July 29, 2019

3287 words 16 mins read

Paper Group AWR 78

Statistics of Deep Generated Images. P-Tree Programming. Automatic Mapping of NES Games with Mappy. Joint Deep Modeling of Users and Items Using Reviews for Recommendation. Empower Sequence Labeling with Task-Aware Neural Language Model. Lenient Multi-Agent Deep Reinforcement Learning. Attentive Generative Adversarial Network for Raindrop Removal f …

Statistics of Deep Generated Images


Title	Statistics of Deep Generated Images
Authors	Yu Zeng, Huchuan Lu, Ali Borji
Abstract	Here, we explore the low-level statistics of images generated by state-of-the-art deep generative models. First, Variational auto-encoder (VAE~\cite{kingma2013auto}), Wasserstein generative adversarial network (WGAN~\cite{arjovsky2017wasserstein}) and deep convolutional generative adversarial network (DCGAN~\cite{radford2015unsupervised}) are trained on the ImageNet dataset and a large set of cartoon frames from animations. Then, for images generated by these models as well as natural scenes and cartoons, statistics including mean power spectrum, the number of connected components in a given image area, distribution of random filter responses, and contrast distribution are computed. Our analyses on training images support current findings on scale invariance, non-Gaussianity, and Weibull contrast distribution of natural scenes. We find that although similar results hold over cartoon images, there is still a significant difference between statistics of natural scenes and images generated by VAE, DCGAN and WGAN models. In particular, generated images do not have scale invariant mean power spectrum magnitude, which indicates existence of extra structures in these images. Inspecting how well the statistics of deep generated images match the known statistical properties of natural images, such as scale invariance, non-Gaussianity, and Weibull contrast distribution, can a) reveal the degree to which deep learning models capture the essence of the natural scenes, b) provide a new dimension to evaluate models, and c) allow possible improvement of image generative models (e.g., via defining new loss functions).
Tasks
Published	2017-08-09
URL	https://arxiv.org/abs/1708.02688v5
PDF	https://arxiv.org/pdf/1708.02688v5.pdf
PWC	https://paperswithcode.com/paper/statistics-of-deep-generated-images
Repo	https://github.com/zengxianyu/generate
Framework	pytorch

P-Tree Programming


Title	P-Tree Programming
Authors	Christian Oesch
Abstract	We propose a novel method for automatic program synthesis. P-Tree Programming represents the program search space through a single probabilistic prototype tree. From this prototype tree we form program instances which we evaluate on a given problem. The error values from the evaluations are propagated through the prototype tree. We use them to update the probability distributions that determine the symbol choices of further instances. The iterative method is applied to several symbolic regression benchmarks from the literature. It outperforms standard Genetic Programming to a large extend. Furthermore, it relies on a concise set of parameters which are held constant for all problems. The algorithm can be employed for most of the typical computational intelligence tasks such as classification, automatic program induction, and symbolic regression.
Tasks	Program Synthesis
Published	2017-07-12
URL	http://arxiv.org/abs/1707.03744v1
PDF	http://arxiv.org/pdf/1707.03744v1.pdf
PWC	https://paperswithcode.com/paper/p-tree-programming
Repo	https://github.com/coesch/ptree
Framework	none

Automatic Mapping of NES Games with Mappy


Title	Automatic Mapping of NES Games with Mappy
Authors	Joseph C. Osborn, Adam Summerville, Michael Mateas
Abstract	Game maps are useful for human players, general-game-playing agents, and data-driven procedural content generation. These maps are generally made by hand-assembling manually-created screenshots of game levels. Besides being tedious and error-prone, this approach requires additional effort for each new game and level to be mapped. The results can still be hard for humans or computational systems to make use of, privileging visual appearance over semantic information. We describe a software system, Mappy, that produces a good approximation of a linked map of rooms given a Nintendo Entertainment System game program and a sequence of button inputs exploring its world. In addition to visual maps, Mappy outputs grids of tiles (and how they change over time), positions of non-tile objects, clusters of similar rooms that might in fact be the same room, and a set of links between these rooms. We believe this is a necessary step towards developing larger corpora of high-quality semantically-annotated maps for PCG via machine learning and other applications.
Tasks
Published	2017-07-12
URL	http://arxiv.org/abs/1707.03908v1
PDF	http://arxiv.org/pdf/1707.03908v1.pdf
PWC	https://paperswithcode.com/paper/automatic-mapping-of-nes-games-with-mappy
Repo	https://github.com/JoeOsborn/mechlearn
Framework	none

