October 16, 2019

2914 words 14 mins read

Paper Group ANR 1016

Improved Breast Mass Segmentation in Mammograms with Conditional Residual U-net. Chest X-ray Inpainting with Deep Generative Models. Supporting Very Large Models using Automatic Dataflow Graph Partitioning. Bayesian Inference of Self-intention Attributed by Observer. Sets of autoencoders with shared latent spaces. Generating Diverse and Accurate Vi …

Improved Breast Mass Segmentation in Mammograms with Conditional Residual U-net


Title	Improved Breast Mass Segmentation in Mammograms with Conditional Residual U-net
Authors	Heyi Li, Dongdong Chen, Bill Nailon, Mike Davies, Dave Laurenson
Abstract	We explore the use of deep learning for breast mass segmentation in mammograms. By integrating the merits of residual learning and probabilistic graphical modelling with standard U-Net, we propose a new deep network, Conditional Residual U-Net (CRU-Net), to improve the U-Net segmentation performance. Benefiting from the advantage of probabilistic graphical modelling in the pixel-level labelling, and the structure insights of a deep residual network in the feature extraction, the CRU-Net provides excellent mass segmentation performance. Evaluations based on INbreast and DDSM-BCRP datasets demonstrate that the CRU-Net achieves the best mass segmentation performance compared to the state-of-art methodologies. Moreover, neither tedious pre-processing nor post-processing techniques are not required in our algorithm.
Tasks
Published	2018-08-27
URL	http://arxiv.org/abs/1808.08885v1
PDF	http://arxiv.org/pdf/1808.08885v1.pdf
PWC	https://paperswithcode.com/paper/improved-breast-mass-segmentation-in
Repo
Framework

Chest X-ray Inpainting with Deep Generative Models


Title	Chest X-ray Inpainting with Deep Generative Models
Authors	Ecem Sogancioglu, Shi Hu, Davide Belli, Bram van Ginneken
Abstract	Generative adversarial networks have been successfully applied to inpainting in natural images. However, the current state-of-the-art models have not yet been widely adopted in the medical imaging domain. In this paper, we investigate the performance of three recently published deep learning based inpainting models: context encoders, semantic image inpainting, and the contextual attention model, applied to chest x-rays, as the chest exam is the most commonly performed radiological procedure. We train these generative models on 1.2M 128 $\times$ 128 patches from 60K healthy x-rays, and learn to predict the center 64 $\times$ 64 region in each patch. We test the models on both the healthy and abnormal radiographs. We evaluate the results by visual inspection and comparing the PSNR scores. The outputs of the models are in most cases highly realistic. We show that the methods have potential to enhance and detect abnormalities. In addition, we perform a 2AFC observer study and show that an experienced human observer performs poorly in detecting inpainted regions, particularly those generated by the contextual attention model.
Tasks	Image Inpainting
Published	2018-08-29
URL	http://arxiv.org/abs/1809.01471v1
PDF	http://arxiv.org/pdf/1809.01471v1.pdf
PWC	https://paperswithcode.com/paper/chest-x-ray-inpainting-with-deep-generative
Repo
Framework

Supporting Very Large Models using Automatic Dataflow Graph Partitioning


Title	Supporting Very Large Models using Automatic Dataflow Graph Partitioning
Authors	Minjie Wang, Chien-chin Huang, Jinyang Li
Abstract	This paper presents Tofu, a system that partitions very large DNN models across multiple GPU devices to reduce per-GPU memory footprint. Tofu is designed to partition a dataflow graph of fine-grained tensor operators in order to work transparently with a general-purpose deep learning platform like MXNet. In order to automatically partition each operator, we propose to describe the semantics of an operator in a simple language which represents tensors as lambda functions mapping from tensor coordinates to values. To optimally partition different operators in a dataflow graph, Tofu uses a recursive search algorithm that minimizes the total communication cost. Our experiments on an 8-GPU machine show that Tofu enables the training of very large CNN and RNN models. It also achieves 25% - 400% speedup over alternative approaches to train very large models.
Tasks	graph partitioning
Published	2018-07-24
URL	http://arxiv.org/abs/1807.08887v2
PDF	http://arxiv.org/pdf/1807.08887v2.pdf
PWC	https://paperswithcode.com/paper/supporting-very-large-models-using-automatic
Repo
Framework

