January 26, 2020

2875 words 14 mins read

Paper Group ANR 1584

Automatic Brain Tumour Segmentation and Biophysics-Guided Survival Prediction. Homogeneous Network Embedding for Massive Graphs via Reweighted Personalized PageRank. Derivative-Free & Order-Robust Optimisation. Air Taxi Skyport Location Problem for Airport Access. Multiclass segmentation as multitask learning for drusen segmentation in retinal opti …

Automatic Brain Tumour Segmentation and Biophysics-Guided Survival Prediction


Title	Automatic Brain Tumour Segmentation and Biophysics-Guided Survival Prediction
Authors	Shuo Wang, Chengliang Dai, Yuanhan Mo, Elsa Angelini, Yike Guo, Wenjia Bai
Abstract	Gliomas are the most common malignant brain tumourswith intrinsic heterogeneity. Accurate segmentation of gliomas and theirsub-regions on multi-parametric magnetic resonance images (mpMRI)is of great clinical importance, which defines tumour size, shape andappearance and provides abundant information for preoperative diag-nosis, treatment planning and survival prediction. Recent developmentson deep learning have significantly improved the performance of auto-mated medical image segmentation. In this paper, we compare severalstate-of-the-art convolutional neural network models for brain tumourimage segmentation. Based on the ensembled segmentation, we presenta biophysics-guided prognostic model for patient overall survival predic-tion which outperforms a data-driven radiomics approach. Our methodwon the second place of the MICCAI 2019 BraTS Challenge for theoverall survival prediction.
Tasks	Medical Image Segmentation, Semantic Segmentation
Published	2019-11-19
URL	https://arxiv.org/abs/1911.08483v1
PDF	https://arxiv.org/pdf/1911.08483v1.pdf
PWC	https://paperswithcode.com/paper/automatic-brain-tumour-segmentation-and
Repo
Framework

Homogeneous Network Embedding for Massive Graphs via Reweighted Personalized PageRank


Title	Homogeneous Network Embedding for Massive Graphs via Reweighted Personalized PageRank
Authors	Renchi Yang, Jieming Shi, Xiaokui Xiao, Yin Yang, Sourav S. Bhowmick
Abstract	Given an input graph G and a node v in G, homogeneous network embedding (HNE) maps the graph structure in the vicinity of v to a compact, fixed-dimensional feature vector. This paper focuses on HNE for massive graphs, e.g., with billions of edges. On this scale, most existing approaches fail, as they incur either prohibitively high costs, or severely compromised result utility. Our proposed solution, called Node-Reweighted PageRank (NRP), is based on a classic idea of deriving embedding vectors from pairwise personalized PageRank (PPR) values. Our contributions are twofold: first, we design a simple and efficient baseline HNE method based on PPR that is capable of handling billion-edge graphs on commodity hardware; second and more importantly, we identify an inherent drawback of vanilla PPR, and address it in our main proposal NRP. Specifically, PPR was designed for a very different purpose, i.e., ranking nodes in G based on their relative importance from a source node’s perspective. In contrast, HNE aims to build node embeddings considering the whole graph. Consequently, node embeddings derived directly from PPR are of suboptimal utility. The proposed NRP approach overcomes the above deficiency through an effective and efficient node reweighting algorithm, which augments PPR values with node degree information, and iteratively adjusts embedding vectors accordingly. Overall, NRP takes O(mlogn) time and O(m) space to compute all node embeddings for a graph with m edges and n nodes. Our extensive experiments that compare NRP against 18 existing solutions over 7 real graphs demonstrate that NRP achieves higher result utility than all the solutions for link prediction, graph reconstruction and node classification, while being up to orders of magnitude faster. In particular, on a billion-edge Twitter graph, NRP terminates within 4 hours, using a single CPU core.
Tasks	Link Prediction, Network Embedding, Node Classification
Published	2019-06-17
URL	https://arxiv.org/abs/1906.06826v5
PDF	https://arxiv.org/pdf/1906.06826v5.pdf
PWC	https://paperswithcode.com/paper/homogeneous-network-embedding-for-massive
Repo
Framework

