July 29, 2019

2972 words 14 mins read

Paper Group ANR 150

Combinatorial Multi-Armed Bandits with Filtered Feedback. SIMILARnet: Simultaneous Intelligent Localization and Recognition Network. Probabilistic Semantic Retrieval for Surveillance Videos with Activity Graphs. K+ Means : An Enhancement Over K-Means Clustering Algorithm. General Video Game AI: Learning from Screen Capture. Deep Binaries: Encoding …

Combinatorial Multi-Armed Bandits with Filtered Feedback


Title	Combinatorial Multi-Armed Bandits with Filtered Feedback
Authors	James A. Grant, David S. Leslie, Kevin Glazebrook, Roberto Szechtman
Abstract	Motivated by problems in search and detection we present a solution to a Combinatorial Multi-Armed Bandit (CMAB) problem with both heavy-tailed reward distributions and a new class of feedback, filtered semibandit feedback. In a CMAB problem an agent pulls a combination of arms from a set ${1,…,k}$ in each round, generating random outcomes from probability distributions associated with these arms and receiving an overall reward. Under semibandit feedback it is assumed that the random outcomes generated are all observed. Filtered semibandit feedback allows the outcomes that are observed to be sampled from a second distribution conditioned on the initial random outcomes. This feedback mechanism is valuable as it allows CMAB methods to be applied to sequential search and detection problems where combinatorial actions are made, but the true rewards (number of objects of interest appearing in the round) are not observed, rather a filtered reward (the number of objects the searcher successfully finds, which must by definition be less than the number that appear). We present an upper confidence bound type algorithm, Robust-F-CUCB, and associated regret bound of order $\mathcal{O}(\ln(n))$ to balance exploration and exploitation in the face of both filtering of reward and heavy tailed reward distributions.
Tasks	Multi-Armed Bandits
Published	2017-05-26
URL	http://arxiv.org/abs/1705.09605v1
PDF	http://arxiv.org/pdf/1705.09605v1.pdf
PWC	https://paperswithcode.com/paper/combinatorial-multi-armed-bandits-with
Repo
Framework

SIMILARnet: Simultaneous Intelligent Localization and Recognition Network


Title	SIMILARnet: Simultaneous Intelligent Localization and Recognition Network
Authors	Arna Ghosh, Biswarup Bhattacharya, Somnath Basu Roy Chowdhury
Abstract	Global Average Pooling (GAP) [4] has been used previously to generate class activation for image classification tasks. The motivation behind SIMILARnet comes from the fact that the convolutional filters possess position information of the essential features and hence, combination of the feature maps could help us locate the class instances in an image. We propose a biologically inspired model that is free of differential connections and doesn’t require separate training thereby reducing computation overhead. Our novel architecture generates promising results and unlike existing methods, the model is not sensitive to the input image size, thus promising wider application. Codes for the experiment and illustrations can be found at: https://github.com/brcsomnath/Advanced-GAP .
Tasks	Image Classification
Published	2017-11-08
URL	http://arxiv.org/abs/1711.02831v1
PDF	http://arxiv.org/pdf/1711.02831v1.pdf
PWC	https://paperswithcode.com/paper/similarnet-simultaneous-intelligent
Repo
Framework

Probabilistic Semantic Retrieval for Surveillance Videos with Activity Graphs


Title	Probabilistic Semantic Retrieval for Surveillance Videos with Activity Graphs
Authors	Yuting Chen, Joseph Wang, Yannan Bai, Gregory Castañón, Venkatesh Saligrama
Abstract	We present a novel framework for finding complex activities matching user-described queries in cluttered surveillance videos. The wide diversity of queries coupled with unavailability of annotated activity data limits our ability to train activity models. To bridge the semantic gap we propose to let users describe an activity as a semantic graph with object attributes and inter-object relationships associated with nodes and edges, respectively. We learn node/edge-level visual predictors during training and, at test-time, propose to retrieve activity by identifying likely locations that match the semantic graph. We formulate a novel CRF based probabilistic activity localization objective that accounts for mis-detections, mis-classifications and track-losses, and outputs a likelihood score for a candidate grounded location of the query in the video. We seek groundings that maximize overall precision and recall. To handle the combinatorial search over all high-probability groundings, we propose a highest precision subgraph matching algorithm. Our method outperforms existing retrieval methods on benchmarked datasets.
Tasks
Published	2017-12-17
URL	http://arxiv.org/abs/1712.06204v2
PDF	http://arxiv.org/pdf/1712.06204v2.pdf
PWC	https://paperswithcode.com/paper/probabilistic-semantic-retrieval-for
Repo
Framework

