernot, Shuang Song, Ilya Mironov, Ananth Raghunathan, Kunal Talwar, Úlfar Erlingsson |
Abstract | Models and examples built with TensorFlow |
Tasks | |
Published | 2018-02-24 |
URL | http://arxiv.org/abs/1802.08908v1 |
http://arxiv.org/pdf/1802.08908v1.pdf | |
PWC | https://paperswithcode.com/paper/scalable-private-learning-with-pate |
Repo | https://github.com/frhrdr/patepy |
Framework | tf |
Non-Adversarial Image Synthesis with Generative Latent Nearest Neighbors
Title | Non-Adversarial Image Synthesis with Generative Latent Nearest Neighbors |
Authors | Yedid Hoshen, Jitendra Malik |
Abstract | Unconditional image generation has recently been dominated by generative adversarial networks (GANs). GAN methods train a generator which regresses images from random noise vectors, as well as a discriminator that attempts to differentiate between the generated images and a training set of real images. GANs have shown amazing results at generating realistic looking images. Despite their success, GANs suffer from critical drawbacks including: unstable training and mode-dropping. The weaknesses in GANs have motivated research into alternatives including: variational auto-encoders (VAEs), latent embedding learning methods (e.g. GLO) and nearest-neighbor based implicit maximum likelihood estimation (IMLE). Unfortunately at the moment, GANs still significantly outperform the alternative methods for image generation. In this work, we present a novel method - Generative Latent Nearest Neighbors (GLANN) - for training generative models without adversarial training. GLANN combines the strengths of IMLE and GLO in a way that overcomes the main drawbacks of each method. Consequently, GLANN generates images that are far better than GLO and IMLE. Our method does not suffer from mode collapse which plagues GAN training and is much more stable. Qualitative results show that GLANN outperforms a baseline consisting of 800 GANs and VAEs on commonly used datasets. Our models are also shown to be effective for training truly non-adversarial unsupervised image translation. |
Tasks | Image Generation |
Published | 2018-12-21 |
URL | http://arxiv.org/abs/1812.08985v1 |
http://arxiv.org/pdf/1812.08985v1.pdf | |
PWC | https://paperswithcode.com/paper/non-adversarial-image-synthesis-with |
Repo | https://github.com/yedidh/glann |
Framework | pytorch |
Fine-Grained Visual Categorization using Meta-Learning Optimization with Sample Selection of Auxiliary Data
Title | Fine-Grained Visual Categorization using Meta-Learning Optimization with Sample Selection of Auxiliary Data |
Authors | Yabin Zhang, Hui Tang, Kui Jia |
Abstract | Fine-grained visual categorization (FGVC) is challenging due in part to the fact that it is often difficult to acquire an enough number of training samples. To employ large models for FGVC without suffering from overfitting, existing methods usually adopt a strategy of pre-training the models using a rich set of auxiliary data, followed by fine-tuning on the target FGVC task. However, the objective of pre-training does not take the target task into account, and consequently such obtained models are suboptimal for fine-tuning. To address this issue, we propose in this paper a new deep FGVC model termed MetaFGNet. Training of MetaFGNet is based on a novel regularized meta-learning objective, which aims to guide the learning of network parameters so that they are optimal for adapting to the target FGVC task. Based on MetaFGNet, we also propose a simple yet effective scheme for selecting more useful samples from the auxiliary data. Experiments on benchmark FGVC datasets show the efficacy of our proposed method. |
Tasks | Fine-Grained Visual Categorization, Meta-Learning |
Published | 2018-07-28 |
URL | http://arxiv.org/abs/1807.10916v1 |
http://arxiv.org/pdf/1807.10916v1.pdf | |
PWC | https://paperswithcode.com/paper/fine-grained-visual-categorization-using-meta |
Repo | https://github.com/YabinZhang1994/MetaFGNet |
Framework | pytorch |
Distribution-Aware Binarization of Neural Networks for Sketch Recognition
Title | Distribution-Aware Binarization of Neural Networks for Sketch Recognition |
Authors | Ameya Prabhu, Vishal Batchu, Sri Aurobindo Munagala, Rohit Gajawada, Anoop Namboodiri |