Derivative-Free & Order-Robust Optimisation


Title	Derivative-Free & Order-Robust Optimisation
Authors	Victor Gabillon, Rasul Tutunov, Michal Valko, Haitham Bou Ammar
Abstract	In this paper, we formalise order-robust optimisation as an instance of online learning minimising simple regret, and propose Vroom, a zero’th order optimisation algorithm capable of achieving vanishing regret in non-stationary environments, while recovering favorable rates under stochastic reward-generating processes. Our results are the first to target simple regret definitions in adversarial scenarios unveiling a challenge that has been rarely considered in prior work.
Tasks
Published	2019-10-09
URL	https://arxiv.org/abs/1910.04034v3
PDF	https://arxiv.org/pdf/1910.04034v3.pdf
PWC	https://paperswithcode.com/paper/derivative-free-order-robust-optimisation
Repo
Framework

Air Taxi Skyport Location Problem for Airport Access


Title	Air Taxi Skyport Location Problem for Airport Access
Authors	Srushti Rath, Joseph Y. J. Chow
Abstract	We consider design of skyport locations for air taxis accessing airports and adopt a novel use of the classic hub location problem to properly make trade-offs on access distances for travelers to skyports from other zones, which is shown to reduce costs relative to a clustering approach from the literature. Extensive experiments on data from New York City show the method outperforms the benchmark clustering method by more than 7.4% here. Results suggest that six skyports located between Manhattan and Brooklyn can adequately serve the airport access travel needs and are sufficiently stable against travel time or transfer time increases.
Tasks
Published	2019-04-01
URL	https://arxiv.org/abs/1904.01497v3
PDF	https://arxiv.org/pdf/1904.01497v3.pdf
PWC	https://paperswithcode.com/paper/air-taxi-skyport-location-problem-for-airport
Repo
Framework

Multiclass segmentation as multitask learning for drusen segmentation in retinal optical coherence tomography


Title	Multiclass segmentation as multitask learning for drusen segmentation in retinal optical coherence tomography
Authors	Rhona Asgari, José Ignacio Orlando, Sebastian Waldstein, Ferdinand Schlanitz, Magdalena Baratsits, Ursula Schmidt-Erfurth, Hrvoje Bogunović
Abstract	Automated drusen segmentation in retinal optical coherence tomography (OCT) scans is relevant for understanding age-related macular degeneration (AMD) risk and progression. This task is usually performed by segmenting the top/bottom anatomical interfaces that define drusen, the outer boundary of the retinal pigment epithelium (OBRPE) and the Bruch’s membrane (BM), respectively. In this paper we propose a novel multi-decoder architecture that tackles drusen segmentation as a multitask problem. Instead of training a multiclass model for OBRPE/BM segmentation, we use one decoder per target class and an extra one aiming for the area between the layers. We also introduce connections between each class-specific branch and the additional decoder to increase the regularization effect of this surrogate task. We validated our approach on private/public data sets with 166 early/intermediate AMD Spectralis, and 200 AMD and control Bioptigen OCT volumes, respectively. Our method consistently outperformed several baselines in both layer and drusen segmentation evaluations.
Tasks
Published	2019-06-18
URL	https://arxiv.org/abs/1906.07679v2
PDF	https://arxiv.org/pdf/1906.07679v2.pdf
PWC	https://paperswithcode.com/paper/multiclass-segmentation-as-multitask-learning
Repo
Framework

TopExNet: Entity-Centric Network Topic Exploration in News Streams


Title	TopExNet: Entity-Centric Network Topic Exploration in News Streams
Authors	Andreas Spitz, Satya Almasian, Michael Gertz
Abstract	The recent introduction of entity-centric implicit network representations of unstructured text offers novel ways for exploring entity relations in document collections and streams efficiently and interactively. Here, we present TopExNet as a tool for exploring entity-centric network topics in streams of news articles. The application is available as a web service at https://topexnet.ifi.uni-heidelberg.de/ .
Tasks
Published	2019-05-29
URL	https://arxiv.org/abs/1905.12335v2
PDF	https://arxiv.org/pdf/1905.12335v2.pdf
PWC	https://paperswithcode.com/paper/topexnet-entity-centric-network-topic
Repo
Framework