K+ Means : An Enhancement Over K-Means Clustering Algorithm


Title	K+ Means : An Enhancement Over K-Means Clustering Algorithm
Authors	Srikanta Kolay, Kumar Sankar Ray, Abhoy Chand Mondal
Abstract	K-means (MacQueen, 1967) [1] is one of the simplest unsupervised learning algorithms that solve the well-known clustering problem. The procedure follows a simple and easy way to classify a given data set to a predefined, say K number of clusters. Determination of K is a difficult job and it is not known that which value of K can partition the objects as per our intuition. To overcome this problem we proposed K+ Means algorithm. This algorithm is an enhancement over K-Means algorithm.
Tasks
Published	2017-06-08
URL	http://arxiv.org/abs/1706.02949v2
PDF	http://arxiv.org/pdf/1706.02949v2.pdf
PWC	https://paperswithcode.com/paper/k-means-an-enhancement-over-k-means
Repo
Framework

General Video Game AI: Learning from Screen Capture


Title	General Video Game AI: Learning from Screen Capture
Authors	Kamolwan Kunanusont, Simon M. Lucas, Diego Perez-Liebana
Abstract	General Video Game Artificial Intelligence is a general game playing framework for Artificial General Intelligence research in the video-games domain. In this paper, we propose for the first time a screen capture learning agent for General Video Game AI framework. A Deep Q-Network algorithm was applied and improved to develop an agent capable of learning to play different games in the framework. After testing this algorithm using various games of different categories and difficulty levels, the results suggest that our proposed screen capture learning agent has the potential to learn many different games using only a single learning algorithm.
Tasks
Published	2017-04-23
URL	http://arxiv.org/abs/1704.06945v1
PDF	http://arxiv.org/pdf/1704.06945v1.pdf
PWC	https://paperswithcode.com/paper/general-video-game-ai-learning-from-screen
Repo
Framework

Deep Binaries: Encoding Semantic-Rich Cues for Efficient Textual-Visual Cross Retrieval


Title	Deep Binaries: Encoding Semantic-Rich Cues for Efficient Textual-Visual Cross Retrieval
Authors	Yuming Shen, Li Liu, Ling Shao, Jingkuan Song
Abstract	Cross-modal hashing is usually regarded as an effective technique for large-scale textual-visual cross retrieval, where data from different modalities are mapped into a shared Hamming space for matching. Most of the traditional textual-visual binary encoding methods only consider holistic image representations and fail to model descriptive sentences. This renders existing methods inappropriate to handle the rich semantics of informative cross-modal data for quality textual-visual search tasks. To address the problem of hashing cross-modal data with semantic-rich cues, in this paper, a novel integrated deep architecture is developed to effectively encode the detailed semantics of informative images and long descriptive sentences, named as Textual-Visual Deep Binaries (TVDB). In particular, region-based convolutional networks with long short-term memory units are introduced to fully explore image regional details while semantic cues of sentences are modeled by a text convolutional network. Additionally, we propose a stochastic batch-wise training routine, where high-quality binary codes and deep encoding functions are efficiently optimized in an alternating manner. Experiments are conducted on three multimedia datasets, i.e. Microsoft COCO, IAPR TC-12, and INRIA Web Queries, where the proposed TVDB model significantly outperforms state-of-the-art binary coding methods in the task of cross-modal retrieval.
Tasks	Cross-Modal Retrieval
Published	2017-08-08
URL	http://arxiv.org/abs/1708.02531v1
PDF	http://arxiv.org/pdf/1708.02531v1.pdf
PWC	https://paperswithcode.com/paper/deep-binaries-encoding-semantic-rich-cues-for
Repo
Framework