Abstract | Deep neural networks are highly effective at a range of computational tasks. However, they tend to be computationally expensive, especially in vision-related problems, and also have large memory requirements. One of the most effective methods to achieve significant improvements in computational/spatial efficiency is to binarize the weights and activations in a network. However, naive binarization results in accuracy drops when applied to networks for most tasks. In this work, we present a highly generalized, distribution-aware approach to binarizing deep networks that allows us to retain the advantages of a binarized network, while reducing accuracy drops. We also develop efficient implementations for our proposed approach across different architectures. We present a theoretical analysis of the technique to show the effective representational power of the resulting layers, and explore the forms of data they model best. Experiments on popular datasets show that our technique offers better accuracies than naive binarization, while retaining the same benefits that binarization provides - with respect to run-time compression, reduction of computational costs, and power consumption. |
Tasks | Sketch Recognition |
Published | 2018-04-09 |
URL | http://arxiv.org/abs/1804.02941v1 |
http://arxiv.org/pdf/1804.02941v1.pdf | |
PWC | https://paperswithcode.com/paper/distribution-aware-binarization-of-neural |
Repo | https://github.com/erilyth/DistributionAwareBinarizedNetworks-WACV18 |
Framework | pytorch |
The Gaussian Process Autoregressive Regression Model (GPAR)
Title | The Gaussian Process Autoregressive Regression Model (GPAR) |
Authors | James Requeima, Will Tebbutt, Wessel Bruinsma, Richard E. Turner |
Abstract | Multi-output regression models must exploit dependencies between outputs to maximise predictive performance. The application of Gaussian processes (GPs) to this setting typically yields models that are computationally demanding and have limited representational power. We present the Gaussian Process Autoregressive Regression (GPAR) model, a scalable multi-output GP model that is able to capture nonlinear, possibly input-varying, dependencies between outputs in a simple and tractable way: the product rule is used to decompose the joint distribution over the outputs into a set of conditionals, each of which is modelled by a standard GP. GPAR’s efficacy is demonstrated on a variety of synthetic and real-world problems, outperforming existing GP models and achieving state-of-the-art performance on established benchmarks. |
Tasks | Gaussian Processes |
Published | 2018-02-20 |
URL | http://arxiv.org/abs/1802.07182v4 |
http://arxiv.org/pdf/1802.07182v4.pdf | |
PWC | https://paperswithcode.com/paper/the-gaussian-process-autoregressive |
Repo | https://github.com/wesselb/gpar |
Framework | none |
Nonparametric Bayesian Deep Networks with Local Competition
Title | Nonparametric Bayesian Deep Networks with Local Competition |
Authors | Konstantinos P. Panousis, Sotirios Chatzis, Sergios Theodoridis |
Abstract | The aim of this work is to enable inference of deep networks that retain high accuracy for the least possible model complexity, with the latter deduced from the data during inference. To this end, we revisit deep networks that comprise competing linear units, as opposed to nonlinear units that do not entail any form of (local) competition. In this context, our main technical innovation consists in an inferential setup that leverages solid arguments from Bayesian nonparametrics. We infer both the needed set of connections or locally competing sets of units, as well as the required floating-point precision for storing the network parameters. Specifically, we introduce auxiliary discrete latent variables representing which initial network components are actually needed for modeling the data at hand, and perform Bayesian inference over them by imposing appropriate stick-breaking priors. As we experimentally show using benchmark datasets, our approach yields networks with less computational footprint than the state-of-the-art, and with no compromises in predictive accuracy. |
Tasks | Bayesian Inference |
Published | 2018-05-19 |
URL | https://arxiv.org/abs/1805.07624v4 |
https://arxiv.org/pdf/1805.07624v4.pdf | |
PWC | https://paperswithcode.com/paper/nonparametric-bayesian-deep-networks-with |
Repo | https://github.com/konpanousis/SB-LWTA |
Framework | tf |