January 27, 2020

3071 words 15 mins read

Paper Group ANR 1305

Power Weighted Shortest Paths for Clustering Euclidean Data. Cyclic Functional Mapping: Self-supervised correspondence between non-isometric deformable shapes. Deep Reinforcement Learning for Online Advertising in Recommender Systems. Using Restart Heuristics to Improve Agent Performance in Angry Birds. Flash X-ray diffraction imaging in 3D: a prop …

Power Weighted Shortest Paths for Clustering Euclidean Data


Title	Power Weighted Shortest Paths for Clustering Euclidean Data
Authors	Daniel Mckenzie, Steven Damelin
Abstract	We study the use of power weighted shortest path distance functions for clustering high dimensional Euclidean data, under the assumption that the data is drawn from a collection of disjoint low dimensional manifolds. We argue, theoretically and experimentally, that this leads to higher clustering accuracy. We also present a fast algorithm for computing these distances.
Tasks
Published	2019-05-30
URL	https://arxiv.org/abs/1905.13345v3
PDF	https://arxiv.org/pdf/1905.13345v3.pdf
PWC	https://paperswithcode.com/paper/power-weighted-shortest-paths-for
Repo
Framework

Cyclic Functional Mapping: Self-supervised correspondence between non-isometric deformable shapes


Title	Cyclic Functional Mapping: Self-supervised correspondence between non-isometric deformable shapes
Authors	Dvir Ginzburg, Dan Raviv
Abstract	We present the first utterly self-supervised network for dense correspondence mapping between non-isometric shapes. The task of alignment in non-Euclidean domains is one of the most fundamental and crucial problems in computer vision. As 3D scanners can generate highly complex and dense models, the mission of finding dense mappings between those models is vital. The novelty of our solution is based on a cyclic mapping between metric spaces, where the distance between a pair of points should remain invariant after the full cycle. As the same learnable rules that generate the point-wise descriptors apply in both directions, the network learns invariant structures without any labels while coping with non-isometric deformations. We show here state-of-the-art-results by a large margin for a variety of tasks compared to known self-supervised and supervised methods.
Tasks
Published	2019-12-03
URL	https://arxiv.org/abs/1912.01249v1
PDF	https://arxiv.org/pdf/1912.01249v1.pdf
PWC	https://paperswithcode.com/paper/cyclic-functional-mapping-self-supervised
Repo
Framework

Deep Reinforcement Learning for Online Advertising in Recommender Systems


Title	Deep Reinforcement Learning for Online Advertising in Recommender Systems
Authors	Xiangyu Zhao, Changsheng Gu, Haoshenglun Zhang, Xiaobing Liu, Xiwang Yang, Jiliang Tang
Abstract	With the recent prevalence of Reinforcement Learning (RL), there have been tremendous interests in utilizing RL for online advertising in recommendation platforms (e.g. e-commerce and news feed sites). However, most RL-based advertising algorithms focus on solely optimizing the revenue of ads while ignoring possible negative influence of ads on user experience of recommended items (products, articles and videos). Developing an optimal advertising algorithm in recommendations faces immense challenges because interpolating ads improperly or too frequently may decrease user experience, while interpolating fewer ads will reduce the advertising revenue. Thus, in this paper, we propose a novel advertising strategy for the rec/ads trade-off. To be specific, we develop a reinforcement learning based framework that can continuously update its advertising strategies and maximize reward in the long run. Given a recommendation list, we design a novel Deep Q-network architecture that can determine three internally related tasks jointly, i.e., (i) whether to interpolate an ad or not in the recommendation list, and if yes, (ii) the optimal ad and (iii) the optimal location to interpolate. The experimental results based on real-world data demonstrate the effectiveness of the proposed framework.
Tasks	Recommendation Systems
Published	2019-09-09
URL	https://arxiv.org/abs/1909.03602v2
PDF	https://arxiv.org/pdf/1909.03602v2.pdf
PWC	https://paperswithcode.com/paper/deep-reinforcement-learning-for-online-1
Repo
Framework

