May 6, 2019

3449 words 17 mins read

Paper Group ANR 166

On the function approximation error for risk-sensitive reinforcement learning. A Boundary Tilting Persepective on the Phenomenon of Adversarial Examples. PoseAgent: Budget-Constrained 6D Object Pose Estimation via Reinforcement Learning. Global Hypothesis Generation for 6D Object Pose Estimation. Toward a new instances of NELL. Issues in evaluating …

On the function approximation error for risk-sensitive reinforcement learning


Title	On the function approximation error for risk-sensitive reinforcement learning
Authors	Prasenjit Karmakar, Shalabh Bhatnagar
Abstract	In this paper we obtain several informative error bounds on function approximation for the policy evaluation algorithm proposed by Basu et al. when the aim is to find the risk-sensitive cost represented using exponential utility. The main idea is to use classical Bapat’s inequality and to use Perron-Frobenius eigenvectors (exists if we assume irreducible Markov chain) to get the new bounds. The novelty of our approach is that we use the irreduciblity of Markov chain to get the new bounds whereas the earlier work by Basu et al. used spectral variation bound which is true for any matrix. We also give examples where all our bounds achieve the “actual error” whereas the earlier bound given by Basu et al. is much weaker in comparison. We show that this happens due to the absence of difference term in the earlier bound which is always present in all our bounds when the state space is large. Additionally, we discuss how all our bounds compare with each other.
Tasks
Published	2016-12-22
URL	http://arxiv.org/abs/1612.07562v10
PDF	http://arxiv.org/pdf/1612.07562v10.pdf
PWC	https://paperswithcode.com/paper/on-the-function-approximation-error-for-risk
Repo
Framework

A Boundary Tilting Persepective on the Phenomenon of Adversarial Examples


Title	A Boundary Tilting Persepective on the Phenomenon of Adversarial Examples
Authors	Thomas Tanay, Lewis Griffin
Abstract	Deep neural networks have been shown to suffer from a surprising weakness: their classification outputs can be changed by small, non-random perturbations of their inputs. This adversarial example phenomenon has been explained as originating from deep networks being “too linear” (Goodfellow et al., 2014). We show here that the linear explanation of adversarial examples presents a number of limitations: the formal argument is not convincing, linear classifiers do not always suffer from the phenomenon, and when they do their adversarial examples are different from the ones affecting deep networks. We propose a new perspective on the phenomenon. We argue that adversarial examples exist when the classification boundary lies close to the submanifold of sampled data, and present a mathematical analysis of this new perspective in the linear case. We define the notion of adversarial strength and show that it can be reduced to the deviation angle between the classifier considered and the nearest centroid classifier. Then, we show that the adversarial strength can be made arbitrarily high independently of the classification performance due to a mechanism that we call boundary tilting. This result leads us to defining a new taxonomy of adversarial examples. Finally, we show that the adversarial strength observed in practice is directly dependent on the level of regularisation used and the strongest adversarial examples, symptomatic of overfitting, can be avoided by using a proper level of regularisation.
Tasks
Published	2016-08-27
URL	http://arxiv.org/abs/1608.07690v1
PDF	http://arxiv.org/pdf/1608.07690v1.pdf
PWC	https://paperswithcode.com/paper/a-boundary-tilting-persepective-on-the
Repo
Framework

PoseAgent: Budget-Constrained 6D Object Pose Estimation via Reinforcement Learning


Title	PoseAgent: Budget-Constrained 6D Object Pose Estimation via Reinforcement Learning
Authors	Alexander Krull, Eric Brachmann, Sebastian Nowozin, Frank Michel, Jamie Shotton, Carsten Rother
Abstract	State-of-the-art computer vision algorithms often achieve efficiency by making discrete choices about which hypotheses to explore next. This allows allocation of computational resources to promising candidates, however, such decisions are non-differentiable. As a result, these algorithms are hard to train in an end-to-end fashion. In this work we propose to learn an efficient algorithm for the task of 6D object pose estimation. Our system optimizes the parameters of an existing state-of-the art pose estimation system using reinforcement learning, where the pose estimation system now becomes the stochastic policy, parametrized by a CNN. Additionally, we present an efficient training algorithm that dramatically reduces computation time. We show empirically that our learned pose estimation procedure makes better use of limited resources and improves upon the state-of-the-art on a challenging dataset. Our approach enables differentiable end-to-end training of complex algorithmic pipelines and learns to make optimal use of a given computational budget.
Tasks	6D Pose Estimation using RGB, Pose Estimation
Published	2016-12-12
URL	http://arxiv.org/abs/1612.03779v2
PDF	http://arxiv.org/pdf/1612.03779v2.pdf
PWC	https://paperswithcode.com/paper/poseagent-budget-constrained-6d-object-pose
Repo
Framework

