January 28, 2020

3115 words 15 mins read

Paper Group ANR 916

Gastroscopic Panoramic View: Application to Automatic Polyps Detection under Gastroscopy. Landing Probabilities of Random Walks for Seed-Set Expansion in Hypergraphs. Towards Optimal Off-Policy Evaluation for Reinforcement Learning with Marginalized Importance Sampling. Semantic expressive capacity with bounded memory. NuClick: From Clicks in the N …

Gastroscopic Panoramic View: Application to Automatic Polyps Detection under Gastroscopy


Title	Gastroscopic Panoramic View: Application to Automatic Polyps Detection under Gastroscopy
Authors	Shi Chenfei, Yan Xue, Chuan Jiang, Hui Tian, Bei Liu
Abstract	Endoscopic diagnosis is an important means for gastric polyp detection. In this paper, a panoramic image of gastroscopy is developed, which can display the inner surface of the stomach intuitively and comprehensively. Moreover, the proposed automatic detection solution can help doctors locate the polyps automatically, and reduce missed diagnosis. The main contributions of this paper are: firstly, a gastroscopic panorama reconstruction method is developed. The reconstruction does not require additional hardware devices, and can solve the problem of texture dislocation and illumination imbalance properly; secondly, an end-to-end multi-object detection for gastroscopic panorama is trained based on deep learning framework. Compared with traditional solutions, the automatic polyp detection system can locate all polyps in the inner wall of stomach in real time and assist doctors to find the lesions. Thirdly, the system was evaluated in the Affiliated Hospital of Zhejiang University. The results show that the average error of the panorama is less than 2 mm, the accuracy of the polyp detection is 95%, and the recall rate is 99%. In addition, the research roadmap of this paper has guiding significance for endoscopy-assisted detection of other human soft cavities.
Tasks	Object Detection
Published	2019-10-19
URL	https://arxiv.org/abs/1910.08697v1
PDF	https://arxiv.org/pdf/1910.08697v1.pdf
PWC	https://paperswithcode.com/paper/gastroscopic-panoramic-view-application-to
Repo
Framework

Landing Probabilities of Random Walks for Seed-Set Expansion in Hypergraphs


Title	Landing Probabilities of Random Walks for Seed-Set Expansion in Hypergraphs
Authors	Eli Chien, Pan Li, Olgica Milenkovic
Abstract	We describe the first known mean-field study of landing probabilities for random walks on hypergraphs. In particular, we examine clique-expansion and tensor methods and evaluate their mean-field characteristics over a class of random hypergraph models for the purpose of seed-set community expansion. We describe parameter regimes in which the two methods outperform each other and propose a hybrid expansion method that uses partial clique-expansion to reduce the projection distortion and low-complexity tensor methods applied directly on the partially expanded hypergraphs.
Tasks
Published	2019-10-20
URL	https://arxiv.org/abs/1910.09040v1
PDF	https://arxiv.org/pdf/1910.09040v1.pdf
PWC	https://paperswithcode.com/paper/landing-probabilities-of-random-walks-for
Repo
Framework

Towards Optimal Off-Policy Evaluation for Reinforcement Learning with Marginalized Importance Sampling


Title	Towards Optimal Off-Policy Evaluation for Reinforcement Learning with Marginalized Importance Sampling
Authors	Tengyang Xie, Yifei Ma, Yu-Xiang Wang
Abstract	Motivated by the many real-world applications of reinforcement learning (RL) that require safe-policy iterations, we consider the problem of off-policy evaluation (OPE) – the problem of evaluating a new policy using the historical data obtained by different behavior policies – under the model of nonstationary episodic Markov Decision Processes (MDP) with a long horizon and a large action space. Existing importance sampling (IS) methods often suffer from large variance that depends exponentially on the RL horizon $H$. To solve this problem, we consider a marginalized importance sampling (MIS) estimator that recursively estimates the state marginal distribution for the target policy at every step. MIS achieves a mean-squared error of $$ \frac{1}{n} \sum\nolimits_{t=1}^H\mathbb{E}_{\mu}\left[\frac{d_t^\pi(s_t)^2}{d_t^\mu(s_t)^2} \mathrm{Var}_{\mu}\left[\frac{\pi_t(a_ts_t)}{\mu_t(a_ts_t)}\big( V_{t+1}^\pi(s_{t+1}) + r_t\big) \middle s_t\right]\right] + \tilde{O}(n^{-1.5}) $$ where $\mu$ and $\pi$ are the logging and target policies, $d_t^{\mu}(s_t)$ and $d_t^{\pi}(s_t)$ are the marginal distribution of the state at $t$th step, $H$ is the horizon, $n$ is the sample size and $V_{t+1}^\pi$ is the value function of the MDP under $\pi$. The result matches the Cramer-Rao lower bound in \citet{jiang2016doubly} up to a multiplicative factor of $H$. To the best of our knowledge, this is the first OPE estimation error bound with a polynomial dependence on $H$. Besides theory, we show empirical superiority of our method in time-varying, partially observable, and long-horizon RL environments.
Tasks
Published	2019-06-08
URL	https://arxiv.org/abs/1906.03393v4
PDF	https://arxiv.org/pdf/1906.03393v4.pdf
PWC	https://paperswithcode.com/paper/optimal-off-policy-evaluation-for
Repo
Framework

