October 18, 2019

3209 words 16 mins read

Paper Group ANR 493

Diversity-Driven Exploration Strategy for Deep Reinforcement Learning. Variance Reduction for Reinforcement Learning in Input-Driven Environments. Pragmatic approach to structured data querying via natural language interface. End-to-end depth from motion with stabilized monocular videos. The Effects of Super-Resolution on Object Detection Performan …

Diversity-Driven Exploration Strategy for Deep Reinforcement Learning


Title	Diversity-Driven Exploration Strategy for Deep Reinforcement Learning
Authors	Zhang-Wei Hong, Tzu-Yun Shann, Shih-Yang Su, Yi-Hsiang Chang, Chun-Yi Lee
Abstract	Efficient exploration remains a challenging research problem in reinforcement learning, especially when an environment contains large state spaces, deceptive local optima, or sparse rewards. To tackle this problem, we present a diversity-driven approach for exploration, which can be easily combined with both off- and on-policy reinforcement learning algorithms. We show that by simply adding a distance measure to the loss function, the proposed methodology significantly enhances an agent’s exploratory behaviors, and thus preventing the policy from being trapped in local optima. We further propose an adaptive scaling method for stabilizing the learning process. Our experimental results in Atari 2600 show that our method outperforms baseline approaches in several tasks in terms of mean scores and exploration efficiency.
Tasks	Efficient Exploration
Published	2018-02-13
URL	http://arxiv.org/abs/1802.04564v2
PDF	http://arxiv.org/pdf/1802.04564v2.pdf
PWC	https://paperswithcode.com/paper/diversity-driven-exploration-strategy-for
Repo
Framework

Variance Reduction for Reinforcement Learning in Input-Driven Environments


Title	Variance Reduction for Reinforcement Learning in Input-Driven Environments
Authors	Hongzi Mao, Shaileshh Bojja Venkatakrishnan, Malte Schwarzkopf, Mohammad Alizadeh
Abstract	We consider reinforcement learning in input-driven environments, where an exogenous, stochastic input process affects the dynamics of the system. Input processes arise in many applications, including queuing systems, robotics control with disturbances, and object tracking. Since the state dynamics and rewards depend on the input process, the state alone provides limited information for the expected future returns. Therefore, policy gradient methods with standard state-dependent baselines suffer high variance during training. We derive a bias-free, input-dependent baseline to reduce this variance, and analytically show its benefits over state-dependent baselines. We then propose a meta-learning approach to overcome the complexity of learning a baseline that depends on a long sequence of inputs. Our experimental results show that across environments from queuing systems, computer networks, and MuJoCo robotic locomotion, input-dependent baselines consistently improve training stability and result in better eventual policies.
Tasks	Meta-Learning, Object Tracking, Policy Gradient Methods
Published	2018-07-06
URL	http://arxiv.org/abs/1807.02264v3
PDF	http://arxiv.org/pdf/1807.02264v3.pdf
PWC	https://paperswithcode.com/paper/variance-reduction-for-reinforcement-learning
Repo
Framework

Pragmatic approach to structured data querying via natural language interface


Title	Pragmatic approach to structured data querying via natural language interface
Authors	Aliaksei Vertsel, Mikhail Rumiantsau
Abstract	As the use of technology increases and data analysis becomes integral in many businesses, the ability to quickly access and interpret data has become more important than ever. Information retrieval technologies are being utilized by organizations and companies to manage their information systems and processes. Despite information retrieval of a large amount of data being efficient organized in relational databases, a user still needs to master the DB language/schema to completely formulate the queries. This puts a burden on organizations and companies to hire employees that are proficient in DB languages/schemas to formulate queries. To reduce some of the burden on already overstretched data teams, many organizations are looking for tools that allow non-developers to query their databases. Unfortunately, writing a valid SQL query that answers the question a user is trying to ask isn’t always easy. Even seemingly simple questions, like “Which start-up companies received more than $200M in funding?” can actually be very hard to answer, let alone convert into a SQL query. How do you define start-up companies? By size, location, duration of time they have been incorporated? This may be fine if a user is working with a database they’re already familiar with, but what if users are not familiar with the database. What is needed is a centralized system that can effectively translate natural language queries into specific database queries for different customer database types. There is a number of factors that can dramatically affect the system architecture and the set of algorithms used to translate NL queries into a structured query representation.
Tasks	Information Retrieval
Published	2018-07-02
URL	http://arxiv.org/abs/1807.00791v1
PDF	http://arxiv.org/pdf/1807.00791v1.pdf
PWC	https://paperswithcode.com/paper/pragmatic-approach-to-structured-data
Repo
Framework