Title	A Statistical Learning Approach to Modal Regression
Authors	Yunlong Feng, Jun Fan, Johan A. K. Suykens
Abstract	This paper studies the nonparametric modal regression problem systematically from a statistical learning view. Originally motivated by pursuing a theoretical understanding of the maximum correntropy criterion based regression (MCCR), our study reveals that MCCR with a tending-to-zero scale parameter is essentially modal regression. We show that nonparametric modal regression problem can be approached via the classical empirical risk minimization. Some efforts are then made to develop a framework for analyzing and implementing modal regression. For instance, the modal regression function is described, the modal regression risk is defined explicitly and its \textit{Bayes} rule is characterized; for the sake of computational tractability, the surrogate modal regression risk, which is termed as the generalization risk in our study, is introduced. On the theoretical side, the excess modal regression risk, the excess generalization risk, the function estimation error, and the relations among the above three quantities are studied rigorously. It turns out that under mild conditions, function estimation consistency and convergence may be pursued in modal regression as in vanilla regression protocols, such as mean regression, median regression, and quantile regression. However, it outperforms these regression models in terms of robustness as shown in our study from a re-descending M-estimation view. This coincides with and in return explains the merits of MCCR on robustness. On the practical side, the implementation issues of modal regression including the computational algorithm and the tuning parameters selection are discussed. Numerical assessments on modal regression are also conducted to verify our findings empirically.
Tasks
Published	2017-02-20
URL	https://arxiv.org/abs/1702.05960v4
PDF	https://arxiv.org/pdf/1702.05960v4.pdf
PWC	https://paperswithcode.com/paper/a-statistical-learning-approach-to-modal
Repo
Framework

Deep Matching and Validation Network – An End-to-End Solution to Constrained Image Splicing Localization and Detection


Title	Deep Matching and Validation Network – An End-to-End Solution to Constrained Image Splicing Localization and Detection
Authors	Yue Wu, Wael AbdAlmageed, Prem Natarajan
Abstract	Image splicing is a very common image manipulation technique that is sometimes used for malicious purposes. A splicing detec- tion and localization algorithm usually takes an input image and produces a binary decision indicating whether the input image has been manipulated, and also a segmentation mask that corre- sponds to the spliced region. Most existing splicing detection and localization pipelines suffer from two main shortcomings: 1) they use handcrafted features that are not robust against subsequent processing (e.g., compression), and 2) each stage of the pipeline is usually optimized independently. In this paper we extend the formulation of the underlying splicing problem to consider two input images, a query image and a potential donor image. Here the task is to estimate the probability that the donor image has been used to splice the query image, and obtain the splicing masks for both the query and donor images. We introduce a novel deep convolutional neural network architecture, called Deep Matching and Validation Network (DMVN), which simultaneously localizes and detects image splicing. The proposed approach does not depend on handcrafted features and uses raw input images to create deep learned representations. Furthermore, the DMVN is end-to-end op- timized to produce the probability estimates and the segmentation masks. Our extensive experiments demonstrate that this approach outperforms state-of-the-art splicing detection methods by a large margin in terms of both AUC score and speed.
Tasks
Published	2017-05-27
URL	http://arxiv.org/abs/1705.09765v1
PDF	http://arxiv.org/pdf/1705.09765v1.pdf
PWC	https://paperswithcode.com/paper/deep-matching-and-validation-network-an-end
Repo
Framework

A Survey on Resilient Machine Learning


Title	A Survey on Resilient Machine Learning
Authors	Atul Kumar, Sameep Mehta
Abstract	Machine learning based system are increasingly being used for sensitive tasks such as security surveillance, guiding autonomous vehicle, taking investment decisions, detecting and blocking network intrusion and malware etc. However, recent research has shown that machine learning models are venerable to attacks by adversaries at all phases of machine learning (eg, training data collection, training, operation). All model classes of machine learning systems can be misled by providing carefully crafted inputs making them wrongly classify inputs. Maliciously created input samples can affect the learning process of a ML system by either slowing down the learning process, or affecting the performance of the learned mode, or causing the system make error(s) only in attacker’s planned scenario. Because of these developments, understanding security of machine learning algorithms and systems is emerging as an important research area among computer security and machine learning researchers and practitioners. We present a survey of this emerging area in machine learning.
Tasks
Published	2017-07-11
URL	http://arxiv.org/abs/1707.03184v1
PDF	http://arxiv.org/pdf/1707.03184v1.pdf
PWC	https://paperswithcode.com/paper/a-survey-on-resilient-machine-learning
Repo
Framework