Semantic expressive capacity with bounded memory


Title	Semantic expressive capacity with bounded memory
Authors	Antoine Venant, Alexander Koller
Abstract	We investigate the capacity of mechanisms for compositional semantic parsing to describe relations between sentences and semantic representations. We prove that in order to represent certain relations, mechanisms which are syntactically projective must be able to remember an unbounded number of locations in the semantic representations, where nonprojective mechanisms need not. This is the first result of this kind, and has consequences both for grammar-based and for neural systems.
Tasks	Semantic Parsing
Published	2019-06-27
URL	https://arxiv.org/abs/1906.11752v1
PDF	https://arxiv.org/pdf/1906.11752v1.pdf
PWC	https://paperswithcode.com/paper/semantic-expressive-capacity-with-bounded
Repo
Framework

NuClick: From Clicks in the Nuclei to Nuclear Boundaries


Title	NuClick: From Clicks in the Nuclei to Nuclear Boundaries
Authors	Mostafa Jahanifar, Navid Alemi Koohbanani, Nasir Rajpoot
Abstract	Best performing nuclear segmentation methods are based on deep learning algorithms that require a large amount of annotated data. However, collecting annotations for nuclear segmentation is a very labor-intensive and time-consuming task. Thereby, providing a tool that can facilitate and speed up this procedure is very demanding. Here we propose a simple yet efficient framework based on convolutional neural networks, named NuClick, which can precisely segment nuclei boundaries by accepting a single point position (or click) inside each nucleus. Based on the clicked positions, inclusion and exclusion maps are generated which comprise 2D Gaussian distributions centered on those positions. These maps serve as guiding signals for the network as they are concatenated to the input image. The inclusion map focuses on the desired nucleus while the exclusion map indicates neighboring nuclei and improve the results of segmentation in scenes with nuclei clutter. The NuClick not only facilitates collecting more annotation from unseen data but also leads to superior segmentation output for deep models. It is also worth mentioning that an instance segmentation model trained on NuClick generated labels was able to rank first in LYON19 challenge.
Tasks	Instance Segmentation, Nuclear Segmentation, Semantic Segmentation
Published	2019-09-07
URL	https://arxiv.org/abs/1909.03253v1
PDF	https://arxiv.org/pdf/1909.03253v1.pdf
PWC	https://paperswithcode.com/paper/nuclick-from-clicks-in-the-nuclei-to-nuclear
Repo
Framework

Binarized Canonical Polyadic Decomposition for Knowledge Graph Completion


Title	Binarized Canonical Polyadic Decomposition for Knowledge Graph Completion
Authors	Koki Kishimoto, Katsuhiko Hayashi, Genki Akai, Masashi Shimbo
Abstract	Methods based on vector embeddings of knowledge graphs have been actively pursued as a promising approach to knowledge graph completion.However, embedding models generate storage-inefficient representations, particularly when the number of entities and relations, and the dimensionality of the real-valued embedding vectors are large. We present a binarized CANDECOMP/PARAFAC(CP) decomposition algorithm, which we refer to as B-CP, where real-valued parameters are replaced by binary values to reduce model size. Moreover, we show that a fast score computation technique can be developed with bitwise operations. We prove that B-CP is fully expressive by deriving a bound on the size of its embeddings. Experimental results on several benchmark datasets demonstrate that the proposed method successfully reduces model size by more than an order of magnitude while maintaining task performance at the same level as the real-valued CP model.
Tasks	Knowledge Graph Completion, Knowledge Graphs
Published	2019-12-04
URL	https://arxiv.org/abs/1912.02686v1
PDF	https://arxiv.org/pdf/1912.02686v1.pdf
PWC	https://paperswithcode.com/paper/binarized-canonical-polyadic-decomposition
Repo
Framework