End-to-end depth from motion with stabilized monocular videos


Title	End-to-end depth from motion with stabilized monocular videos
Authors	Clément Pinard, Laure Chevalley, Antoine Manzanera, David Filliat
Abstract	We propose a depth map inference system from monocular videos based on a novel dataset for navigation that mimics aerial footage from gimbal stabilized monocular camera in rigid scenes. Unlike most navigation datasets, the lack of rotation implies an easier structure from motion problem which can be leveraged for different kinds of tasks such as depth inference and obstacle avoidance. We also propose an architecture for end-to-end depth inference with a fully convolutional network. Results show that although tied to camera inner parameters, the problem is locally solvable and leads to good quality depth prediction.
Tasks	Depth Estimation
Published	2018-09-12
URL	http://arxiv.org/abs/1809.04453v1
PDF	http://arxiv.org/pdf/1809.04453v1.pdf
PWC	https://paperswithcode.com/paper/end-to-end-depth-from-motion-with-stabilized
Repo
Framework

The Effects of Super-Resolution on Object Detection Performance in Satellite Imagery


Title	The Effects of Super-Resolution on Object Detection Performance in Satellite Imagery
Authors	Jacob Shermeyer, Adam Van Etten
Abstract	We explore the application of super-resolution techniques to satellite imagery, and the effects of these techniques on object detection algorithm performance. Specifically, we enhance satellite imagery beyond its native resolution, and test if we can identify various types of vehicles, planes, and boats with greater accuracy than native resolution. Using the Very Deep Super-Resolution (VDSR) framework and a custom Random Forest Super-Resolution (RFSR) framework we generate enhancement levels of 2x, 4x, and 8x over five distinct resolutions ranging from 30 cm to 4.8 meters. Using both native and super-resolved data, we then train several custom detection models using the SIMRDWN object detection framework. SIMRDWN combines a number of popular object detection algorithms (e.g. SSD, YOLO) into a unified framework that is designed to rapidly detect objects in large satellite images. This approach allows us to quantify the effects of super-resolution techniques on object detection performance across multiple classes and resolutions. We also quantify the performance of object detection as a function of native resolution and object pixel size. For our test set we note that performance degrades from mean average precision (mAP) = 0.53 at 30 cm resolution, down to mAP = 0.11 at 4.8 m resolution. Super-resolving native 30 cm imagery to 15 cm yields the greatest benefit; a 13-36% improvement in mAP. Super-resolution is less beneficial at coarser resolutions, though still provides a small improvement in performance.
Tasks	Object Detection, Super-Resolution
Published	2018-12-10
URL	http://arxiv.org/abs/1812.04098v3
PDF	http://arxiv.org/pdf/1812.04098v3.pdf
PWC	https://paperswithcode.com/paper/the-effects-of-super-resolution-on-object
Repo
Framework

Improved Techniques for GAN based Facial Inpainting


Title	Improved Techniques for GAN based Facial Inpainting
Authors	Avisek Lahiri, Arnav Jain, Divyasri Nadendla, Prabir Kumar Biswas
Abstract	In this paper we present several architectural and optimization recipes for generative adversarial network(GAN) based facial semantic inpainting. Current benchmark models are susceptible to initial solutions of non-convex optimization criterion of GAN based inpainting. We present an end-to-end trainable parametric network to deterministically start from good initial solutions leading to more photo realistic reconstructions with significant optimization speed up. For the first time, we show how to efficiently extend GAN based single image inpainter models to sequences by a)learning to initialize a temporal window of solutions with a recurrent neural network and b)imposing a temporal smoothness loss(during iterative optimization) to respect the redundancy in temporal dimension of a sequence. We conduct comprehensive empirical evaluations on CelebA images and pseudo sequences followed by real life videos of VidTIMIT dataset. The proposed method significantly outperforms current GAN based state-of-the-art in terms of reconstruction quality with a simultaneous speedup of over 15$\times$. We also show that our proposed model is better in preserving facial identity in a sequence even without explicitly using any face recognition module during training.
Tasks	Face Recognition, Facial Inpainting
Published	2018-10-20
URL	http://arxiv.org/abs/1810.08774v1
PDF	http://arxiv.org/pdf/1810.08774v1.pdf
PWC	https://paperswithcode.com/paper/improved-techniques-for-gan-based-facial
Repo
Framework