Bayesian Inference of Self-intention Attributed by Observer


Title	Bayesian Inference of Self-intention Attributed by Observer
Authors	Yosuke Fukuchi, Masahiko Osawa, Hiroshi Yamakawa, Tatsuji Takahashi, Michita Imai
Abstract	Most of agents that learn policy for tasks with reinforcement learning (RL) lack the ability to communicate with people, which makes human-agent collaboration challenging. We believe that, in order for RL agents to comprehend utterances from human colleagues, RL agents must infer the mental states that people attribute to them because people sometimes infer an interlocutor’s mental states and communicate on the basis of this mental inference. This paper proposes PublicSelf model, which is a model of a person who infers how the person’s own behavior appears to their colleagues. We implemented the PublicSelf model for an RL agent in a simulated environment and examined the inference of the model by comparing it with people’s judgment. The results showed that the agent’s intention that people attributed to the agent’s movement was correctly inferred by the model in scenes where people could find certain intentionality from the agent’s behavior.
Tasks	Bayesian Inference
Published	2018-10-12
URL	http://arxiv.org/abs/1810.05564v1
PDF	http://arxiv.org/pdf/1810.05564v1.pdf
PWC	https://paperswithcode.com/paper/bayesian-inference-of-self-intention
Repo
Framework

Sets of autoencoders with shared latent spaces


Title	Sets of autoencoders with shared latent spaces
Authors	Vasily Morzhakov
Abstract	Autoencoders receive latent models of input data. It was shown in recent works that they also estimate probability density functions of the input. This fact makes using the Bayesian decision theory possible. If we obtain latent models of input data for each class or for some points in the space of parameters in a parameter estimation task, we are able to estimate likelihood functions for those classes or points in parameter space. We show how the set of autoencoders solves the recognition problem. Each autoencoder describes its own model or context, a latent vector that presents input data in the latent space may be called treatment in its context. Sharing latent spaces of autoencoders gives a very important property that is the ability to separate treatment and context where the input information is treated through the set of autoencoders. There are two remarkable and most valuable results of this work: a mechanism that shows a possible way of forming abstract concepts and a way of reducing dataset’s size during training. These results are confirmed by tests presented in the article.
Tasks
Published	2018-11-06
URL	http://arxiv.org/abs/1811.02373v1
PDF	http://arxiv.org/pdf/1811.02373v1.pdf
PWC	https://paperswithcode.com/paper/sets-of-autoencoders-with-shared-latent
Repo
Framework

Generating Diverse and Accurate Visual Captions by Comparative Adversarial Learning


Title	Generating Diverse and Accurate Visual Captions by Comparative Adversarial Learning
Authors	Dianqi Li, Qiuyuan Huang, Xiaodong He, Lei Zhang, Ming-Ting Sun
Abstract	We study how to generate captions that are not only accurate in describing an image but also discriminative across different images. The problem is both fundamental and interesting, as most machine-generated captions, despite phenomenal research progresses in the past several years, are expressed in a very monotonic and featureless format. While such captions are normally accurate, they often lack important characteristics in human languages - distinctiveness for each caption and diversity for different images. To address this problem, we propose a novel conditional generative adversarial network for generating diverse captions across images. Instead of estimating the quality of a caption solely on one image, the proposed comparative adversarial learning framework better assesses the quality of captions by comparing a set of captions within the image-caption joint space. By contrasting with human-written captions and image-mismatched captions, the caption generator effectively exploits the inherent characteristics of human languages, and generates more discriminative captions. We show that our proposed network is capable of producing accurate and diverse captions across images.
Tasks
Published	2018-04-03
URL	http://arxiv.org/abs/1804.00861v3
PDF	http://arxiv.org/pdf/1804.00861v3.pdf
PWC	https://paperswithcode.com/paper/generating-diverse-and-accurate-visual
Repo
Framework