A Topological Nomenclature for 3D Shape Analysis in Connectomics


Title	A Topological Nomenclature for 3D Shape Analysis in Connectomics
Authors	Abhimanyu Talwar, Zudi Lin, Donglai Wei, Yuesong Wu, Bowen Zheng, Jinglin Zhao, Won-Dong Jang, Xueying Wang, Jeff W. Lichtman, Hanspeter Pfister
Abstract	One of the essential tasks in connectomics is the morphology analysis of neurons and organelles like mitochondria to shed light on their biological properties. However, these biological objects often have tangled parts or complex branching patterns, which make it hard to abstract, categorize, and manipulate their morphology. In this paper, we develop a novel topological nomenclature system to name these objects like the appellation for chemical compounds to promote neuroscience analysis based on their skeletal structures. We first convert the volumetric representation into the topology-preserving reduced graph to untangle the objects. Next, we develop nomenclature rules for pyramidal neurons and mitochondria from the reduced graph and finally learn the feature embedding for shape manipulation. In ablation studies, we quantitatively show that graphs generated by our proposed method align with the perception of experts. On 3D shape retrieval and decomposition tasks, we qualitatively demonstrate that the encoded topological nomenclature features achieve better results than state-of-the-art shape descriptors. To advance neuroscience, we will release a 3D segmentation dataset of mitochondria and pyramidal neurons reconstructed from a 100um cube electron microscopy volume with their reduced graph and topological nomenclature annotations. Code is publicly available at https://github.com/donglaiw/ibexHelper.
Tasks	3D Shape Analysis, 3D Shape Retrieval
Published	2019-09-27
URL	https://arxiv.org/abs/1909.12887v2
PDF	https://arxiv.org/pdf/1909.12887v2.pdf
PWC	https://paperswithcode.com/paper/a-topological-nomenclature-for-3d-shape
Repo
Framework

CIA-Net: Robust Nuclei Instance Segmentation with Contour-aware Information Aggregation


Title	CIA-Net: Robust Nuclei Instance Segmentation with Contour-aware Information Aggregation
Authors	Yanning Zhou, Omer Fahri Onder, Qi Dou, Efstratios Tsougenis, Hao Chen, Pheng-Ann Heng
Abstract	Accurate segmenting nuclei instances is a crucial step in computer-aided image analysis to extract rich features for cellular estimation and following diagnosis as well as treatment. While it still remains challenging because the wide existence of nuclei clusters, along with the large morphological variances among different organs make nuclei instance segmentation susceptible to over-/under-segmentation. Additionally, the inevitably subjective annotating and mislabeling prevent the network learning from reliable samples and eventually reduce the generalization capability for robustly segmenting unseen organ nuclei. To address these issues, we propose a novel deep neural network, namely Contour-aware Informative Aggregation Network (CIA-Net) with multi-level information aggregation module between two task-specific decoders. Rather than independent decoders, it leverages the merit of spatial and texture dependencies between nuclei and contour by bi-directionally aggregating task-specific features. Furthermore, we proposed a novel smooth truncated loss that modulates losses to reduce the perturbation from outliers. Consequently, the network can focus on learning from reliable and informative samples, which inherently improves the generalization capability. Experiments on the 2018 MICCAI challenge of Multi-Organ-Nuclei-Segmentation validated the effectiveness of our proposed method, surpassing all the other 35 competitive teams by a significant margin.
Tasks	Instance Segmentation, Semantic Segmentation
Published	2019-03-13
URL	http://arxiv.org/abs/1903.05358v1
PDF	http://arxiv.org/pdf/1903.05358v1.pdf
PWC	https://paperswithcode.com/paper/cia-net-robust-nuclei-instance-segmentation
Repo
Framework

Solving NMF with smoothness and sparsity constraints using PALM


Title	Solving NMF with smoothness and sparsity constraints using PALM
Authors	Raimon Fabregat, Nelly Pustelnik, Paulo Gonçalves, Pierre Borgnat
Abstract	Non-negative matrix factorization is a problem of dimensionality reduction and source separation of data that has been widely used in many fields since it was studied in depth in 1999 by Lee and Seung, including in compression of data, document clustering, processing of audio spectrograms and astronomy. In this work we have adapted a minimization scheme for convex functions with non-differentiable constraints called PALM to solve the NMF problem with solutions that can be smooth and/or sparse, two properties frequently desired.
Tasks	Dimensionality Reduction
Published	2019-10-31
URL	https://arxiv.org/abs/1910.14576v1
PDF	https://arxiv.org/pdf/1910.14576v1.pdf
PWC	https://paperswithcode.com/paper/solving-nmf-with-smoothness-and-sparsity
Repo
Framework

