Paper Group ANR 94
Feature Decomposition Based Saliency Detection in Electron Cryo-Tomograms. Transfer Learning for Estimating Causal Effects using Neural Networks. Adversarial Binary Coding for Efficient Person Re-identification. Model-Free Control for Distributed Stream Data Processing using Deep Reinforcement Learning. Protecting JPEG Images Against Adversarial At …
Feature Decomposition Based Saliency Detection in Electron Cryo-Tomograms
Title | Feature Decomposition Based Saliency Detection in Electron Cryo-Tomograms |
Authors | Bo Zhou, Qiang Guo, Xiangrui Zeng, Min Xu |
Abstract | Electron Cryo-Tomography (ECT) allows 3D visualization of subcellular structures at the submolecular resolution in close to the native state. However, due to the high degree of structural complexity and imaging limits, the automatic segmentation of cellular components from ECT images is very difficult. To complement and speed up existing segmentation methods, it is desirable to develop a generic cell component segmentation method that is 1) not specific to particular types of cellular components, 2) able to segment unknown cellular components, 3) fully unsupervised and does not rely on the availability of training data. As an important step towards this goal, in this paper, we propose a saliency detection method that computes the likelihood that a subregion in a tomogram stands out from the background. Our method consists of four steps: supervoxel over-segmentation, feature extraction, feature matrix decomposition, and computation of saliency. The method produces a distribution map that represents the regions’ saliency in tomograms. Our experiments show that our method can successfully label most salient regions detected by a human observer, and able to filter out regions not containing cellular components. Therefore, our method can remove the majority of the background region, and significantly speed up the subsequent processing of segmentation and recognition of cellular components captured by ECT. |
Tasks | Saliency Detection |
Published | 2018-01-31 |
URL | http://arxiv.org/abs/1801.10562v1 |
http://arxiv.org/pdf/1801.10562v1.pdf | |
PWC | https://paperswithcode.com/paper/feature-decomposition-based-saliency |
Repo | |
Framework | |
Transfer Learning for Estimating Causal Effects using Neural Networks
Title | Transfer Learning for Estimating Causal Effects using Neural Networks |
Authors | Sören R. Künzel, Bradly C. Stadie, Nikita Vemuri, Varsha Ramakrishnan, Jasjeet S. Sekhon, Pieter Abbeel |
Abstract | We develop new algorithms for estimating heterogeneous treatment effects, combining recent developments in transfer learning for neural networks with insights from the causal inference literature. By taking advantage of transfer learning, we are able to efficiently use different data sources that are related to the same underlying causal mechanisms. We compare our algorithms with those in the extant literature using extensive simulation studies based on large-scale voter persuasion experiments and the MNIST database. Our methods can perform an order of magnitude better than existing benchmarks while using a fraction of the data. |
Tasks | Causal Inference, Transfer Learning |
Published | 2018-08-23 |
URL | http://arxiv.org/abs/1808.07804v1 |
http://arxiv.org/pdf/1808.07804v1.pdf | |
PWC | https://paperswithcode.com/paper/transfer-learning-for-estimating-causal |
Repo | |
Framework | |
Adversarial Binary Coding for Efficient Person Re-identification
Title | Adversarial Binary Coding for Efficient Person Re-identification |
Authors | Zheng Liu, Jie Qin, Annan Li, Yunhong Wang, Luc Van Gool |
Abstract | Person re-identification (ReID) aims at matching persons across different views/scenes. In addition to accuracy, the matching efficiency has received more and more attention because of demanding applications using large-scale data. Several binary coding based methods have been proposed for efficient ReID, which either learn projections to map high-dimensional features to compact binary codes, or directly adopt deep neural networks by simply inserting an additional fully-connected layer with tanh-like activations. However, the former approach requires time-consuming hand-crafted feature extraction and complicated (discrete) optimizations; the latter lacks the necessary discriminative information greatly due to the straightforward activation functions. In this paper, we propose a simple yet effective framework for efficient ReID inspired by the recent advances in adversarial learning. Specifically, instead of learning explicit projections or adding fully-connected mapping layers, the proposed Adversarial Binary Coding (ABC) framework guides the extraction of binary codes implicitly and effectively. The discriminability of the extracted codes is further enhanced by equipping the ABC with a deep triplet network for the ReID task. More importantly, the ABC and triplet network are simultaneously optimized in an end-to-end manner. Extensive experiments on three large-scale ReID benchmarks demonstrate the superiority of our approach over the state-of-the-art methods. |