Improving Explainable Recommendations with Synthetic Reviews


Title	Improving Explainable Recommendations with Synthetic Reviews
Authors	Sixun Ouyang, Aonghus Lawlor, Felipe Costa, Peter Dolog
Abstract	An important task for a recommender system to provide interpretable explanations for the user. This is important for the credibility of the system. Current interpretable recommender systems tend to focus on certain features known to be important to the user and offer their explanations in a structured form. It is well known that user generated reviews and feedback from reviewers have strong leverage over the users’ decisions. On the other hand, recent text generation works have been shown to generate text of similar quality to human written text, and we aim to show that generated text can be successfully used to explain recommendations. In this paper, we propose a framework consisting of popular review-oriented generation models aiming to create personalised explanations for recommendations. The interpretations are generated at both character and word levels. We build a dataset containing reviewers’ feedback from the Amazon books review dataset. Our cross-domain experiments are designed to bridge from natural language processing to the recommender system domain. Besides language model evaluation methods, we employ DeepCoNN, a novel review-oriented recommender system using a deep neural network, to evaluate the recommendation performance of generated reviews by root mean square error (RMSE). We demonstrate that the synthetic personalised reviews have better recommendation performance than human written reviews. To our knowledge, this presents the first machine-generated natural language explanations for rating prediction.
Tasks	Language Modelling, Recommendation Systems, Text Generation
Published	2018-07-18
URL	http://arxiv.org/abs/1807.06978v1
PDF	http://arxiv.org/pdf/1807.06978v1.pdf
PWC	https://paperswithcode.com/paper/improving-explainable-recommendations-with
Repo
Framework

Explaining Deep Learning Models using Causal Inference


Title	Explaining Deep Learning Models using Causal Inference
Authors	Tanmayee Narendra, Anush Sankaran, Deepak Vijaykeerthy, Senthil Mani
Abstract	Although deep learning models have been successfully applied to a variety of tasks, due to the millions of parameters, they are becoming increasingly opaque and complex. In order to establish trust for their widespread commercial use, it is important to formalize a principled framework to reason over these models. In this work, we use ideas from causal inference to describe a general framework to reason over CNN models. Specifically, we build a Structural Causal Model (SCM) as an abstraction over a specific aspect of the CNN. We also formulate a method to quantitatively rank the filters of a convolution layer according to their counterfactual importance. We illustrate our approach with popular CNN architectures such as LeNet5, VGG19, and ResNet32.
Tasks	Causal Inference
Published	2018-11-11
URL	http://arxiv.org/abs/1811.04376v1
PDF	http://arxiv.org/pdf/1811.04376v1.pdf
PWC	https://paperswithcode.com/paper/explaining-deep-learning-models-using-causal
Repo
Framework

Fast MVAE: Joint separation and classification of mixed sources based on multichannel variational autoencoder with auxiliary classifier


Title	Fast MVAE: Joint separation and classification of mixed sources based on multichannel variational autoencoder with auxiliary classifier
Authors	Li Li, Hirokazu Kameoka, Shoji Makino
Abstract	This paper proposes an alternative algorithm for multichannel variational autoencoder (MVAE), a recently proposed multichannel source separation approach. While MVAE is notable in its impressive source separation performance, the convergence-guaranteed optimization algorithm and that it allows us to estimate source-class labels simultaneously with source separation, there are still two major drawbacks, i.e., the high computational complexity and unsatisfactory source classification accuracy. To overcome these drawbacks, the proposed method employs an auxiliary classifier VAE, an information-theoretic extension of the conditional VAE, for learning the generative model of the source spectrograms. Furthermore, with the trained auxiliary classifier, we introduce a novel algorithm for the optimization that is able to not only reduce the computational time but also improve the source classification performance. We call the proposed method “fast MVAE (fMVAE)". Experimental evaluations revealed that fMVAE achieved comparative source separation performance to MVAE and about 80% source classification accuracy rate while it reduced about 93% computational time.
Tasks
Published	2018-12-16
URL	http://arxiv.org/abs/1812.06391v2
PDF	http://arxiv.org/pdf/1812.06391v2.pdf
PWC	https://paperswithcode.com/paper/fast-mvae-joint-separation-and-classification
Repo
Framework