Global Hypothesis Generation for 6D Object Pose Estimation


Title	Global Hypothesis Generation for 6D Object Pose Estimation
Authors	Frank Michel, Alexander Kirillov, Eric Brachmann, Alexander Krull, Stefan Gumhold, Bogdan Savchynskyy, Carsten Rother
Abstract	This paper addresses the task of estimating the 6D pose of a known 3D object from a single RGB-D image. Most modern approaches solve this task in three steps: i) Compute local features; ii) Generate a pool of pose-hypotheses; iii) Select and refine a pose from the pool. This work focuses on the second step. While all existing approaches generate the hypotheses pool via local reasoning, e.g. RANSAC or Hough-voting, we are the first to show that global reasoning is beneficial at this stage. In particular, we formulate a novel fully-connected Conditional Random Field (CRF) that outputs a very small number of pose-hypotheses. Despite the potential functions of the CRF being non-Gaussian, we give a new and efficient two-step optimization procedure, with some guarantees for optimality. We utilize our global hypotheses generation procedure to produce results that exceed state-of-the-art for the challenging “Occluded Object Dataset”.
Tasks	6D Pose Estimation using RGB, Pose Estimation
Published	2016-12-07
URL	http://arxiv.org/abs/1612.02287v3
PDF	http://arxiv.org/pdf/1612.02287v3.pdf
PWC	https://paperswithcode.com/paper/global-hypothesis-generation-for-6d-object
Repo
Framework

Toward a new instances of NELL


Title	Toward a new instances of NELL
Authors	Maisa C. Duarte, Pierre Maret
Abstract	We are developing the method to start new instances of NELL in various languages and develop then NELL multilingualism. We base our method on our experience on NELL Portuguese and NELL French. This reports explain our method and develops some research perspectives.
Tasks
Published	2016-10-11
URL	http://arxiv.org/abs/1610.03246v1
PDF	http://arxiv.org/pdf/1610.03246v1.pdf
PWC	https://paperswithcode.com/paper/toward-a-new-instances-of-nell
Repo
Framework

Issues in evaluating semantic spaces using word analogies


Title	Issues in evaluating semantic spaces using word analogies
Authors	Tal Linzen
Abstract	The offset method for solving word analogies has become a standard evaluation tool for vector-space semantic models: it is considered desirable for a space to represent semantic relations as consistent vector offsets. We show that the method’s reliance on cosine similarity conflates offset consistency with largely irrelevant neighborhood structure, and propose simple baselines that should be used to improve the utility of the method in vector space evaluation.
Tasks
Published	2016-06-24
URL	http://arxiv.org/abs/1606.07736v1
PDF	http://arxiv.org/pdf/1606.07736v1.pdf
PWC	https://paperswithcode.com/paper/issues-in-evaluating-semantic-spaces-using
Repo
Framework

Toward a Robust Diversity-Based Model to Detect Changes of Context


Title	Toward a Robust Diversity-Based Model to Detect Changes of Context
Authors	Sylvain Castagnos, Amaury L ‘Huillier, Anne Boyer
Abstract	Being able to automatically and quickly understand the user context during a session is a main issue for recommender systems. As a first step toward achieving that goal, we propose a model that observes in real time the diversity brought by each item relatively to a short sequence of consultations, corresponding to the recent user history. Our model has a complexity in constant time, and is generic since it can apply to any type of items within an online service (e.g. profiles, products, music tracks) and any application domain (e-commerce, social network, music streaming), as long as we have partial item descriptions. The observation of the diversity level over time allows us to detect implicit changes. In the long term, we plan to characterize the context, i.e. to find common features among a contiguous sub-sequence of items between two changes of context determined by our model. This will allow us to make context-aware and privacy-preserving recommendations, to explain them to users. As this is an ongoing research, the first step consists here in studying the robustness of our model while detecting changes of context. In order to do so, we use a music corpus of 100 users and more than 210,000 consultations (number of songs played in the global history). We validate the relevancy of our detections by finding connections between changes of context and events, such as ends of session. Of course, these events are a subset of the possible changes of context, since there might be several contexts within a session. We altered the quality of our corpus in several manners, so as to test the performances of our model when confronted with sparsity and different types of items. The results show that our model is robust and constitutes a promising approach.
Tasks	Recommendation Systems
Published	2016-01-08
URL	http://arxiv.org/abs/1601.01917v1
PDF	http://arxiv.org/pdf/1601.01917v1.pdf
PWC	https://paperswithcode.com/paper/toward-a-robust-diversity-based-model-to
Repo
Framework