Tasks | Person Re-Identification |
Published | 2018-03-29 |
URL | http://arxiv.org/abs/1803.10914v3 |
http://arxiv.org/pdf/1803.10914v3.pdf | |
PWC | https://paperswithcode.com/paper/adversarial-binary-coding-for-efficient |
Repo | |
Framework | |
Model-Free Control for Distributed Stream Data Processing using Deep Reinforcement Learning
Title | Model-Free Control for Distributed Stream Data Processing using Deep Reinforcement Learning |
Authors | Teng Li, Zhiyuan Xu, Jian Tang, Yanzhi Wang |
Abstract | In this paper, we focus on general-purpose Distributed Stream Data Processing Systems (DSDPSs), which deal with processing of unbounded streams of continuous data at scale distributedly in real or near-real time. A fundamental problem in a DSDPS is the scheduling problem with the objective of minimizing average end-to-end tuple processing time. A widely-used solution is to distribute workload evenly over machines in the cluster in a round-robin manner, which is obviously not efficient due to lack of consideration for communication delay. Model-based approaches do not work well either due to the high complexity of the system environment. We aim to develop a novel model-free approach that can learn to well control a DSDPS from its experience rather than accurate and mathematically solvable system models, just as a human learns a skill (such as cooking, driving, swimming, etc). Specifically, we, for the first time, propose to leverage emerging Deep Reinforcement Learning (DRL) for enabling model-free control in DSDPSs; and present design, implementation and evaluation of a novel and highly effective DRL-based control framework, which minimizes average end-to-end tuple processing time by jointly learning the system environment via collecting very limited runtime statistics data and making decisions under the guidance of powerful Deep Neural Networks. To validate and evaluate the proposed framework, we implemented it based on a widely-used DSDPS, Apache Storm, and tested it with three representative applications. Extensive experimental results show 1) Compared to Storm’s default scheduler and the state-of-the-art model-based method, the proposed framework reduces average tuple processing by 33.5% and 14.0% respectively on average. 2) The proposed framework can quickly reach a good scheduling solution during online learning, which justifies its practicability for online control in DSDPSs. |
Tasks | |
Published | 2018-03-02 |
URL | http://arxiv.org/abs/1803.01016v1 |
http://arxiv.org/pdf/1803.01016v1.pdf | |
PWC | https://paperswithcode.com/paper/model-free-control-for-distributed-stream |
Repo | |
Framework | |
Protecting JPEG Images Against Adversarial Attacks
Title | Protecting JPEG Images Against Adversarial Attacks |
Authors | Aaditya Prakash, Nick Moran, Solomon Garber, Antonella DiLillo, James Storer |
Abstract | As deep neural networks (DNNs) have been integrated into critical systems, several methods to attack these systems have been developed. These adversarial attacks make imperceptible modifications to an image that fool DNN classifiers. We present an adaptive JPEG encoder which defends against many of these attacks. Experimentally, we show that our method produces images with high visual quality while greatly reducing the potency of state-of-the-art attacks. Our algorithm requires only a modest increase in encoding time, produces a compressed image which can be decompressed by an off-the-shelf JPEG decoder, and classified by an unmodified classifier |
Tasks | |
Published | 2018-03-02 |
URL | http://arxiv.org/abs/1803.00940v1 |
http://arxiv.org/pdf/1803.00940v1.pdf | |
PWC | https://paperswithcode.com/paper/protecting-jpeg-images-against-adversarial |
Repo | |
Framework | |
Back to the Future for Dialogue Research: A Position Paper
Title | Back to the Future for Dialogue Research: A Position Paper |
Authors | Philip R Cohen |
Abstract | This short position paper is intended to provide a critique of current approaches to dialogue, as well as a roadmap for collaborative dialogue research. It is unapologetically opinionated, but informed by 40 years of dialogue re-search. No attempt is made to be comprehensive. The paper will discuss current research into building so-called “chatbots”, slot-filling dialogue systems, and plan-based dialogue systems. For further discussion of some of these issues, please see (Allen et al., in press). |
Tasks | Slot Filling |
Published | 2018-12-04 |
URL | http://arxiv.org/abs/1812.01144v1 |
http://arxiv.org/pdf/1812.01144v1.pdf | |
PWC | https://paperswithcode.com/paper/back-to-the-future-for-dialogue-research-a |
Repo | |
Framework | |