Massively scalable Sinkhorn distances via the Nyström method


Title	Massively scalable Sinkhorn distances via the Nyström method
Authors	Jason Altschuler, Francis Bach, Alessandro Rudi, Jonathan Niles-Weed
Abstract	The Sinkhorn “distance”, a variant of the Wasserstein distance with entropic regularization, is an increasingly popular tool in machine learning and statistical inference. However, the time and memory requirements of standard algorithms for computing this distance grow quadratically with the size of the data, making them prohibitively expensive on massive data sets. In this work, we show that this challenge is surprisingly easy to circumvent: combining two simple techniques—the Nystr"om method and Sinkhorn scaling—provably yields an accurate approximation of the Sinkhorn distance with significantly lower time and memory requirements than other approaches. We prove our results via new, explicit analyses of the Nystr"om method and of the stability properties of Sinkhorn scaling. We validate our claims experimentally by showing that our approach easily computes Sinkhorn distances on data sets hundreds of times larger than can be handled by other techniques.
Tasks
Published	2018-12-12
URL	https://arxiv.org/abs/1812.05189v3
PDF	https://arxiv.org/pdf/1812.05189v3.pdf
PWC	https://paperswithcode.com/paper/massively-scalable-sinkhorn-distances-via-the
Repo
Framework

Improving Mild Cognitive Impairment Prediction via Reinforcement Learning and Dialogue Simulation


Title	Improving Mild Cognitive Impairment Prediction via Reinforcement Learning and Dialogue Simulation
Authors	Fengyi Tang, Kaixiang Lin, Ikechukwu Uchendu, Hiroko H. Dodge, Jiayu Zhou
Abstract	Mild cognitive impairment (MCI) is a prodromal phase in the progression from normal aging to dementia, especially Alzheimers disease. Even though there is mild cognitive decline in MCI patients, they have normal overall cognition and thus is challenging to distinguish from normal aging. Using transcribed data obtained from recorded conversational interactions between participants and trained interviewers, and applying supervised learning models to these data, a recent clinical trial has shown a promising result in differentiating MCI from normal aging. However, the substantial amount of interactions with medical staff can still incur significant medical care expenses in practice. In this paper, we propose a novel reinforcement learning (RL) framework to train an efficient dialogue agent on existing transcripts from clinical trials. Specifically, the agent is trained to sketch disease-specific lexical probability distribution, and thus to converse in a way that maximizes the diagnosis accuracy and minimizes the number of conversation turns. We evaluate the performance of the proposed reinforcement learning framework on the MCI diagnosis from a real clinical trial. The results show that while using only a few turns of conversation, our framework can significantly outperform state-of-the-art supervised learning approaches.
Tasks
Published	2018-02-18
URL	http://arxiv.org/abs/1802.06428v1
PDF	http://arxiv.org/pdf/1802.06428v1.pdf
PWC	https://paperswithcode.com/paper/improving-mild-cognitive-impairment
Repo
Framework

Patch-based Evaluation of Dense Image Matching Quality


Title	Patch-based Evaluation of Dense Image Matching Quality
Authors	Zhenchao Zhang, Markus Gerke, George Vosselman, Michael Ying Yang
Abstract	Airborne laser scanning and photogrammetry are two main techniques to obtain 3D data representing the object surface. Due to the high cost of laser scanning, we want to explore the potential of using point clouds derived by dense image matching (DIM), as effective alternatives to laser scanning data. We present a framework to evaluate point clouds from dense image matching and derived Digital Surface Models (DSM) based on automatically extracted sample patches. Dense matching error and noise level are evaluated quantitatively at both the local level and whole block level. Experiments show that the optimal vertical accuracy achieved by dense matching is as follows: the mean offset to the reference data is 0.1 Ground Sampling Distance (GSD); the maximum offset goes up to 1.0 GSD. When additional oblique images are used in dense matching, the mean deviation, the variation of mean deviation and the level of random noise all get improved. We also detect a bias between the point cloud and DSM from a single photogrammetric workflow. This framework also allows to reveal inhomogeneity in the distribution of the dense matching errors due to over-fitted BBA network. Meanwhile, suggestions are given on the photogrammetric quality control.
Tasks
Published	2018-07-25
URL	http://arxiv.org/abs/1807.09546v1
PDF	http://arxiv.org/pdf/1807.09546v1.pdf
PWC	https://paperswithcode.com/paper/patch-based-evaluation-of-dense-image
Repo
Framework