Online Localization and Prediction of Actions and Interactions


Title	Online Localization and Prediction of Actions and Interactions
Authors	Khurram Soomro, Haroon Idrees, Mubarak Shah
Abstract	This paper proposes a person-centric and online approach to the challenging problem of localization and prediction of actions and interactions in videos. Typically, localization or recognition is performed in an offline manner where all the frames in the video are processed together. This prevents timely localization and prediction of actions and interactions - an important consideration for many tasks including surveillance and human-machine interaction. In our approach, we estimate human poses at each frame and train discriminative appearance models using the superpixels inside the pose bounding boxes. Since the pose estimation per frame is inherently noisy, the conditional probability of pose hypotheses at current time-step (frame) is computed using pose estimations in the current frame and their consistency with poses in the previous frames. Next, both the superpixel and pose-based foreground likelihoods are used to infer the location of actors at each time through a Conditional Random. The issue of visual drift is handled by updating the appearance models, and refining poses using motion smoothness on joint locations, in an online manner. For online prediction of action (interaction) confidences, we propose an approach based on Structural SVM that operates on short video segments, and is trained with the objective that confidence of an action or interaction increases as time progresses. Lastly, we quantify the performance of both detection and prediction together, and analyze how the prediction accuracy varies as a time function of observed action (interaction) at different levels of detection performance. Our experiments on several datasets suggest that despite using only a few frames to localize actions (interactions) at each time instant, we are able to obtain competitive results to state-of-the-art offline methods.
Tasks	Pose Estimation
Published	2016-12-04
URL	http://arxiv.org/abs/1612.01194v1
PDF	http://arxiv.org/pdf/1612.01194v1.pdf
PWC	https://paperswithcode.com/paper/online-localization-and-prediction-of-actions
Repo
Framework

Learning Filter Banks Using Deep Learning For Acoustic Signals


Title	Learning Filter Banks Using Deep Learning For Acoustic Signals
Authors	Shuhui Qu, Juncheng Li, Wei Dai, Samarjit Das
Abstract	Designing appropriate features for acoustic event recognition tasks is an active field of research. Expressive features should both improve the performance of the tasks and also be interpret-able. Currently, heuristically designed features based on the domain knowledge requires tremendous effort in hand-crafting, while features extracted through deep network are difficult for human to interpret. In this work, we explore the experience guided learning method for designing acoustic features. This is a novel hybrid approach combining both domain knowledge and purely data driven feature designing. Based on the procedure of log Mel-filter banks, we design a filter bank learning layer. We concatenate this layer with a convolutional neural network (CNN) model. After training the network, the weight of the filter bank learning layer is extracted to facilitate the design of acoustic features. We smooth the trained weight of the learning layer and re-initialize it in filter bank learning layer as audio feature extractor. For the environmental sound recognition task based on the Urban- sound8K dataset, the experience guided learning leads to a 2% accuracy improvement compared with the fixed feature extractors (the log Mel-filter bank). The shape of the new filter banks are visualized and explained to prove the effectiveness of the feature design process.
Tasks
Published	2016-11-29
URL	http://arxiv.org/abs/1611.09526v1
PDF	http://arxiv.org/pdf/1611.09526v1.pdf
PWC	https://paperswithcode.com/paper/learning-filter-banks-using-deep-learning-for
Repo
Framework