Object Detection of Satellite Images Using Multi-Channel Higher-order Local Autocorrelation


Title	Object Detection of Satellite Images Using Multi-Channel Higher-order Local Autocorrelation
Authors	Kazuki Uehara, Hidenori Sakanashi, Hirokazu Nosato, Masahiro Murakawa, Hiroki Miyamoto, Ryosuke Nakamura
Abstract	The Earth observation satellites have been monitoring the earth’s surface for a long time, and the images taken by the satellites contain large amounts of valuable data. However, it is extremely hard work to manually analyze such huge data. Thus, a method of automatic object detection is needed for satellite images to facilitate efficient data analyses. This paper describes a new image feature extended from higher-order local autocorrelation to the object detection of multispectral satellite images. The feature has been extended to extract spectral inter-relationships in addition to spatial relationships to fully exploit multispectral information. The results of experiments with object detection tasks conducted to evaluate the effectiveness of the proposed feature extension indicate that the feature realized a higher performance compared to existing methods.
Tasks	Object Detection
Published	2017-07-28
URL	http://arxiv.org/abs/1707.09099v1
PDF	http://arxiv.org/pdf/1707.09099v1.pdf
PWC	https://paperswithcode.com/paper/object-detection-of-satellite-images-using
Repo
Framework

Optimizing Differentiable Relaxations of Coreference Evaluation Metrics


Title	Optimizing Differentiable Relaxations of Coreference Evaluation Metrics
Authors	Phong Le, Ivan Titov
Abstract	Coreference evaluation metrics are hard to optimize directly as they are non-differentiable functions, not easily decomposable into elementary decisions. Consequently, most approaches optimize objectives only indirectly related to the end goal, resulting in suboptimal performance. Instead, we propose a differentiable relaxation that lends itself to gradient-based optimisation, thus bypassing the need for reinforcement learning or heuristic modification of cross-entropy. We show that by modifying the training objective of a competitive neural coreference system, we obtain a substantial gain in performance. This suggests that our approach can be regarded as a viable alternative to using reinforcement learning or more computationally expensive imitation learning.
Tasks	Imitation Learning
Published	2017-04-14
URL	http://arxiv.org/abs/1704.04451v3
PDF	http://arxiv.org/pdf/1704.04451v3.pdf
PWC	https://paperswithcode.com/paper/optimizing-differentiable-relaxations-of
Repo
Framework

Provable Estimation of the Number of Blocks in Block Models


Title	Provable Estimation of the Number of Blocks in Block Models
Authors	Bowei Yan, Purnamrita Sarkar, Xiuyuan Cheng
Abstract	Community detection is a fundamental unsupervised learning problem for unlabeled networks which has a broad range of applications. Many community detection algorithms assume that the number of clusters $r$ is known apriori. In this paper, we propose an approach based on semi-definite relaxations, which does not require prior knowledge of model parameters like many existing convex relaxation methods and recovers the number of clusters and the clustering matrix exactly under a broad parameter regime, with probability tending to one. On a variety of simulated and real data experiments, we show that the proposed method often outperforms state-of-the-art techniques for estimating the number of clusters.
Tasks	Community Detection
Published	2017-05-24
URL	http://arxiv.org/abs/1705.08580v3
PDF	http://arxiv.org/pdf/1705.08580v3.pdf
PWC	https://paperswithcode.com/paper/provable-estimation-of-the-number-of-blocks
Repo
Framework