Using Restart Heuristics to Improve Agent Performance in Angry Birds


Title	Using Restart Heuristics to Improve Agent Performance in Angry Birds
Authors	Tommy Liu, Jochen Renz, Peng Zhang, Matthew Stephenson
Abstract	Over the past few years the Angry Birds AI competition has been held in an attempt to develop intelligent agents that can successfully and efficiently solve levels for the video game Angry Birds. Many different agents and strategies have been developed to solve the complex and challenging physical reasoning problems associated with such a game. However none of these agents attempt one of the key strategies which humans employ to solve Angry Birds levels, which is restarting levels. Restarting is important in Angry Birds because sometimes the level is no longer solvable or some given shot made has little to no benefit towards the ultimate goal of the game. This paper proposes a framework and experimental evaluation for when to restart levels in Angry Birds. We demonstrate that restarting is a viable strategy to improve agent performance in many cases.
Tasks
Published	2019-05-30
URL	https://arxiv.org/abs/1905.12877v1
PDF	https://arxiv.org/pdf/1905.12877v1.pdf
PWC	https://paperswithcode.com/paper/using-restart-heuristics-to-improve-agent
Repo
Framework

Flash X-ray diffraction imaging in 3D: a proposed analysis pipeline


Title	Flash X-ray diffraction imaging in 3D: a proposed analysis pipeline
Authors	Jing Liu, Stefan Engblom, Carl Nettelblad
Abstract	Modern Flash X-ray diffraction Imaging (FXI) acquires diffraction signals from single biomolecules at a high repetition rate from X-ray Free Electron Lasers (XFELs), easily obtaining millions of 2D diffraction patterns from a single experiment. Due to the stochastic nature of FXI experiments and the massive volumes of data, retrieving 3D electron densities from raw 2D diffraction patterns is a challenging and time-consuming task. We propose a semi-automatic data analysis pipeline for FXI experiments, which includes four steps: hit finding and preliminary filtering, pattern classification, 3D Fourier reconstruction, and post analysis. We also include a recently developed bootstrap methodology in the post-analysis step for uncertainty analysis and quality control. To achieve the best possible resolution, we further suggest using background subtraction, signal windowing, and convex optimization techniques when retrieving the Fourier phases in the post-analysis step. As an application example, we quantified the 3D electron structure of the PR772 virus using the proposed data-analysis pipeline. The retrieved structure was above the detector-edge resolution and clearly showed the pseudo-icosahedral capsid of the PR772.
Tasks
Published	2019-10-30
URL	https://arxiv.org/abs/1910.14029v2
PDF	https://arxiv.org/pdf/1910.14029v2.pdf
PWC	https://paperswithcode.com/paper/flash-x-ray-diffraction-imaging-in-3d-a
Repo
Framework

Adversarial Robustness of Flow-Based Generative Models


Title	Adversarial Robustness of Flow-Based Generative Models
Authors	Phillip Pope, Yogesh Balaji, Soheil Feizi
Abstract	Flow-based generative models leverage invertible generator functions to fit a distribution to the training data using maximum likelihood. Despite their use in several application domains, robustness of these models to adversarial attacks has hardly been explored. In this paper, we study adversarial robustness of flow-based generative models both theoretically (for some simple models) and empirically (for more complex ones). First, we consider a linear flow-based generative model and compute optimal sample-specific and universal adversarial perturbations that maximally decrease the likelihood scores. Using this result, we study the robustness of the well-known adversarial training procedure, where we characterize the fundamental trade-off between model robustness and accuracy. Next, we empirically study the robustness of two prominent deep, non-linear, flow-based generative models, namely GLOW and RealNVP. We design two types of adversarial attacks; one that minimizes the likelihood scores of in-distribution samples, while the other that maximizes the likelihood scores of out-of-distribution ones. We find that GLOW and RealNVP are extremely sensitive to both types of attacks. Finally, using a hybrid adversarial training procedure, we significantly boost the robustness of these generative models.
Tasks
Published	2019-11-20
URL	https://arxiv.org/abs/1911.08654v1
PDF	https://arxiv.org/pdf/1911.08654v1.pdf
PWC	https://paperswithcode.com/paper/adversarial-robustness-of-flow-based
Repo
Framework

Exploration of Self-Propelling Droplets Using a Curiosity Driven Robotic Assistant