A Comparative Study for the Nuclear Norms Minimization Methods


Title	A Comparative Study for the Nuclear Norms Minimization Methods
Authors	Zhiyuan Zha, Bihan Wen, Jiachao Zhang, Jiantao Zhou, Ce Zhu
Abstract	The nuclear norm minimization (NNM) is commonly used to approximate the matrix rank by shrinking all singular values equally. However, the singular values have clear physical meanings in many practical problems, and NNM may not be able to faithfully approximate the matrix rank. To alleviate the above-mentioned limitation of NNM, recent studies have suggested that the weighted nuclear norm minimization (WNNM) can achieve a better rank estimation than NNM, which heuristically set the weight being inverse to the singular values. However, it still lacks a rigorous explanation why WNNM is more effective than NMM in various applications. In this paper, we analyze NNM and WNNM from the perspective of group sparse representation (GSR). Concretely, an adaptive dictionary learning method is devised to connect the rank minimization and GSR models. Based on the proposed dictionary, we prove that NNM and WNNM are equivalent to L1-norm minimization and the weighted L1-norm minimization in GSR, respectively. Inspired by enhancing sparsity of the weighted L1-norm minimization in comparison with L1-norm minimization in sparse representation, we thus explain that WNNM is more effective than NMM. By integrating the image nonlocal self-similarity (NSS) prior with the WNNM model, we then apply it to solve the image denoising problem. Experimental results demonstrate that WNNM is more effective than NNM and outperforms several state-of-the-art methods in both objective and perceptual quality.
Tasks	Deblurring, Denoising, Dictionary Learning, Image Denoising, Image Inpainting
Published	2016-08-16
URL	https://arxiv.org/abs/1608.04517v4
PDF	https://arxiv.org/pdf/1608.04517v4.pdf
PWC	https://paperswithcode.com/paper/a-comparative-study-for-the-weighted-nuclear
Repo
Framework

Incomplete Pivoted QR-based Dimensionality Reduction


Title	Incomplete Pivoted QR-based Dimensionality Reduction
Authors	Amit Bermanis, Aviv Rotbart, Moshe Salhov, Amir Averbuch
Abstract	High-dimensional big data appears in many research fields such as image recognition, biology and collaborative filtering. Often, the exploration of such data by classic algorithms is encountered with difficulties due to `curse of dimensionality’ phenomenon. Therefore, dimensionality reduction methods are applied to the data prior to its analysis. Many of these methods are based on principal components analysis, which is statistically driven, namely they map the data into a low-dimension subspace that preserves significant statistical properties of the high-dimensional data. As a consequence, such methods do not directly address the geometry of the data, reflected by the mutual distances between multidimensional data point. Thus, operations such as classification, anomaly detection or other machine learning tasks may be affected. This work provides a dictionary-based framework for geometrically driven data analysis that includes dimensionality reduction, out-of-sample extension and anomaly detection. It embeds high-dimensional data in a low-dimensional subspace. This embedding preserves the original high-dimensional geometry of the data up to a user-defined distortion rate. In addition, it identifies a subset of landmark data points that constitute a dictionary for the analyzed dataset. The dictionary enables to have a natural extension of the low-dimensional embedding to out-of-sample data points, which gives rise to a distortion-based criterion for anomaly detection. The suggested method is demonstrated on synthetic and real-world datasets and achieves good results for classification, anomaly detection and out-of-sample tasks. \|
Tasks	Anomaly Detection, Dimensionality Reduction
Published	2016-07-12
URL	http://arxiv.org/abs/1607.03456v1
PDF	http://arxiv.org/pdf/1607.03456v1.pdf
PWC	https://paperswithcode.com/paper/incomplete-pivoted-qr-based-dimensionality
Repo
Framework

On Clustering and Embedding Mixture Manifolds using a Low Rank Neighborhood Approach


Title	On Clustering and Embedding Mixture Manifolds using a Low Rank Neighborhood Approach
Authors	Arun M. Saranathan, Mario Parente
Abstract	Samples from intimate (non-linear) mixtures are generally modeled as being drawn from a smooth manifold. Scenarios where the data contains multiple intimate mixtures with some constituent materials in common can be thought of as manifolds which share a boundary. Two important steps in the processing of such data are (i) to identify (cluster) the different mixture-manifolds present in the data and (ii) to eliminate the non-linearities present the data by mapping each mixture-manifold into some low-dimensional euclidean space (embedding). Manifold clustering and embedding techniques appear to be an ideal tool for this task, but the present state-of-the-art algorithms perform poorly for hyperspectral data, particularly in the embedding task. We propose a novel reconstruction-based algorithm for improved clustering and embedding of mixture-manifolds. The algorithms attempts to reconstruct each target-point as an affine combination of its nearest neighbors with an additional rank penalty on the neighborhood to ensure that only neighbors on the same manifold as the target-point are used in the reconstruction. The reconstruction matrix generated by using this technique is block-diagonal and can be used for clustering (using spectral clustering) and embedding. The improved performance of the algorithms vis-a-vis its competitors is exhibited on a variety of simulated and real mixture datasets.
Tasks
Published	2016-08-23
URL	http://arxiv.org/abs/1608.06669v3
PDF	http://arxiv.org/pdf/1608.06669v3.pdf
PWC	https://paperswithcode.com/paper/on-clustering-and-embedding-mixture-manifolds
Repo
Framework