Unsupervised Domain Adaptation for Automatic Estimation of Cardiothoracic Ratio
Title | Unsupervised Domain Adaptation for Automatic Estimation of Cardiothoracic Ratio |
Authors | Nanqing Dong, Michael Kampffmeyer, Xiaodan Liang, Zeya Wang, Wei Dai, Eric P. Xing |
Abstract | The cardiothoracic ratio (CTR), a clinical metric of heart size in chest X-rays (CXRs), is a key indicator of cardiomegaly. Manual measurement of CTR is time-consuming and can be affected by human subjectivity, making it desirable to design computer-aided systems that assist clinicians in the diagnosis process. Automatic CTR estimation through chest organ segmentation, however, requires large amounts of pixel-level annotated data, which is often unavailable. To alleviate this problem, we propose an unsupervised domain adaptation framework based on adversarial networks. The framework learns domain invariant feature representations from openly available data sources to produce accurate chest organ segmentation for unlabeled datasets. Specifically, we propose a model that enforces our intuition that prediction masks should be domain independent. Hence, we introduce a discriminator that distinguishes segmentation predictions from ground truth masks. We evaluate our system’s prediction based on the assessment of radiologists and demonstrate the clinical practicability for the diagnosis of cardiomegaly. We finally illustrate on the JSRT dataset that the semi-supervised performance of our model is also very promising. |
Tasks | Domain Adaptation, Unsupervised Domain Adaptation |
Published | 2018-07-10 |
URL | http://arxiv.org/abs/1807.03434v1 |
http://arxiv.org/pdf/1807.03434v1.pdf | |
PWC | https://paperswithcode.com/paper/unsupervised-domain-adaptation-for-automatic |
Repo | |
Framework | |
A unified strategy for implementing curiosity and empowerment driven reinforcement learning
Title | A unified strategy for implementing curiosity and empowerment driven reinforcement learning |
Authors | Ildefons Magrans de Abril, Ryota Kanai |
Abstract | Although there are many approaches to implement intrinsically motivated artificial agents, the combined usage of multiple intrinsic drives remains still a relatively unexplored research area. Specifically, we hypothesize that a mechanism capable of quantifying and controlling the evolution of the information flow between the agent and the environment could be the fundamental component for implementing a higher degree of autonomy into artificial intelligent agents. This paper propose a unified strategy for implementing two semantically orthogonal intrinsic motivations: curiosity and empowerment. Curiosity reward informs the agent about the relevance of a recent agent action, whereas empowerment is implemented as the opposite information flow from the agent to the environment that quantifies the agent’s potential of controlling its own future. We show that an additional homeostatic drive is derived from the curiosity reward, which generalizes and enhances the information gain of a classical curious/heterostatic reinforcement learning agent. We show how a shared internal model by curiosity and empowerment facilitates a more efficient training of the empowerment function. Finally, we discuss future directions for further leveraging the interplay between these two intrinsic rewards. |
Tasks | |
Published | 2018-06-18 |
URL | http://arxiv.org/abs/1806.06505v1 |
http://arxiv.org/pdf/1806.06505v1.pdf | |
PWC | https://paperswithcode.com/paper/a-unified-strategy-for-implementing-curiosity |
Repo | |
Framework | |
XL-NBT: A Cross-lingual Neural Belief Tracking Framework
Title | XL-NBT: A Cross-lingual Neural Belief Tracking Framework |
Authors | Wenhu Chen, Jianshu Chen, Yu Su, Xin Wang, Dong Yu, Xifeng Yan, William Yang Wang |
Abstract | Task-oriented dialog systems are becoming pervasive, and many companies heavily rely on them to complement human agents for customer service in call centers. With globalization, the need for providing cross-lingual customer support becomes more urgent than ever. However, cross-lingual support poses great challenges—it requires a large amount of additional annotated data from native speakers. In order to bypass the expensive human annotation and achieve the first step towards the ultimate goal of building a universal dialog system, we set out to build a cross-lingual state tracking framework. Specifically, we assume that there exists a source language with dialog belief tracking annotations while the target languages have no annotated dialog data of any form. Then, we pre-train a state tracker for the source language as a teacher, which is able to exploit easy-to-access parallel data. We then distill and transfer its own knowledge to the student state tracker in target languages. We specifically discuss two types of common parallel resources: bilingual corpus and bilingual dictionary, and design different transfer learning strategies accordingly. Experimentally, we successfully use English state tracker as the teacher to transfer its knowledge to both Italian and German trackers and achieve promising results. |