Title	Exploration of Self-Propelling Droplets Using a Curiosity Driven Robotic Assistant
Authors	Jonathan Grizou, Laurie J. Points, Abhishek Sharma, Leroy Cronin
Abstract	We describe a chemical robotic assistant equipped with a curiosity algorithm (CA) that can efficiently explore the state a complex chemical system can exhibit. The CA-robot is designed to explore formulations in an open-ended way with no explicit optimization target. By applying the CA-robot to the study of self-propelling multicomponent oil-in-water droplets, we are able to observe an order of magnitude more variety of droplet behaviours than possible with a random parameter search and given the same budget. We demonstrate that the CA-robot enabled the discovery of a sudden and highly specific response of droplets to slight temperature changes. Six modes of self-propelled droplets motion were identified and classified using a time-temperature phase diagram and probed using a variety of techniques including NMR. This work illustrates how target free search can significantly increase the rate of unpredictable observations leading to new discoveries with potential applications in formulation chemistry.
Tasks
Published	2019-04-22
URL	http://arxiv.org/abs/1904.12635v1
PDF	http://arxiv.org/pdf/1904.12635v1.pdf
PWC	https://paperswithcode.com/paper/190412635
Repo
Framework

Regularizing Generative Models Using Knowledge of Feature Dependence


Title	Regularizing Generative Models Using Knowledge of Feature Dependence
Authors	Naoya Takeishi, Yoshinobu Kawahara
Abstract	Generative modeling is a fundamental problem in machine learning with many potential applications. Efficient learning of generative models requires available prior knowledge to be exploited as much as possible. In this paper, we propose a method to exploit prior knowledge of relative dependence between features for learning generative models. Such knowledge is available, for example, when side-information on features is present. We incorporate the prior knowledge by forcing marginals of the learned generative model to follow a prescribed relative feature dependence. To this end, we formulate a regularization term using a kernel-based dependence criterion. The proposed method can be incorporated straightforwardly into many optimization-based learning schemes of generative models, including variational autoencoders and generative adversarial networks. We show the effectiveness of the proposed method in experiments with multiple types of datasets and models.
Tasks
Published	2019-02-06
URL	http://arxiv.org/abs/1902.02068v1
PDF	http://arxiv.org/pdf/1902.02068v1.pdf
PWC	https://paperswithcode.com/paper/regularizing-generative-models-using
Repo
Framework

Machine learning for long-distance quantum communication


Title	Machine learning for long-distance quantum communication
Authors	Julius Wallnöfer, Alexey A. Melnikov, Wolfgang Dür, Hans J. Briegel
Abstract	Machine learning can help us in solving problems in the context big data analysis and classification, as well as in playing complex games such as Go. But can it also be used to find novel protocols and algorithms for applications such as large-scale quantum communication? Here we show that machine learning can be used to identify central quantum protocols, including teleportation, entanglement purification and the quantum repeater. These schemes are of importance in long-distance quantum communication, and their discovery has shaped the field of quantum information processing. However, the usefulness of learning agents goes beyond the mere re-production of known protocols; the same approach allows one to find improved solutions to long-distance communication problems, in particular when dealing with asymmetric situations where channel noise and segment distance are non-uniform. Our findings are based on the use of projective simulation, a model of a learning agent that combines reinforcement learning and decision making in a physically motivated framework. The learning agent is provided with a universal gate set, and the desired task is specified via a reward scheme. From a technical perspective, the learning agent has to deal with stochastic environments and reactions. We utilize an idea reminiscent of hierarchical skill acquisition, where solutions to sub-problems are learned and re-used in the overall scheme. This is of particular importance in the development of long-distance communication schemes, and opens the way for using machine learning in the design and implementation of quantum networks.
Tasks	Decision Making
Published	2019-04-24
URL	http://arxiv.org/abs/1904.10797v1
PDF	http://arxiv.org/pdf/1904.10797v1.pdf
PWC	https://paperswithcode.com/paper/machine-learning-for-long-distance-quantum
Repo
Framework

Information Plane Analysis of Deep Neural Networks via Matrix-Based Renyi’s Entropy and Tensor Kernels