Information based Deep Clustering: An experimental study


Title	Information based Deep Clustering: An experimental study
Authors	Jizong Peng, Christian Desrosiers, Marco Pedersoli
Abstract	Recently, two methods have shown outstanding performance for clustering images and jointly learning the feature representation. The first, called Information Maximiz-ing Self-Augmented Training (IMSAT), maximizes the mutual information between input and clusters while using a regularization term based on virtual adversarial examples. The second, named Invariant Information Clustering (IIC), maximizes the mutual information between the clustering of a sample and its geometrically transformed version. These methods use mutual information in distinct ways and leverage different kinds of transformations. This work proposes a comprehensive analysis of transformation and losses for deep clustering, where we compare numerous combinations of these two components and evaluate how they interact with one another. Results suggest that mutual information between a sample and its transformed representation leads to state-of-the-art performance for deep clustering, especially when used jointly with geometrical and adversarial transformations.
Tasks
Published	2019-10-03
URL	https://arxiv.org/abs/1910.01665v2
PDF	https://arxiv.org/pdf/1910.01665v2.pdf
PWC	https://paperswithcode.com/paper/information-based-deep-clustering-an
Repo
Framework

A Replication Study: Machine Learning Models Are Capable of Predicting Sexual Orientation From Facial Images


Title	A Replication Study: Machine Learning Models Are Capable of Predicting Sexual Orientation From Facial Images
Authors	John Leuner
Abstract	Recent research used machine learning methods to predict a person’s sexual orientation from their photograph (Wang and Kosinski, 2017). To verify this result, two of these models are replicated, one based on a deep neural network (DNN) and one on facial morphology (FM). Using a new dataset of 20,910 photographs from dating websites, the ability to predict sexual orientation is confirmed (DNN accuracy male 68%, female 77%, FM male 62%, female 72%). To investigate whether facial features such as brightness or predominant colours are predictive of sexual orientation, a new model based on highly blurred facial images was created. This model was also able to predict sexual orientation (male 63%, female 72%). The tested models are invariant to intentional changes to a subject’s makeup, eyewear, facial hair and head pose (angle that the photograph is taken at). It is shown that the head pose is not correlated with sexual orientation. While demonstrating that dating profile images carry rich information about sexual orientation these results leave open the question of how much is determined by facial morphology and how much by differences in grooming, presentation and lifestyle. The advent of new technology that is able to detect sexual orientation in this way may have serious implications for the privacy and safety of gay men and women.
Tasks
Published	2019-02-27
URL	http://arxiv.org/abs/1902.10739v1
PDF	http://arxiv.org/pdf/1902.10739v1.pdf
PWC	https://paperswithcode.com/paper/a-replication-study-machine-learning-models
Repo
Framework

A Mean Field Theory of Batch Normalization


Title	A Mean Field Theory of Batch Normalization
Authors	Greg Yang, Jeffrey Pennington, Vinay Rao, Jascha Sohl-Dickstein, Samuel S. Schoenholz
Abstract	We develop a mean field theory for batch normalization in fully-connected feedforward neural networks. In so doing, we provide a precise characterization of signal propagation and gradient backpropagation in wide batch-normalized networks at initialization. Our theory shows that gradient signals grow exponentially in depth and that these exploding gradients cannot be eliminated by tuning the initial weight variances or by adjusting the nonlinear activation function. Indeed, batch normalization itself is the cause of gradient explosion. As a result, vanilla batch-normalized networks without skip connections are not trainable at large depths for common initialization schemes, a prediction that we verify with a variety of empirical simulations. While gradient explosion cannot be eliminated, it can be reduced by tuning the network close to the linear regime, which improves the trainability of deep batch-normalized networks without residual connections. Finally, we investigate the learning dynamics of batch-normalized networks and observe that after a single step of optimization the networks achieve a relatively stable equilibrium in which gradients have dramatically smaller dynamic range. Our theory leverages Laplace, Fourier, and Gegenbauer transforms and we derive new identities that may be of independent interest.
Tasks
Published	2019-02-21
URL	http://arxiv.org/abs/1902.08129v2
PDF	http://arxiv.org/pdf/1902.08129v2.pdf
PWC	https://paperswithcode.com/paper/a-mean-field-theory-of-batch-normalization
Repo
Framework