Joint Deep Modeling of Users and Items Using Reviews for Recommendation


Title	Joint Deep Modeling of Users and Items Using Reviews for Recommendation
Authors	Lei Zheng, Vahid Noroozi, Philip S. Yu
Abstract	A large amount of information exists in reviews written by users. This source of information has been ignored by most of the current recommender systems while it can potentially alleviate the sparsity problem and improve the quality of recommendations. In this paper, we present a deep model to learn item properties and user behaviors jointly from review text. The proposed model, named Deep Cooperative Neural Networks (DeepCoNN), consists of two parallel neural networks coupled in the last layers. One of the networks focuses on learning user behaviors exploiting reviews written by the user, and the other one learns item properties from the reviews written for the item. A shared layer is introduced on the top to couple these two networks together. The shared layer enables latent factors learned for users and items to interact with each other in a manner similar to factorization machine techniques. Experimental results demonstrate that DeepCoNN significantly outperforms all baseline recommender systems on a variety of datasets.
Tasks	Recommendation Systems
Published	2017-01-17
URL	http://arxiv.org/abs/1701.04783v1
PDF	http://arxiv.org/pdf/1701.04783v1.pdf
PWC	https://paperswithcode.com/paper/joint-deep-modeling-of-users-and-items-using
Repo	https://github.com/HuijunZhao/recommendation-system
Framework	none

Empower Sequence Labeling with Task-Aware Neural Language Model


Title	Empower Sequence Labeling with Task-Aware Neural Language Model
Authors	Liyuan Liu, Jingbo Shang, Frank F. Xu, Xiang Ren, Huan Gui, Jian Peng, Jiawei Han
Abstract	Linguistic sequence labeling is a general modeling approach that encompasses a variety of problems, such as part-of-speech tagging and named entity recognition. Recent advances in neural networks (NNs) make it possible to build reliable models without handcrafted features. However, in many cases, it is hard to obtain sufficient annotations to train these models. In this study, we develop a novel neural framework to extract abundant knowledge hidden in raw texts to empower the sequence labeling task. Besides word-level knowledge contained in pre-trained word embeddings, character-aware neural language models are incorporated to extract character-level knowledge. Transfer learning techniques are further adopted to mediate different components and guide the language model towards the key knowledge. Comparing to previous methods, these task-specific knowledge allows us to adopt a more concise model and conduct more efficient training. Different from most transfer learning methods, the proposed framework does not rely on any additional supervision. It extracts knowledge from self-contained order information of training sequences. Extensive experiments on benchmark datasets demonstrate the effectiveness of leveraging character-level knowledge and the efficiency of co-training. For example, on the CoNLL03 NER task, model training completes in about 6 hours on a single GPU, reaching F1 score of 91.71$\pm$0.10 without using any extra annotation.
Tasks	Language Modelling, Named Entity Recognition, Part-Of-Speech Tagging, Transfer Learning, Word Embeddings
Published	2017-09-13
URL	http://arxiv.org/abs/1709.04109v4
PDF	http://arxiv.org/pdf/1709.04109v4.pdf
PWC	https://paperswithcode.com/paper/empower-sequence-labeling-with-task-aware
Repo	https://github.com/LiyuanLucasLiu/LM-LSTM-CRF
Framework	pytorch

Lenient Multi-Agent Deep Reinforcement Learning


Title	Lenient Multi-Agent Deep Reinforcement Learning
Authors	Gregory Palmer, Karl Tuyls, Daan Bloembergen, Rahul Savani
Abstract	Much of the success of single agent deep reinforcement learning (DRL) in recent years can be attributed to the use of experience replay memories (ERM), which allow Deep Q-Networks (DQNs) to be trained efficiently through sampling stored state transitions. However, care is required when using ERMs for multi-agent deep reinforcement learning (MA-DRL), as stored transitions can become outdated because agents update their policies in parallel [11]. In this work we apply leniency [23] to MA-DRL. Lenient agents map state-action pairs to decaying temperature values that control the amount of leniency applied towards negative policy updates that are sampled from the ERM. This introduces optimism in the value-function update, and has been shown to facilitate cooperation in tabular fully-cooperative multi-agent reinforcement learning problems. We evaluate our Lenient-DQN (LDQN) empirically against the related Hysteretic-DQN (HDQN) algorithm [22] as well as a modified version we call scheduled-HDQN, that uses average reward learning near terminal states. Evaluations take place in extended variations of the Coordinated Multi-Agent Object Transportation Problem (CMOTP) [8] which include fully-cooperative sub-tasks and stochastic rewards. We find that LDQN agents are more likely to converge to the optimal policy in a stochastic reward CMOTP compared to standard and scheduled-HDQN agents.
Tasks	Multi-agent Reinforcement Learning
Published	2017-07-14
URL	http://arxiv.org/abs/1707.04402v2
PDF	http://arxiv.org/pdf/1707.04402v2.pdf
PWC	https://paperswithcode.com/paper/lenient-multi-agent-deep-reinforcement
Repo	https://github.com/gjp1203/nui_in_madrl
Framework	none