Active Learning for Breast Cancer Identification


Title	Active Learning for Breast Cancer Identification
Authors	Xinpeng Xie, Yuexiang Li, Linlin Shen
Abstract	Breast cancer is the second most common malignancy among women and has become a major public health problem in current society. Traditional breast cancer identification requires experienced pathologists to carefully read the breast slice, which is laborious and suffers from inter-observer variations. Consequently, an automatic classification framework for breast cancer identification is worthwhile to develop. Recent years witnessed the development of deep learning technique. Increasing number of medical applications start to use deep learning to improve diagnosis accuracy. In this paper, we proposed a novel training strategy, namely reversed active learning (RAL), to train network to automatically classify breast cancer images. Our RAL is applied to the training set of a simple convolutional neural network (CNN) to remove mislabeled images. We evaluate the CNN trained with RAL on publicly available ICIAR 2018 Breast Cancer Dataset (IBCD). The experimental results show that our RAL increases the slice-based accuracy of CNN from 93.75% to 96.25%.
Tasks	Active Learning
Published	2018-04-18
URL	http://arxiv.org/abs/1804.06670v1
PDF	http://arxiv.org/pdf/1804.06670v1.pdf
PWC	https://paperswithcode.com/paper/active-learning-for-breast-cancer
Repo
Framework

OATM: Occlusion Aware Template Matching by Consensus Set Maximization


Title	OATM: Occlusion Aware Template Matching by Consensus Set Maximization
Authors	Simon Korman, Mark Milam, Stefano Soatto
Abstract	We present a novel approach to template matching that is efficient, can handle partial occlusions, and comes with provable performance guarantees. A key component of the method is a reduction that transforms the problem of searching a nearest neighbor among $N$ high-dimensional vectors, to searching neighbors among two sets of order $\sqrt{N}$ vectors, which can be found efficiently using range search techniques. This allows for a quadratic improvement in search complexity, and makes the method scalable in handling large search spaces. The second contribution is a hashing scheme based on consensus set maximization, which allows us to handle occlusions. The resulting scheme can be seen as a randomized hypothesize-and-test algorithm, which is equipped with guarantees regarding the number of iterations required for obtaining an optimal solution with high probability. The predicted matching rates are validated empirically and the algorithm shows a significant improvement over the state-of-the-art in both speed and robustness to occlusions.
Tasks
Published	2018-04-08
URL	http://arxiv.org/abs/1804.02638v1
PDF	http://arxiv.org/pdf/1804.02638v1.pdf
PWC	https://paperswithcode.com/paper/oatm-occlusion-aware-template-matching-by
Repo
Framework

Active Learning based on Data Uncertainty and Model Sensitivity


Title	Active Learning based on Data Uncertainty and Model Sensitivity
Authors	Nutan Chen, Alexej Klushyn, Alexandros Paraschos, Djalel Benbouzid, Patrick van der Smagt
Abstract	Robots can rapidly acquire new skills from demonstrations. However, during generalisation of skills or transitioning across fundamentally different skills, it is unclear whether the robot has the necessary knowledge to perform the task. Failing to detect missing information often leads to abrupt movements or to collisions with the environment. Active learning can quantify the uncertainty of performing the task and, in general, locate regions of missing information. We introduce a novel algorithm for active learning and demonstrate its utility for generating smooth trajectories. Our approach is based on deep generative models and metric learning in latent spaces. It relies on the Jacobian of the likelihood to detect non-smooth transitions in the latent space, i.e., transitions that lead to abrupt changes in the movement of the robot. When non-smooth transitions are detected, our algorithm asks for an additional demonstration from that specific region. The newly acquired knowledge modifies the data manifold and allows for learning a latent representation for generating smooth movements. We demonstrate the efficacy of our approach on generalising elementary skills, transitioning across different skills, and implicitly avoiding collisions with the environment. For our experiments, we use a simulated pendulum where we observe its motion from images and a 7-DoF anthropomorphic arm.
Tasks	Active Learning, Metric Learning
Published	2018-08-06
URL	http://arxiv.org/abs/1808.02026v1
PDF	http://arxiv.org/pdf/1808.02026v1.pdf
PWC	https://paperswithcode.com/paper/active-learning-based-on-data-uncertainty-and
Repo
Framework