OMNIA Faster R-CNN: Detection in the wild through dataset merging and soft distillation


Title	OMNIA Faster R-CNN: Detection in the wild through dataset merging and soft distillation
Authors	Alexandre Rame, Emilien Garreau, Hedi Ben-Younes, Charles Ollion
Abstract	Object detectors tend to perform poorly in new or open domains, and require exhaustive yet costly annotations from fully labeled datasets. We aim at benefiting from several datasets with different categories but without additional labelling, not only to increase the number of categories detected, but also to take advantage from transfer learning and to enhance domain independence. Our dataset merging procedure starts with training several initial Faster R-CNN on the different datasets while considering the complementary datasets’ images for domain adaptation. Similarly to self-training methods, the predictions of these initial detectors mitigate the missing annotations on the complementary datasets. The final OMNIA Faster R-CNN is trained with all categories on the union of the datasets enriched by predictions. The joint training handles unsafe targets with a new classification loss called SoftSig in a softly supervised way. Experimental results show that in the case of fashion detection for images in the wild, merging Modanet with COCO increases the final performance from 45.5% to 57.4% in mAP. Applying our soft distillation to the task of detection with domain shift between GTA and Cityscapes enables to beat the state-of-the-art by 5.3 points. Our methodology could unlock object detection for real-world applications without immense datasets.
Tasks	Domain Adaptation, Object Detection, Transfer Learning
Published	2018-12-06
URL	http://arxiv.org/abs/1812.02611v2
PDF	http://arxiv.org/pdf/1812.02611v2.pdf
PWC	https://paperswithcode.com/paper/omnia-faster-r-cnn-detection-in-the-wild
Repo
Framework

Quasi-Dilemmas for Artificial Moral Agents


Title	Quasi-Dilemmas for Artificial Moral Agents
Authors	Daniel Kasenberg, Vasanth Sarathy, Thomas Arnold, Matthias Scheutz, Tom Williams
Abstract	In this paper we describe moral quasi-dilemmas (MQDs): situations similar to moral dilemmas, but in which an agent is unsure whether exploring the plan space or the world may reveal a course of action that satisfies all moral requirements. We argue that artificial moral agents (AMAs) should be built to handle MQDs (in particular, by exploring the plan space rather than immediately accepting the inevitability of the moral dilemma), and that MQDs may be useful for evaluating AMA architectures.
Tasks
Published	2018-07-06
URL	http://arxiv.org/abs/1807.02572v1
PDF	http://arxiv.org/pdf/1807.02572v1.pdf
PWC	https://paperswithcode.com/paper/quasi-dilemmas-for-artificial-moral-agents
Repo
Framework

How to Combine Tree-Search Methods in Reinforcement Learning


Title	How to Combine Tree-Search Methods in Reinforcement Learning
Authors	Yonathan Efroni, Gal Dalal, Bruno Scherrer, Shie Mannor
Abstract	Finite-horizon lookahead policies are abundantly used in Reinforcement Learning and demonstrate impressive empirical success. Usually, the lookahead policies are implemented with specific planning methods such as Monte Carlo Tree Search (e.g. in AlphaZero). Referring to the planning problem as tree search, a reasonable practice in these implementations is to back up the value only at the leaves while the information obtained at the root is not leveraged other than for updating the policy. Here, we question the potency of this approach. Namely, the latter procedure is non-contractive in general, and its convergence is not guaranteed. Our proposed enhancement is straightforward and simple: use the return from the optimal tree path to back up the values at the descendants of the root. This leads to a $\gamma^h$-contracting procedure, where $\gamma$ is the discount factor and $h$ is the tree depth. To establish our results, we first introduce a notion called \emph{multiple-step greedy consistency}. We then provide convergence rates for two algorithmic instantiations of the above enhancement in the presence of noise injected to both the tree search stage and value estimation stage.
Tasks
Published	2018-09-06
URL	http://arxiv.org/abs/1809.01843v2
PDF	http://arxiv.org/pdf/1809.01843v2.pdf
PWC	https://paperswithcode.com/paper/how-to-combine-tree-search-methods-in
Repo
Framework