Hardware/Software Codesign for Training/Testing Multiple Neural Networks on Multiple FPGAs


Title	Hardware/Software Codesign for Training/Testing Multiple Neural Networks on Multiple FPGAs
Authors	Brosnan Yuen
Abstract	Most neural network designs for FPGAs are inflexible. In this paper, we propose a flexible VHDL structure that would allow any neural network to be implemented on multiple FPGAs. Moreover, the VHDL structure allows for testing as well as training multiple neural networks. The VHDL design consists of multiple processor groups. There are two types of processor groups: Mini Vector Machine Processor Group and Activation Processor Group. Each processor group consists of individual Mini Vector Machines and Activation Processor. The Mini Vector Machines apply vector operations to the data, while the Activation Processors apply activation functions to the data. A ring buffer was implemented to connect the various processor groups.
Tasks
Published	2019-10-13
URL	https://arxiv.org/abs/1910.05683v2
PDF	https://arxiv.org/pdf/1910.05683v2.pdf
PWC	https://paperswithcode.com/paper/hardwaresoftware-codesign-for-trainingtesting
Repo
Framework

Human Annotations Improve GAN Performances


Title	Human Annotations Improve GAN Performances
Authors	Juanyong Duan, Sim Heng Ong, Qi Zhao
Abstract	Generative Adversarial Networks (GANs) have shown great success in many applications. In this work, we present a novel method that leverages human annotations to improve the quality of generated images. Unlike previous paradigms that directly ask annotators to distinguish between real and fake data in a straightforward way, we propose and annotate a set of carefully designed attributes that encode important image information at various levels, to understand the differences between fake and real images. Specifically, we have collected an annotated dataset that contains 600 fake images and 400 real images. These images are evaluated by 10 workers from the Amazon Mechanical Turk (AMT) based on eight carefully defined attributes. Statistical analyses have revealed different distributions of the proposed attributes between real and fake images. These attributes are shown to be useful in discriminating fake images from real ones, and deep neural networks are developed to automatically predict the attributes. We further utilize the information by integrating the attributes into GANs to generate better images. Experimental results evaluated by multiple metrics show performance improvement of the proposed model.
Tasks
Published	2019-11-15
URL	https://arxiv.org/abs/1911.06460v1
PDF	https://arxiv.org/pdf/1911.06460v1.pdf
PWC	https://paperswithcode.com/paper/human-annotations-improve-gan-performances
Repo
Framework

Understanding Misclassifications by Attributes


Title	Understanding Misclassifications by Attributes
Authors	Sadaf Gulshad, Zeynep Akata, Jan Hendrik Metzen, Arnold Smeulders
Abstract	In this paper, we aim to understand and explain the decisions of deep neural networks by studying the behavior of predicted attributes when adversarial examples are introduced. We study the changes in attributes for clean as well as adversarial images in both standard and adversarially robust networks. We propose a metric to quantify the robustness of an adversarially robust network against adversarial attacks. In a standard network, attributes predicted for adversarial images are consistent with the wrong class, while attributes predicted for the clean images are consistent with the true class. In an adversarially robust network, the attributes predicted for adversarial images classified correctly are consistent with the true class. Finally, we show that the ability to robustify a network varies for different datasets. For the fine grained dataset, it is higher as compared to the coarse-grained dataset. Additionally, the ability to robustify a network increases with the increase in adversarial noise.
Tasks
Published	2019-10-15
URL	https://arxiv.org/abs/1910.07416v1
PDF	https://arxiv.org/pdf/1910.07416v1.pdf
PWC	https://paperswithcode.com/paper/understanding-misclassifications-by
Repo
Framework