Title	Information Plane Analysis of Deep Neural Networks via Matrix-Based Renyi’s Entropy and Tensor Kernels
Authors	Kristoffer Wickstrøm, Sigurd Løkse, Michael Kampffmeyer, Shujian Yu, Jose Principe, Robert Jenssen
Abstract	Analyzing deep neural networks (DNNs) via information plane (IP) theory has gained tremendous attention recently as a tool to gain insight into, among others, their generalization ability. However, it is by no means obvious how to estimate mutual information (MI) between each hidden layer and the input/desired output, to construct the IP. For instance, hidden layers with many neurons require MI estimators with robustness towards the high dimensionality associated with such layers. MI estimators should also be able to naturally handle convolutional layers, while at the same time being computationally tractable to scale to large networks. None of the existing IP methods to date have been able to study truly deep Convolutional Neural Networks (CNNs), such as the e.g.\ VGG-16. In this paper, we propose an IP analysis using the new matrix–based R'enyi’s entropy coupled with tensor kernels over convolutional layers, leveraging the power of kernel methods to represent properties of the probability distribution independently of the dimensionality of the data. The obtained results shed new light on the previous literature concerning small-scale DNNs, however using a completely new approach. Importantly, the new framework enables us to provide the first comprehensive IP analysis of contemporary large-scale DNNs and CNNs, investigating the different training phases and providing new insights into the training dynamics of large-scale neural networks.
Tasks
Published	2019-09-25
URL	https://arxiv.org/abs/1909.11396v1
PDF	https://arxiv.org/pdf/1909.11396v1.pdf
PWC	https://paperswithcode.com/paper/information-plane-analysis-of-deep-neural
Repo
Framework

Fitting, Comparison, and Alignment of Trajectories on Positive Semi-Definite Matrices with Application to Action Recognition


Title	Fitting, Comparison, and Alignment of Trajectories on Positive Semi-Definite Matrices with Application to Action Recognition
Authors	Benjamin Szczapa, Mohamed Daoudi, Stefano Berretti, Alberto Del Bimbo, Pietro Pala, Estelle Massart
Abstract	In this paper, we tackle the problem of action recognition using body skeletons extracted from video sequences. Our approach lies in the continuity of recent works representing video frames by Gramian matrices that describe a trajectory on the Riemannian manifold of positive-semidefinite matrices of fixed rank. In comparison with previous works, the manifold of fixed-rank positive-semidefinite matrices is here endowed with a different metric, and we resort to different algorithms for the curve fitting and temporal alignment steps. We evaluated our approach on three publicly available datasets (UTKinect-Action3D, KTH-Action and UAV-Gesture). The results of the proposed approach are competitive with respect to state-of-the-art methods, while only involving body skeletons.
Tasks
Published	2019-08-01
URL	https://arxiv.org/abs/1908.00646v3
PDF	https://arxiv.org/pdf/1908.00646v3.pdf
PWC	https://paperswithcode.com/paper/fitting-comparison-and-alignment-of
Repo
Framework

Deep MR Fingerprinting with total-variation and low-rank subspace priors


Title	Deep MR Fingerprinting with total-variation and low-rank subspace priors
Authors	Mohammad Golbabaee, Carolin M. Pirkl, Marion I. Menzel, Guido Buonincontri, Pedro A. Gómez
Abstract	Deep learning (DL) has recently emerged to address the heavy storage and computation requirements of the baseline dictionary-matching (DM) for Magnetic Resonance Fingerprinting (MRF) reconstruction. Fed with non-iterated back-projected images, the network is unable to fully resolve spatially-correlated corruptions caused from the undersampling artefacts. We propose an accelerated iterative reconstruction to minimize these artefacts before feeding into the network. This is done through a convex regularization that jointly promotes spatio-temporal regularities of the MRF time-series. Except for training, the rest of the parameter estimation pipeline is dictionary-free. We validate the proposed approach on synthetic and in-vivo datasets.
Tasks	Magnetic Resonance Fingerprinting, Time Series
Published	2019-02-26
URL	http://arxiv.org/abs/1902.10205v1
PDF	http://arxiv.org/pdf/1902.10205v1.pdf
PWC	https://paperswithcode.com/paper/deep-mr-fingerprinting-with-total-variation
Repo
Framework