Tasks | Transfer Learning |
Published | 2018-08-19 |
URL | http://arxiv.org/abs/1808.06244v2 |
http://arxiv.org/pdf/1808.06244v2.pdf | |
PWC | https://paperswithcode.com/paper/xl-nbt-a-cross-lingual-neural-belief-tracking |
Repo | |
Framework | |
Recursive Feature Generation for Knowledge-based Learning
Title | Recursive Feature Generation for Knowledge-based Learning |
Authors | Lior Friedman, Shaul Markovitch |
Abstract | When humans perform inductive learning, they often enhance the process with background knowledge. With the increasing availability of well-formed collaborative knowledge bases, the performance of learning algorithms could be significantly enhanced if a way were found to exploit these knowledge bases. In this work, we present a novel algorithm for injecting external knowledge into induction algorithms using feature generation. Given a feature, the algorithm defines a new learning task over its set of values, and uses the knowledge base to solve the constructed learning task. The resulting classifier is then used as a new feature for the original problem. We have applied our algorithm to the domain of text classification using large semantic knowledge bases. We have shown that the generated features significantly improve the performance of existing learning algorithms. |
Tasks | Text Classification |
Published | 2018-01-31 |
URL | http://arxiv.org/abs/1802.00050v1 |
http://arxiv.org/pdf/1802.00050v1.pdf | |
PWC | https://paperswithcode.com/paper/recursive-feature-generation-for-knowledge |
Repo | |
Framework | |
Bayesian Learning with Wasserstein Barycenters
Title | Bayesian Learning with Wasserstein Barycenters |
Authors | Julio Backhoff-Veraguas, Joaquin Fontbona, Gonzalo Rios, Felipe Tobar |
Abstract | We introduce a novel paradigm for Bayesian learning based on optimal transport theory. Namely, we propose to use the Wasserstein barycenter of the posterior law on models as a predictive posterior, thus introducing an alternative to classical choices like the maximum a posteriori estimator and the Bayesian model average. We exhibit conditions granting the existence and statistical consistency of this estimator, discuss some of its basic and specific properties, and provide insight into its theoretical advantages. Finally, we introduce a novel numerical method which is ideally suited for the computation of our estimator, and we explicitly discuss its implementations for specific families of models. This method can be seen as a stochastic gradient descent algorithm in the Wasserstein space, and is of independent interest and applicability for the computation of Wasserstein barycenters. We also provide an illustrative numerical example for experimental validation of the proposed method. |
Tasks | |
Published | 2018-05-28 |
URL | http://arxiv.org/abs/1805.10833v3 |
http://arxiv.org/pdf/1805.10833v3.pdf | |
PWC | https://paperswithcode.com/paper/bayesian-learning-with-wasserstein |
Repo | |
Framework | |
DOLORES: Deep Contextualized Knowledge Graph Embeddings
Title | DOLORES: Deep Contextualized Knowledge Graph Embeddings |
Authors | Haoyu Wang, Vivek Kulkarni, William Yang Wang |
Abstract | We introduce a new method DOLORES for learning knowledge graph embeddings that effectively captures contextual cues and dependencies among entities and relations. First, we note that short paths on knowledge graphs comprising of chains of entities and relations can encode valuable information regarding their contextual usage. We operationalize this notion by representing knowledge graphs not as a collection of triples but as a collection of entity-relation chains, and learn embeddings for entities and relations using deep neural models that capture such contextual usage. In particular, our model is based on Bi-Directional LSTMs and learn deep representations of entities and relations from constructed entity-relation chains. We show that these representations can very easily be incorporated into existing models to significantly advance the state of the art on several knowledge graph prediction tasks like link prediction, triple classification, and missing relation type prediction (in some cases by at least 9.5%). |
Tasks | Knowledge Graph Embeddings, Knowledge Graphs, Link Prediction |
Published | 2018-10-31 |
URL | http://arxiv.org/abs/1811.00147v1 |
http://arxiv.org/pdf/1811.00147v1.pdf | |
PWC | https://paperswithcode.com/paper/dolores-deep-contextualized-knowledge-graph |
Repo | |
Framework | |
MedGAN: Medical Image Translation using GANs
Title | MedGAN: Medical Image Translation using GANs |
Authors | Karim Armanious, Chenming Jiang, Marc Fischer, Thomas Küstner, Konstantin Nikolaou, Sergios Gatidis, Bin Yang |