Online Meta-Learning


Title	Online Meta-Learning
Authors	Chelsea Finn, Aravind Rajeswaran, Sham Kakade, Sergey Levine
Abstract	A central capability of intelligent systems is the ability to continuously build upon previous experiences to speed up and enhance learning of new tasks. Two distinct research paradigms have studied this question. Meta-learning views this problem as learning a prior over model parameters that is amenable for fast adaptation on a new task, but typically assumes the set of tasks are available together as a batch. In contrast, online (regret based) learning considers a sequential setting in which problems are revealed one after the other, but conventionally train only a single model without any task-specific adaptation. This work introduces an online meta-learning setting, which merges ideas from both the aforementioned paradigms to better capture the spirit and practice of continual lifelong learning. We propose the follow the meta leader algorithm which extends the MAML algorithm to this setting. Theoretically, this work provides an $\mathcal{O}(\log T)$ regret guarantee with only one additional higher order smoothness assumption in comparison to the standard online setting. Our experimental evaluation on three different large-scale tasks suggest that the proposed algorithm significantly outperforms alternatives based on traditional online learning approaches.
Tasks	Meta-Learning
Published	2019-02-22
URL	https://arxiv.org/abs/1902.08438v4
PDF	https://arxiv.org/pdf/1902.08438v4.pdf
PWC	https://paperswithcode.com/paper/online-meta-learning
Repo
Framework

Reprojection R-CNN: A Fast and Accurate Object Detector for 360° Images


Title	Reprojection R-CNN: A Fast and Accurate Object Detector for 360° Images
Authors	Pengyu Zhao, Ansheng You, Yuanxing Zhang, Jiaying Liu, Kaigui Bian, Yunhai Tong
Abstract	360{\deg} images are usually represented in either equirectangular projection (ERP) or multiple perspective projections. Different from the flat 2D images, the detection task is challenging for 360{\deg} images due to the distortion of ERP and the inefficiency of perspective projections. However, existing methods mostly focus on one of the above representations instead of both, leading to limited detection performance. Moreover, the lack of appropriate bounding-box annotations as well as the annotated datasets further increases the difficulties of the detection task. In this paper, we present a standard object detection framework for 360{\deg} images. Specifically, we adapt the terminologies of the traditional object detection task to the omnidirectional scenarios, and propose a novel two-stage object detector, i.e., Reprojection R-CNN by combining both ERP and perspective projection. Owing to the omnidirectional field-of-view of ERP, Reprojection R-CNN first generates coarse region proposals efficiently by a distortion-aware spherical region proposal network. Then, it leverages the distortion-free perspective projection and refines the proposed regions by a novel reprojection network. We construct two novel synthetic datasets for training and evaluation. Experiments reveal that Reprojection R-CNN outperforms the previous state-of-the-art methods on the mAP metric. In addition, the proposed detector could run at 178ms per image in the panoramic datasets, which implies its practicability in real-world applications.
Tasks	Object Detection
Published	2019-07-27
URL	https://arxiv.org/abs/1907.11830v1
PDF	https://arxiv.org/pdf/1907.11830v1.pdf
PWC	https://paperswithcode.com/paper/reprojection-r-cnn-a-fast-and-accurate-object
Repo
Framework

AuxBlocks: Defense Adversarial Example via Auxiliary Blocks


Title	AuxBlocks: Defense Adversarial Example via Auxiliary Blocks
Authors	Yueyao Yu, Pengfei Yu, Wenye Li
Abstract	Deep learning models are vulnerable to adversarial examples, which poses an indisputable threat to their applications. However, recent studies observe gradient-masking defenses are self-deceiving methods if an attacker can realize this defense. In this paper, we propose a new defense method based on appending information. We introduce the Aux Block model to produce extra outputs as a self-ensemble algorithm and analytically investigate the robustness mechanism of Aux Block. We have empirically studied the efficiency of our method against adversarial examples in two types of white-box attacks, and found that even in the full white-box attack where an adversary can craft malicious examples from defense models, our method has a more robust performance of about 54.6% precision on Cifar10 dataset and 38.7% precision on Mini-Imagenet dataset. Another advantage of our method is that it is able to maintain the prediction accuracy of the classification model on clean images, and thereby exhibits its high potential in practical applications
Tasks
Published	2019-02-18
URL	http://arxiv.org/abs/1902.06415v1
PDF	http://arxiv.org/pdf/1902.06415v1.pdf
PWC	https://paperswithcode.com/paper/auxblocks-defense-adversarial-example-via
Repo
Framework