Segmenting Ships in Satellite Imagery With Squeeze and Excitation U-Net


Title	Segmenting Ships in Satellite Imagery With Squeeze and Excitation U-Net
Authors	Venkatesh R, Anand Metha
Abstract	The ship-detection task in satellite imagery presents significant obstacles to even the most state of the art segmentation models due to lack of labelled dataset or approaches which are not able to generalize to unseen images. The most common methods for semantic segmentation involve complex two-stage networks or networks which make use of a multi-scale scene parsing module. In this paper, we propose a modified version of the popular U-Net architecture called Squeeze and Excitation U-Net and train it with a loss that helps in directly optimizing the intersection over union (IoU) score. Our method gives comparable performance to other methods while having the additional benefit of being computationally efficient.
Tasks	Scene Parsing, Semantic Segmentation
Published	2019-10-27
URL	https://arxiv.org/abs/1910.12206v1
PDF	https://arxiv.org/pdf/1910.12206v1.pdf
PWC	https://paperswithcode.com/paper/segmenting-ships-in-satellite-imagery-with
Repo
Framework

SSAP: Single-Shot Instance Segmentation With Affinity Pyramid


Title	SSAP: Single-Shot Instance Segmentation With Affinity Pyramid
Authors	Naiyu Gao, Yanhu Shan, Yupei Wang, Xin Zhao, Yinan Yu, Ming Yang, Kaiqi Huang
Abstract	Recently, proposal-free instance segmentation has received increasing attention due to its concise and efficient pipeline. Generally, proposal-free methods generate instance-agnostic semantic segmentation labels and instance-aware features to group pixels into different object instances. However, previous methods mostly employ separate modules for these two sub-tasks and require multiple passes for inference. We argue that treating these two sub-tasks separately is suboptimal. In fact, employing multiple separate modules significantly reduces the potential for application. The mutual benefits between the two complementary sub-tasks are also unexplored. To this end, this work proposes a single-shot proposal-free instance segmentation method that requires only one single pass for prediction. Our method is based on a pixel-pair affinity pyramid, which computes the probability that two pixels belong to the same instance in a hierarchical manner. The affinity pyramid can also be jointly learned with the semantic class labeling and achieve mutual benefits. Moreover, incorporating with the learned affinity pyramid, a novel cascaded graph partition module is presented to sequentially generate instances from coarse to fine. Unlike previous time-consuming graph partition methods, this module achieves $5\times$ speedup and 9% relative improvement on Average-Precision (AP). Our approach achieves state-of-the-art results on the challenging Cityscapes dataset.
Tasks	Instance Segmentation, Semantic Segmentation
Published	2019-09-04
URL	https://arxiv.org/abs/1909.01616v1
PDF	https://arxiv.org/pdf/1909.01616v1.pdf
PWC	https://paperswithcode.com/paper/ssap-single-shot-instance-segmentation-with
Repo
Framework

Deep Multiphase Level Set for Scene Parsing


Title	Deep Multiphase Level Set for Scene Parsing
Authors	Pingping Zhang, Wei Liu, Yinjie Lei, Hongyu Wang, Huchuan Lu
Abstract	Recently, Fully Convolutional Network (FCN) seems to be the go-to architecture for image segmentation, including semantic scene parsing. However, it is difficult for a generic FCN to discriminate pixels around the object boundaries, thus FCN based methods may output parsing results with inaccurate boundaries. Meanwhile, level set based active contours are superior to the boundary estimation due to the sub-pixel accuracy that they achieve. However, they are quite sensitive to initial settings. To address these limitations, in this paper we propose a novel Deep Multiphase Level Set (DMLS) method for semantic scene parsing, which efficiently incorporates multiphase level sets into deep neural networks. The proposed method consists of three modules, i.e., recurrent FCNs, adaptive multiphase level set, and deeply supervised learning. More specifically, recurrent FCNs learn multi-level representations of input images with different contexts. Adaptive multiphase level set drives the discriminative contour for each semantic class, which makes use of the advantages of both global and local information. In each time-step of the recurrent FCNs, deeply supervised learning is incorporated for model training. Extensive experiments on three public benchmarks have shown that our proposed method achieves new state-of-the-art performances.
Tasks	Scene Parsing, Semantic Segmentation
Published	2019-10-08
URL	https://arxiv.org/abs/1910.03166v2
PDF	https://arxiv.org/pdf/1910.03166v2.pdf
PWC	https://paperswithcode.com/paper/deep-multiphase-level-set-for-scene-parsing
Repo
Framework