Attentive Generative Adversarial Network for Raindrop Removal from a Single Image


Title	Attentive Generative Adversarial Network for Raindrop Removal from a Single Image
Authors	Rui Qian, Robby T. Tan, Wenhan Yang, Jiajun Su, Jiaying Liu
Abstract	Raindrops adhered to a glass window or camera lens can severely hamper the visibility of a background scene and degrade an image considerably. In this paper, we address the problem by visually removing raindrops, and thus transforming a raindrop degraded image into a clean one. The problem is intractable, since first the regions occluded by raindrops are not given. Second, the information about the background scene of the occluded regions is completely lost for most part. To resolve the problem, we apply an attentive generative network using adversarial training. Our main idea is to inject visual attention into both the generative and discriminative networks. During the training, our visual attention learns about raindrop regions and their surroundings. Hence, by injecting this information, the generative network will pay more attention to the raindrop regions and the surrounding structures, and the discriminative network will be able to assess the local consistency of the restored regions. This injection of visual attention to both generative and discriminative networks is the main contribution of this paper. Our experiments show the effectiveness of our approach, which outperforms the state of the art methods quantitatively and qualitatively.
Tasks	Rain Removal
Published	2017-11-28
URL	http://arxiv.org/abs/1711.10098v4
PDF	http://arxiv.org/pdf/1711.10098v4.pdf
PWC	https://paperswithcode.com/paper/attentive-generative-adversarial-network-for
Repo	https://github.com/rui1996/DeRaindrop
Framework	pytorch

Image De-raining Using a Conditional Generative Adversarial Network


Title	Image De-raining Using a Conditional Generative Adversarial Network
Authors	He Zhang, Vishwanath Sindagi, Vishal M. Patel
Abstract	Severe weather conditions such as rain and snow adversely affect the visual quality of images captured under such conditions thus rendering them useless for further usage and sharing. In addition, such degraded images drastically affect performance of vision systems. Hence, it is important to solve the problem of single image de-raining/de-snowing. However, this is a difficult problem to solve due to its inherent ill-posed nature. Existing approaches attempt to introduce prior information to convert it into a well-posed problem. In this paper, we investigate a new point of view in addressing the single image de-raining problem. Instead of focusing only on deciding what is a good prior or a good framework to achieve good quantitative and qualitative performance, we also ensure that the de-rained image itself does not degrade the performance of a given computer vision algorithm such as detection and classification. In other words, the de-rained result should be indistinguishable from its corresponding clear image to a given discriminator. This criterion can be directly incorporated into the optimization framework by using the recently introduced conditional generative adversarial networks (GANs). To minimize artifacts introduced by GANs and ensure better visual quality, a new refined loss function is introduced. Based on this, we propose a novel single image de-raining method called Image De-raining Conditional General Adversarial Network (ID-CGAN), which considers quantitative, visual and also discriminative performance into the objective function. Experiments evaluated on synthetic images and real images show that the proposed method outperforms many recent state-of-the-art single image de-raining methods in terms of quantitative and visual performance.
Tasks	Rain Removal
Published	2017-01-21
URL	https://arxiv.org/abs/1701.05957v4
PDF	https://arxiv.org/pdf/1701.05957v4.pdf
PWC	https://paperswithcode.com/paper/image-de-raining-using-a-conditional
Repo	https://github.com/yoyotv/Image-derain-via-CGAN
Framework	tf

Single Classifier-based Passive System for Source Printer Classification using Local Texture Features