Abstract | Image-to-image translation is considered a new frontier in the field of medical image analysis, with numerous potential applications. However, a large portion of recent approaches offers individualized solutions based on specialized task-specific architectures or require refinement through non-end-to-end training. In this paper, we propose a new framework, named MedGAN, for medical image-to-image translation which operates on the image level in an end-to-end manner. MedGAN builds upon recent advances in the field of generative adversarial networks (GANs) by merging the adversarial framework with a new combination of non-adversarial losses. We utilize a discriminator network as a trainable feature extractor which penalizes the discrepancy between the translated medical images and the desired modalities. Moreover, style-transfer losses are utilized to match the textures and fine-structures of the desired target images to the translated images. Additionally, we present a new generator architecture, titled CasNet, which enhances the sharpness of the translated medical outputs through progressive refinement via encoder-decoder pairs. Without any application-specific modifications, we apply MedGAN on three different tasks: PET-CT translation, correction of MR motion artefacts and PET image denoising. Perceptual analysis by radiologists and quantitative evaluations illustrate that the MedGAN outperforms other existing translation approaches. |
Tasks | Denoising, Image Denoising, Image-to-Image Translation, Style Transfer |
Published | 2018-06-17 |
URL | http://arxiv.org/abs/1806.06397v2 |
http://arxiv.org/pdf/1806.06397v2.pdf | |
PWC | https://paperswithcode.com/paper/medgan-medical-image-translation-using-gans |
Repo | |
Framework | |
A family of neighborhood contingency logics
Title | A family of neighborhood contingency logics |
Authors | Jie Fan |
Abstract | This article proposes the axiomatizations of contingency logics of various natural classes of neighborhood frames. In particular, by defining a suitable canonical neighborhood function, we give sound and complete axiomatizations of monotone contingency logic and regular contingency logic, thereby answering two open questions raised by Bakhtiari, van Ditmarsch, and Hansen. The canonical function is inspired by a function proposed by Kuhn in~1995. We show that Kuhn’s function is actually equal to a related function originally given by Humberstone. |
Tasks | |
Published | 2018-09-24 |
URL | http://arxiv.org/abs/1809.09495v1 |
http://arxiv.org/pdf/1809.09495v1.pdf | |
PWC | https://paperswithcode.com/paper/a-family-of-neighborhood-contingency-logics |
Repo | |
Framework | |
Large Neighborhood-Based Metaheuristic and Branch-and-Price for the Pickup and Delivery Problem with Split Loads
Title | Large Neighborhood-Based Metaheuristic and Branch-and-Price for the Pickup and Delivery Problem with Split Loads |
Authors | Matheus Nohra Haddad, Rafael Martinelli, Thibaut Vidal, Luiz Satoru Ochi, Simone Martins, Marcone Jamilson Freitas Souza, Richard Hartl |
Abstract | We consider the multi-vehicle one-to-one pickup and delivery problem with split loads, a NP-hard problem linked with a variety of applications for bulk product transportation, bike-sharing systems and inventory re-balancing. This problem is notoriously difficult due to the interaction of two challenging vehicle routing attributes, “pickups and deliveries” and “split deliveries”. This possibly leads to optimal solutions of a size that grows exponentially with the instance size, containing multiple visits per customer pair, even in the same route. To solve this problem, we propose an iterated local search metaheuristic as well as a branch-and-price algorithm. The core of the metaheuristic consists of a new large neighborhood search, which reduces the problem of finding the best insertion combination of a pickup and delivery pair into a route (with possible splits) to a resource-constrained shortest path and knapsack problem. Similarly, the branch-and-price algorithm uses sophisticated labeling techniques, route relaxations, pre-processing and branching rules for an efficient resolution. Our computational experiments on classical single-vehicle instances demonstrate the excellent performance of the metaheuristic, which produces new best known solutions for 92 out of 93 test instances, and outperforms all previous algorithms. Experimental results on new multi-vehicle instances with distance constraints are also reported. The branch-and-price algorithm produces optimal solutions for instances with up to 20 pickup-and-delivery pairs, and very accurate solutions are found by the metaheuristic. |
Tasks | |
Published | 2018-02-18 |
URL | http://arxiv.org/abs/1802.06318v1 |
http://arxiv.org/pdf/1802.06318v1.pdf | |
PWC | https://paperswithcode.com/paper/large-neighborhood-based-metaheuristic-and |
Repo | |
Framework | |