Topic-aware Pointer-Generator Networks for Summarizing Spoken Conversations


Title	Topic-aware Pointer-Generator Networks for Summarizing Spoken Conversations
Authors	Zhengyuan Liu, Angela Ng, Sheldon Lee, Ai Ti Aw, Nancy F. Chen
Abstract	Due to the lack of publicly available resources, conversation summarization has received far less attention than text summarization. As the purpose of conversations is to exchange information between at least two interlocutors, key information about a certain topic is often scattered and spanned across multiple utterances and turns from different speakers. This phenomenon is more pronounced during spoken conversations, where speech characteristics such as backchanneling and false-starts might interrupt the topical flow. Moreover, topic diffusion and (intra-utterance) topic drift are also more common in human-to-human conversations. Such linguistic characteristics of dialogue topics make sentence-level extractive summarization approaches used in spoken documents ill-suited for summarizing conversations. Pointer-generator networks have effectively demonstrated its strength at integrating extractive and abstractive capabilities through neural modeling in text summarization. To the best of our knowledge, to date no one has adopted it for summarizing conversations. In this work, we propose a topic-aware architecture to exploit the inherent hierarchical structure in conversations to further adapt the pointer-generator model. Our approach significantly outperforms competitive baselines, achieves more efficient learning outcomes, and attains more robust performance.
Tasks	Text Summarization
Published	2019-10-03
URL	https://arxiv.org/abs/1910.01335v1
PDF	https://arxiv.org/pdf/1910.01335v1.pdf
PWC	https://paperswithcode.com/paper/topic-aware-pointer-generator-networks-for
Repo
Framework

Phase Retrieval using Conditional Generative Adversarial Networks


Title	Phase Retrieval using Conditional Generative Adversarial Networks
Authors	Tobias Uelwer, Alexander Oberstraß, Stefan Harmeling
Abstract	In this paper, we propose the application of conditional generative adversarial networks to solve various phase retrieval problems. We show that including knowledge of the measurement process at training time leads to an optimization at test time that is more robust to initialization than existing approaches involving generative models. In addition, conditioning the generator network on the measurements enables us to achieve much more detailed results. We empirically demonstrate that these advantages provide meaningful solutions to the Fourier and the compressive phase retrieval problem and that our method outperforms well-established projection-based methods as well as existing methods that are based on neural networks. Like other deep learning methods, our approach is very robust to noise and can therefore be very useful for real-world applications.
Tasks
Published	2019-12-10
URL	https://arxiv.org/abs/1912.04981v1
PDF	https://arxiv.org/pdf/1912.04981v1.pdf
PWC	https://paperswithcode.com/paper/phase-retrieval-using-conditional-generative
Repo
Framework

FocusNet: Imbalanced Large and Small Organ Segmentation with an End-to-End Deep Neural Network for Head and Neck CT Images


Title	FocusNet: Imbalanced Large and Small Organ Segmentation with an End-to-End Deep Neural Network for Head and Neck CT Images
Authors	Yunhe Gao, Rui Huang, Ming Chen, Zhe Wang, Jincheng Deng, Yuanyuan Chen, Yiwei Yang, Jie Zhang, Chanjuan Tao, Hongsheng Li
Abstract	In this paper, we propose an end-to-end deep neural network for solving the problem of imbalanced large and small organ segmentation in head and neck (HaN) CT images. To conduct radiotherapy planning for nasopharyngeal cancer, more than 10 organs-at-risk (normal organs) need to be precisely segmented in advance. However, the size ratio between large and small organs in the head could reach hundreds. Directly using such imbalanced organ annotations to train deep neural networks generally leads to inaccurate small-organ label maps. We propose a novel end-to-end deep neural network to solve this challenging problem by automatically locating, ROI-pooling, and segmenting small organs with specifically designed small-organ sub-networks while maintaining the accuracy of large organ segmentation. A strong main network with densely connected atrous spatial pyramid pooling and squeeze-and-excitation modules is used for segmenting large organs, where large organs’ label maps are directly output. For small organs, their probabilistic locations instead of label maps are estimated by the main network. High-resolution and multi-scale feature volumes for each small organ are ROI-pooled according to their locations and are fed into small-organ networks for accurate segmenting small organs. Our proposed network is extensively tested on both collected real data and the \emph{MICCAI Head and Neck Auto Segmentation Challenge 2015} dataset, and shows superior performance compared with state-of-the-art segmentation methods.
Tasks
Published	2019-07-28
URL	https://arxiv.org/abs/1907.12056v1
PDF	https://arxiv.org/pdf/1907.12056v1.pdf
PWC	https://paperswithcode.com/paper/focusnet-imbalanced-large-and-small-organ
Repo
Framework