Towards Segmenting Anything That Moves


Title	Towards Segmenting Anything That Moves
Authors	Achal Dave, Pavel Tokmakov, Deva Ramanan
Abstract	Detecting and segmenting individual objects, regardless of their category, is crucial for many applications such as action detection or robotic interaction. While this problem has been well-studied under the classic formulation of spatio-temporal grouping, state-of-the-art approaches do not make use of learning-based methods. To bridge this gap, we propose a simple learning-based approach for spatio-temporal grouping. Our approach leverages motion cues from optical flow as a bottom-up signal for separating objects from each other. Motion cues are then combined with appearance cues that provide a generic objectness prior for capturing the full extent of objects. We show that our approach outperforms all prior work on the benchmark FBMS dataset. One potential worry with learning-based methods is that they might overfit to the particular type of objects that they have been trained on. To address this concern, we propose two new benchmarks for generic, moving object detection, and show that our model matches top-down methods on common categories, while significantly out-performing both top-down and bottom-up methods on never-before-seen categories.
Tasks	Action Detection, Instance Segmentation, Motion Estimation, Motion Segmentation, Object Detection, Optical Flow Estimation, Semantic Segmentation, Video Semantic Segmentation
Published	2019-02-11
URL	https://arxiv.org/abs/1902.03715v4
PDF	https://arxiv.org/pdf/1902.03715v4.pdf
PWC	https://paperswithcode.com/paper/towards-segmenting-everything-that-moves
Repo
Framework

JND-SalCAR: A Novel JND-based Saliency-Channel Attention Residual Network for Image Quality Prediction


Title	JND-SalCAR: A Novel JND-based Saliency-Channel Attention Residual Network for Image Quality Prediction
Authors	Soomin Seo, Sehwan Ki, Munchurl Kim
Abstract	In image quality enhancement processing, it is the most important to predict how humans perceive processed images since human observers are the ultimate receivers of the images. Thus, objective image quality assessment (IQA) methods based on human visual sensitivity from psychophysical experiments have been extensively studied. Thanks to the powerfulness of deep convolutional neural networks (CNN), many CNN based IQA models have been studied. However, previous CNN-based IQA models have not fully utilized the characteristics of human visual systems (HVS) for IQA problems by simply entrusting everything to CNN where the CNN-based models are often trained as a regressor to predict the scores of subjective quality assessment obtained from IQA datasets. In this paper, we propose a novel JND-based saliency-channel attention residual network for image quality assessment, called JND-SalCAR, where the human psychophysical characteristics such as visual saliency and just noticeable difference (JND) are effectively incorporated. We newly propose a SalCAR block so that perceptually important features can be extracted by using a saliency-based spatial attention and a channel attention. In addition, the visual saliency map is further used as a guideline for predicting the patch weight map in order to afford a stable training of end-to-end optimization for the JND-SalCAR. To our best knowledge, our work is the first HVS-inspired trainable IQA network that considers both the visual saliency and JND characteristics of HVS. We evaluate the proposed JND-SalCAR on large IQA datasets where it outperforms all the recent state-of-the-art IQA methods.
Tasks	Image Quality Assessment
Published	2019-02-14
URL	https://arxiv.org/abs/1902.05316v3
PDF	https://arxiv.org/pdf/1902.05316v3.pdf
PWC	https://paperswithcode.com/paper/deep-hvs-iqa-net-human-visual-system-inspired
Repo
Framework

Synaptic Partner Assignment Using Attentional Voxel Association Networks


Title	Synaptic Partner Assignment Using Attentional Voxel Association Networks
Authors	Nicholas Turner, Kisuk Lee, Ran Lu, Jingpeng Wu, Dodam Ih, H. Sebastian Seung
Abstract	Connectomics aims to recover a complete set of synaptic connections within a dataset imaged by volume electron microscopy. Many systems have been proposed for locating synapses, and recent research has included a way to identify the synaptic partners that communicate at a synaptic cleft. We re-frame the problem of identifying synaptic partners as directly generating the mask of the synaptic partners from a given cleft. We train a convolutional network to perform this task. The network takes the local image context and a binary mask representing a single cleft as input. It is trained to produce two binary output masks: one which labels the voxels of the presynaptic partner within the input image, and another similar labeling for the postsynaptic partner. The cleft mask acts as an attentional gating signal for the network. We find that an implementation of this approach performs well on a dataset of mouse somatosensory cortex, and evaluate it as part of a combined system to predict both clefts and connections.
Tasks
Published	2019-04-22
URL	https://arxiv.org/abs/1904.09947v2
PDF	https://arxiv.org/pdf/1904.09947v2.pdf
PWC	https://paperswithcode.com/paper/synaptic-partner-assignment-using-attentional
Repo
Framework