Joint Nonparametric Precision Matrix Estimation with Confounding


Title	Joint Nonparametric Precision Matrix Estimation with Confounding
Authors	Sinong Geng, Mladen Kolar, Oluwasanmi Koyejo
Abstract	We consider the problem of precision matrix estimation where, due to extraneous confounding of the underlying precision matrix, the data are independent but not identically distributed. While such confounding occurs in many scientific problems, our approach is inspired by recent neuroscientific research suggesting that brain function, as measured using functional magnetic resonance imagine (fMRI), is susceptible to confounding by physiological noise such as breathing and subject motion. Following the scientific motivation, we propose a graphical model, which in turn motivates a joint nonparametric estimator. We provide theoretical guarantees for the consistency and the convergence rate of the proposed estimator. In addition, we demonstrate that the optimization of the proposed estimator can be transformed into a series of linear programming problems, and thus be efficiently solved in parallel. Empirical results are presented using simulated and real brain imaging data, which suggest that our approach improves precision matrix estimation, as compared to baselines, when confounding is present.
Tasks
Published	2018-10-16
URL	https://arxiv.org/abs/1810.07147v2
PDF	https://arxiv.org/pdf/1810.07147v2.pdf
PWC	https://paperswithcode.com/paper/joint-nonparametric-precision-matrix
Repo
Framework

From Text to Topics in Healthcare Records: An Unsupervised Graph Partitioning Methodology


Title	From Text to Topics in Healthcare Records: An Unsupervised Graph Partitioning Methodology
Authors	M. Tarik Altuncu, Erik Mayer, Sophia N. Yaliraki, Mauricio Barahona
Abstract	Electronic Healthcare Records contain large volumes of unstructured data, including extensive free text. Yet this source of detailed information often remains under-used because of a lack of methodologies to extract interpretable content in a timely manner. Here we apply network-theoretical tools to analyse free text in Hospital Patient Incident reports from the National Health Service, to find clusters of documents with similar content in an unsupervised manner at different levels of resolution. We combine deep neural network paragraph vector text-embedding with multiscale Markov Stability community detection applied to a sparsified similarity graph of document vectors, and showcase the approach on incident reports from Imperial College Healthcare NHS Trust, London. The multiscale community structure reveals different levels of meaning in the topics of the dataset, as shown by descriptive terms extracted from the clusters of records. We also compare a posteriori against hand-coded categories assigned by healthcare personnel, and show that our approach outperforms LDA-based models. Our content clusters exhibit good correspondence with two levels of hand-coded categories, yet they also provide further medical detail in certain areas and reveal complementary descriptors of incidents beyond the external classification taxonomy.
Tasks	Community Detection, graph partitioning
Published	2018-07-07
URL	http://arxiv.org/abs/1807.02599v1
PDF	http://arxiv.org/pdf/1807.02599v1.pdf
PWC	https://paperswithcode.com/paper/from-text-to-topics-in-healthcare-records-an
Repo
Framework

Learning Privacy Preserving Encodings through Adversarial Training


Title	Learning Privacy Preserving Encodings through Adversarial Training
Authors	Francesco Pittaluga, Sanjeev J. Koppal, Ayan Chakrabarti
Abstract	We present a framework to learn privacy-preserving encodings of images that inhibit inference of chosen private attributes, while allowing recovery of other desirable information. Rather than simply inhibiting a given fixed pre-trained estimator, our goal is that an estimator be unable to learn to accurately predict the private attributes even with knowledge of the encoding function. We use a natural adversarial optimization-based formulation for this—training the encoding function against a classifier for the private attribute, with both modeled as deep neural networks. The key contribution of our work is a stable and convergent optimization approach that is successful at learning an encoder with our desired properties—maintaining utility while inhibiting inference of private attributes, not just within the adversarial optimization, but also by classifiers that are trained after the encoder is fixed. We adopt a rigorous experimental protocol for verification wherein classifiers are trained exhaustively till saturation on the fixed encoders. We evaluate our approach on tasks of real-world complexity—learning high-dimensional encodings that inhibit detection of different scene categories—and find that it yields encoders that are resilient at maintaining privacy.
Tasks
Published	2018-02-14
URL	http://arxiv.org/abs/1802.05214v3
PDF	http://arxiv.org/pdf/1802.05214v3.pdf
PWC	https://paperswithcode.com/paper/learning-privacy-preserving-encodings-through
Repo
Framework