Suppressing Background Radiation Using Poisson Principal Component Analysis


Title	Suppressing Background Radiation Using Poisson Principal Component Analysis
Authors	P. Tandon, P. Huggins, A. Dubrawski, S. Labov, K. Nelson
Abstract	Performance of nuclear threat detection systems based on gamma-ray spectrometry often strongly depends on the ability to identify the part of measured signal that can be attributed to background radiation. We have successfully applied a method based on Principal Component Analysis (PCA) to obtain a compact null-space model of background spectra using PCA projection residuals to derive a source detection score. We have shown the method’s utility in a threat detection system using mobile spectrometers in urban scenes (Tandon et al 2012). While it is commonly assumed that measured photon counts follow a Poisson process, standard PCA makes a Gaussian assumption about the data distribution, which may be a poor approximation when photon counts are low. This paper studies whether and in what conditions PCA with a Poisson-based loss function (Poisson PCA) can outperform standard Gaussian PCA in modeling background radiation to enable more sensitive and specific nuclear threat detection.
Tasks
Published	2016-05-26
URL	http://arxiv.org/abs/1605.08455v1
PDF	http://arxiv.org/pdf/1605.08455v1.pdf
PWC	https://paperswithcode.com/paper/suppressing-background-radiation-using
Repo
Framework

A CNN Cascade for Landmark Guided Semantic Part Segmentation


Title	A CNN Cascade for Landmark Guided Semantic Part Segmentation
Authors	Aaron Jackson, Michel Valstar, Georgios Tzimiropoulos
Abstract	This paper proposes a CNN cascade for semantic part segmentation guided by pose-specific information encoded in terms of a set of landmarks (or keypoints). There is large amount of prior work on each of these tasks separately, yet, to the best of our knowledge, this is the first time in literature that the interplay between pose estimation and semantic part segmentation is investigated. To address this limitation of prior work, in this paper, we propose a CNN cascade of tasks that firstly performs landmark localisation and then uses this information as input for guiding semantic part segmentation. We applied our architecture to the problem of facial part segmentation and report large performance improvement over the standard unguided network on the most challenging face datasets. Testing code and models will be published online at http://cs.nott.ac.uk/~psxasj/.
Tasks	Pose Estimation
Published	2016-09-30
URL	http://arxiv.org/abs/1609.09642v1
PDF	http://arxiv.org/pdf/1609.09642v1.pdf
PWC	https://paperswithcode.com/paper/a-cnn-cascade-for-landmark-guided-semantic
Repo
Framework

Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning


Title	Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning
Authors	Hoo-Chang Shin, Holger R. Roth, Mingchen Gao, Le Lu, Ziyue Xu, Isabella Nogues, Jianhua Yao, Daniel Mollura, Ronald M. Summers
Abstract	Remarkable progress has been made in image recognition, primarily due to the availability of large-scale annotated datasets and the revival of deep CNN. CNNs enable learning data-driven, highly representative, layered hierarchical image features from sufficient training data. However, obtaining datasets as comprehensively annotated as ImageNet in the medical imaging domain remains a challenge. There are currently three major techniques that successfully employ CNNs to medical image classification: training the CNN from scratch, using off-the-shelf pre-trained CNN features, and conducting unsupervised CNN pre-training with supervised fine-tuning. Another effective method is transfer learning, i.e., fine-tuning CNN models pre-trained from natural image dataset to medical image tasks. In this paper, we exploit three important, but previously understudied factors of employing deep convolutional neural networks to computer-aided detection problems. We first explore and evaluate different CNN architectures. The studied models contain 5 thousand to 160 million parameters, and vary in numbers of layers. We then evaluate the influence of dataset scale and spatial image context on performance. Finally, we examine when and why transfer learning from pre-trained ImageNet (via fine-tuning) can be useful. We study two specific computer-aided detection (CADe) problems, namely thoraco-abdominal lymph node (LN) detection and interstitial lung disease (ILD) classification. We achieve the state-of-the-art performance on the mediastinal LN detection, with 85% sensitivity at 3 false positive per patient, and report the first five-fold cross-validation classification results on predicting axial CT slices with ILD categories. Our extensive empirical evaluation, CNN model analysis and valuable insights can be extended to the design of high performance CAD systems for other medical imaging tasks.
Tasks	Image Classification, Transfer Learning
Published	2016-02-10
URL	http://arxiv.org/abs/1602.03409v1
PDF	http://arxiv.org/pdf/1602.03409v1.pdf
PWC	https://paperswithcode.com/paper/deep-convolutional-neural-networks-for-1
Repo
Framework