Title	Single Classifier-based Passive System for Source Printer Classification using Local Texture Features
Authors	Sharad Joshi, Nitin Khanna
Abstract	An important aspect of examining printed documents for potential forgeries and copyright infringement is the identification of source printer as it can be helpful for ascertaining the leak and detecting forged documents. This paper proposes a system for classification of source printer from scanned images of printed documents using all the printed letters simultaneously. This system uses local texture patterns based features and a single classifier for classifying all the printed letters. Letters are extracted from scanned images using connected component analysis followed by morphological filtering without the need of using an OCR. Each letter is sub-divided into a flat region and an edge region, and local tetra patterns are estimated separately for these two regions. A strategically constructed pooling technique is used to extract the final feature vectors. The proposed method has been tested on both a publicly available dataset of 10 printers and a new dataset of 18 printers scanned at a resolution of 600 dpi as well as 300 dpi printed in four different fonts. The results indicate shape independence property in the proposed method as using a single classifier it outperforms existing handcrafted feature-based methods and needs much smaller number of training pages by using all the printed letters.
Tasks	Optical Character Recognition
Published	2017-06-22
URL	http://arxiv.org/abs/1706.07422v1
PDF	http://arxiv.org/pdf/1706.07422v1.pdf
PWC	https://paperswithcode.com/paper/single-classifier-based-passive-system-for
Repo	https://github.com/Hedgehogues/HoChiMinh
Framework	none

A Robust Adaptive Stochastic Gradient Method for Deep Learning


Title	A Robust Adaptive Stochastic Gradient Method for Deep Learning
Authors	Caglar Gulcehre, Jose Sotelo, Marcin Moczulski, Yoshua Bengio
Abstract	Stochastic gradient algorithms are the main focus of large-scale optimization problems and led to important successes in the recent advancement of the deep learning algorithms. The convergence of SGD depends on the careful choice of learning rate and the amount of the noise in stochastic estimates of the gradients. In this paper, we propose an adaptive learning rate algorithm, which utilizes stochastic curvature information of the loss function for automatically tuning the learning rates. The information about the element-wise curvature of the loss function is estimated from the local statistics of the stochastic first order gradients. We further propose a new variance reduction technique to speed up the convergence. In our experiments with deep neural networks, we obtained better performance compared to the popular stochastic gradient algorithms.
Tasks
Published	2017-03-02
URL	http://arxiv.org/abs/1703.00788v1
PDF	http://arxiv.org/pdf/1703.00788v1.pdf
PWC	https://paperswithcode.com/paper/a-robust-adaptive-stochastic-gradient-method
Repo	https://github.com/sotelo/scribe
Framework	none

Motif-based Convolutional Neural Network on Graphs


Title	Motif-based Convolutional Neural Network on Graphs
Authors	Aravind Sankar, Xinyang Zhang, Kevin Chen-Chuan Chang
Abstract	This paper introduces a generalization of Convolutional Neural Networks (CNNs) to graphs with irregular linkage structures, especially heterogeneous graphs with typed nodes and schemas. We propose a novel spatial convolution operation to model the key properties of local connectivity and translation invariance, using high-order connection patterns or motifs. We develop a novel deep architecture Motif-CNN that employs an attention model to combine the features extracted from multiple patterns, thus effectively capturing high-order structural and feature information. Our experiments on semi-supervised node classification on real-world social networks and multiple representative heterogeneous graph datasets indicate significant gains of 6-21% over existing graph CNNs and other state-of-the-art techniques.
Tasks	Node Classification
Published	2017-11-15
URL	https://arxiv.org/abs/1711.05697v4
PDF	https://arxiv.org/pdf/1711.05697v4.pdf
PWC	https://paperswithcode.com/paper/motif-based-convolutional-neural-network-on
Repo	https://github.com/aravindsankar28/Meta-GNN
Framework	tf

DiracNets: Training Very Deep Neural Networks Without Skip-Connections


Title	DiracNets: Training Very Deep Neural Networks Without Skip-Connections
Authors	Sergey Zagoruyko, Nikos Komodakis
Abstract	Deep neural networks with skip-connections, such as ResNet, show excellent performance in various image classification benchmarks. It is though observed that the initial motivation behind them - training deeper networks - does not actually hold true, and the benefits come from increased capacity, rather than from depth. Motivated by this, and inspired from ResNet, we propose a simple Dirac weight parameterization, which allows us to train very deep plain networks without explicit skip-connections, and achieve nearly the same performance. This parameterization has a minor computational cost at training time and no cost at all at inference, as both Dirac parameterization and batch normalization can be folded into convolutional filters, so that network becomes a simple chain of convolution-ReLU pairs. We are able to match ResNet-1001 accuracy on CIFAR-10 with 28-layer wider plain DiracNet, and closely match ResNets on ImageNet. Our parameterization also mostly eliminates the need of careful initialization in residual and non-residual networks. The code and models for our experiments are available at https://github.com/szagoruyko/diracnets
Tasks	Image Classification
Published	2017-06-01
URL	http://arxiv.org/abs/1706.00388v2
PDF	http://arxiv.org/pdf/1706.00388v2.pdf
PWC	https://paperswithcode.com/paper/diracnets-training-very-deep-neural-networks
Repo	https://github.com/escorciav/roi_pooling
Framework	pytorch