Neural Chinese Word Segmentation with Dictionary Knowledge


Title	Neural Chinese Word Segmentation with Dictionary Knowledge
Authors	Junxin Liu, Fangzhao Wu, Chuhan Wu, Yongfeng Huang, Xing Xie
Abstract	Chinese word segmentation (CWS) is an important task for Chinese NLP. Recently, many neural network based methods have been proposed for CWS. However, these methods require a large number of labeled sentences for model training, and usually cannot utilize the useful information in Chinese dictionary. In this paper, we propose two methods to exploit the dictionary information for CWS. The first one is based on pseudo labeled data generation, and the second one is based on multi-task learning. The experimental results on two benchmark datasets validate that our approach can effectively improve the performance of Chinese word segmentation, especially when training data is insufficient.
Tasks	Chinese Word Segmentation, Multi-Task Learning
Published	2018-07-11
URL	http://arxiv.org/abs/1807.05849v1
PDF	http://arxiv.org/pdf/1807.05849v1.pdf
PWC	https://paperswithcode.com/paper/neural-chinese-word-segmentation-with
Repo
Framework

Computationally Efficient Measures of Internal Neuron Importance


Title	Computationally Efficient Measures of Internal Neuron Importance
Authors	Avanti Shrikumar, Jocelin Su, Anshul Kundaje
Abstract	The challenge of assigning importance to individual neurons in a network is of interest when interpreting deep learning models. In recent work, Dhamdhere et al. proposed Total Conductance, a “natural refinement of Integrated Gradients” for attributing importance to internal neurons. Unfortunately, the authors found that calculating conductance in tensorflow required the addition of several custom gradient operators and did not scale well. In this work, we show that the formula for Total Conductance is mathematically equivalent to Path Integrated Gradients computed on a hidden layer in the network. We provide a scalable implementation of Total Conductance using standard tensorflow gradient operators that we call Neuron Integrated Gradients. We compare Neuron Integrated Gradients to DeepLIFT, a pre-existing computationally efficient approach that is applicable to calculating internal neuron importance. We find that DeepLIFT produces strong empirical results and is faster to compute, but because it lacks the theoretical properties of Neuron Integrated Gradients, it may not always be preferred in practice. Colab notebook reproducing results: http://bit.ly/neuronintegratedgradients
Tasks
Published	2018-07-26
URL	http://arxiv.org/abs/1807.09946v1
PDF	http://arxiv.org/pdf/1807.09946v1.pdf
PWC	https://paperswithcode.com/paper/computationally-efficient-measures-of
Repo
Framework

Hypergraph Clustering: A Modularity Maximization Approach


Title	Hypergraph Clustering: A Modularity Maximization Approach
Authors	Tarun Kumar, Sankaran Vaidyanathan, Harini Ananthapadmanabhan, Srinivasan Parthasarathy, Balaraman Ravindran
Abstract	Clustering on hypergraphs has been garnering increased attention with potential applications in network analysis, VLSI design and computer vision, among others. In this work, we generalize the framework of modularity maximization for clustering on hypergraphs. To this end, we introduce a hypergraph null model, analogous to the configuration model on undirected graphs, and a node-degree preserving reduction to work with this model. This is used to define a modularity function that can be maximized using the popular and fast Louvain algorithm. We additionally propose a refinement over this clustering, by reweighting cut hyperedges in an iterative fashion. The efficacy and efficiency of our methods are demonstrated on several real-world datasets.
Tasks
Published	2018-12-28
URL	http://arxiv.org/abs/1812.10869v1
PDF	http://arxiv.org/pdf/1812.10869v1.pdf
PWC	https://paperswithcode.com/paper/hypergraph-clustering-a-modularity
Repo
Framework