Differentially Private Mixture of Generative Neural Networks


Title	Differentially Private Mixture of Generative Neural Networks
Authors	Gergely Acs, Luca Melis, Claude Castelluccia, Emiliano De Cristofaro
Abstract	Generative models are used in a wide range of applications building on large amounts of contextually rich information. Due to possible privacy violations of the individuals whose data is used to train these models, however, publishing or sharing generative models is not always viable. In this paper, we present a novel technique for privately releasing generative models and entire high-dimensional datasets produced by these models. We model the generator distribution of the training data with a mixture of $k$ generative neural networks. These are trained together and collectively learn the generator distribution of a dataset. Data is divided into $k$ clusters, using a novel differentially private kernel $k$-means, then each cluster is given to separate generative neural networks, such as Restricted Boltzmann Machines or Variational Autoencoders, which are trained only on their own cluster using differentially private gradient descent. We evaluate our approach using the MNIST dataset, as well as call detail records and transit datasets, showing that it produces realistic synthetic samples, which can also be used to accurately compute arbitrary number of counting queries.
Tasks
Published	2017-09-13
URL	http://arxiv.org/abs/1709.04514v4
PDF	http://arxiv.org/pdf/1709.04514v4.pdf
PWC	https://paperswithcode.com/paper/differentially-private-mixture-of-generative
Repo
Framework

Stochastic Training of Neural Networks via Successive Convex Approximations


Title	Stochastic Training of Neural Networks via Successive Convex Approximations
Authors	Simone Scardapane, Paolo Di Lorenzo
Abstract	This paper proposes a new family of algorithms for training neural networks (NNs). These are based on recent developments in the field of non-convex optimization, going under the general name of successive convex approximation (SCA) techniques. The basic idea is to iteratively replace the original (non-convex, highly dimensional) learning problem with a sequence of (strongly convex) approximations, which are both accurate and simple to optimize. Differently from similar ideas (e.g., quasi-Newton algorithms), the approximations can be constructed using only first-order information of the neural network function, in a stochastic fashion, while exploiting the overall structure of the learning problem for a faster convergence. We discuss several use cases, based on different choices for the loss function (e.g., squared loss and cross-entropy loss), and for the regularization of the NN’s weights. We experiment on several medium-sized benchmark problems, and on a large-scale dataset involving simulated physical data. The results show how the algorithm outperforms state-of-the-art techniques, providing faster convergence to a better minimum. Additionally, we show how the algorithm can be easily parallelized over multiple computational units without hindering its performance. In particular, each computational unit can optimize a tailored surrogate function defined on a randomly assigned subset of the input variables, whose dimension can be selected depending entirely on the available computational power.
Tasks
Published	2017-06-15
URL	http://arxiv.org/abs/1706.04769v1
PDF	http://arxiv.org/pdf/1706.04769v1.pdf
PWC	https://paperswithcode.com/paper/stochastic-training-of-neural-networks-via
Repo
Framework

DeepVisage: Making face recognition simple yet with powerful generalization skills


Title	DeepVisage: Making face recognition simple yet with powerful generalization skills
Authors	Abul Hasnat, Julien Bohné, Jonathan Milgram, Stéphane Gentric, Liming Chen
Abstract	Face recognition (FR) methods report significant performance by adopting the convolutional neural network (CNN) based learning methods. Although CNNs are mostly trained by optimizing the softmax loss, the recent trend shows an improvement of accuracy with different strategies, such as task-specific CNN learning with different loss functions, fine-tuning on target dataset, metric learning and concatenating features from multiple CNNs. Incorporating these tasks obviously requires additional efforts. Moreover, it demotivates the discovery of efficient CNN models for FR which are trained only with identity labels. We focus on this fact and propose an easily trainable and single CNN based FR method. Our CNN model exploits the residual learning framework. Additionally, it uses normalized features to compute the loss. Our extensive experiments show excellent generalization on different datasets. We obtain very competitive and state-of-the-art results on the LFW, IJB-A, YouTube faces and CACD datasets.
Tasks	Face Recognition, Metric Learning
Published	2017-03-24
URL	http://arxiv.org/abs/1703.08388v2
PDF	http://arxiv.org/pdf/1703.08388v2.pdf
PWC	https://paperswithcode.com/paper/deepvisage-making-face-recognition-simple-yet
Repo
Framework