Semantic speech retrieval with a visually grounded model of untranscribed speech


Title	Semantic speech retrieval with a visually grounded model of untranscribed speech
Authors	Herman Kamper, Gregory Shakhnarovich, Karen Livescu
Abstract	There is growing interest in models that can learn from unlabelled speech paired with visual context. This setting is relevant for low-resource speech processing, robotics, and human language acquisition research. Here we study how a visually grounded speech model, trained on images of scenes paired with spoken captions, captures aspects of semantics. We use an external image tagger to generate soft text labels from images, which serve as targets for a neural model that maps untranscribed speech to (semantic) keyword labels. We introduce a newly collected data set of human semantic relevance judgements and an associated task, semantic speech retrieval, where the goal is to search for spoken utterances that are semantically relevant to a given text query. Without seeing any text, the model trained on parallel speech and images achieves a precision of almost 60% on its top ten semantic retrievals. Compared to a supervised model trained on transcriptions, our model matches human judgements better by some measures, especially in retrieving non-verbatim semantic matches. We perform an extensive analysis of the model and its resulting representations.
Tasks	Language Acquisition
Published	2017-10-05
URL	http://arxiv.org/abs/1710.01949v2
PDF	http://arxiv.org/pdf/1710.01949v2.pdf
PWC	https://paperswithcode.com/paper/semantic-speech-retrieval-with-a-visually
Repo	https://github.com/kamperh/semantic_flickraudio
Framework	none

Predicting and Explaining Human Semantic Search in a Cognitive Model


Title	Predicting and Explaining Human Semantic Search in a Cognitive Model
Authors	Filip Miscevic, Aida Nematzadeh, Suzanne Stevenson
Abstract	Recent work has attempted to characterize the structure of semantic memory and the search algorithms which, together, best approximate human patterns of search revealed in a semantic fluency task. There are a number of models that seek to capture semantic search processes over networks, but they vary in the cognitive plausibility of their implementation. Existing work has also neglected to consider the constraints that the incremental process of language acquisition must place on the structure of semantic memory. Here we present a model that incrementally updates a semantic network, with limited computational steps, and replicates many patterns found in human semantic fluency using a simple random walk. We also perform thorough analyses showing that a combination of both structural and semantic features are correlated with human performance patterns.
Tasks	Language Acquisition
Published	2017-11-29
URL	http://arxiv.org/abs/1711.11125v1
PDF	http://arxiv.org/pdf/1711.11125v1.pdf
PWC	https://paperswithcode.com/paper/predicting-and-explaining-human-semantic
Repo	https://github.com/mkduer/semantic-fluency-nn
Framework	none

Convolutional Networks with Adaptive Inference Graphs


Title	Convolutional Networks with Adaptive Inference Graphs
Authors	Andreas Veit, Serge Belongie
Abstract	Do convolutional networks really need a fixed feed-forward structure? What if, after identifying the high-level concept of an image, a network could move directly to a layer that can distinguish fine-grained differences? Currently, a network would first need to execute sometimes hundreds of intermediate layers that specialize in unrelated aspects. Ideally, the more a network already knows about an image, the better it should be at deciding which layer to compute next. In this work, we propose convolutional networks with adaptive inference graphs (ConvNet-AIG) that adaptively define their network topology conditioned on the input image. Following a high-level structure similar to residual networks (ResNets), ConvNet-AIG decides for each input image on the fly which layers are needed. In experiments on ImageNet we show that ConvNet-AIG learns distinct inference graphs for different categories. Both ConvNet-AIG with 50 and 101 layers outperform their ResNet counterpart, while using 20% and 33% less computations respectively. By grouping parameters into layers for related classes and only executing relevant layers, ConvNet-AIG improves both efficiency and overall classification quality. Lastly, we also study the effect of adaptive inference graphs on the susceptibility towards adversarial examples. We observe that ConvNet-AIG shows a higher robustness than ResNets, complementing other known defense mechanisms.
Tasks
Published	2017-11-30
URL	http://arxiv.org/abs/1711.11503v2
PDF	http://arxiv.org/pdf/1711.11503v2.pdf
PWC	https://paperswithcode.com/paper/convolutional-networks-with-adaptive
Repo	https://github.com/rtanno21609/AdaptiveNeuralTrees
Framework	pytorch