July 28, 2019

2777 words 14 mins read

Paper Group ANR 448

Fooling Vision and Language Models Despite Localization and Attention Mechanism. Camera Calibration by Global Constraints on the Motion of Silhouettes. Non-negative Matrix Factorization: Robust Extraction of Extended Structures. Egocentric Hand Detection Via Dynamic Region Growing. Adaptive Cost Function for Pointcloud Registration. Novel Sensor Sc …

Fooling Vision and Language Models Despite Localization and Attention Mechanism


Title	Fooling Vision and Language Models Despite Localization and Attention Mechanism
Authors	Xiaojun Xu, Xinyun Chen, Chang Liu, Anna Rohrbach, Trevor Darrell, Dawn Song
Abstract	Adversarial attacks are known to succeed on classifiers, but it has been an open question whether more complex vision systems are vulnerable. In this paper, we study adversarial examples for vision and language models, which incorporate natural language understanding and complex structures such as attention, localization, and modular architectures. In particular, we investigate attacks on a dense captioning model and on two visual question answering (VQA) models. Our evaluation shows that we can generate adversarial examples with a high success rate (i.e., > 90%) for these models. Our work sheds new light on understanding adversarial attacks on vision systems which have a language component and shows that attention, bounding box localization, and compositional internal structures are vulnerable to adversarial attacks. These observations will inform future work towards building effective defenses.
Tasks	Question Answering, Visual Question Answering
Published	2017-09-25
URL	http://arxiv.org/abs/1709.08693v2
PDF	http://arxiv.org/pdf/1709.08693v2.pdf
PWC	https://paperswithcode.com/paper/fooling-vision-and-language-models-despite
Repo
Framework

Camera Calibration by Global Constraints on the Motion of Silhouettes


Title	Camera Calibration by Global Constraints on the Motion of Silhouettes
Authors	Gil Ben-Artzi
Abstract	We address the problem of epipolar geometry using the motion of silhouettes. Such methods match epipolar lines or frontier points across views, which are then used as the set of putative correspondences. We introduce an approach that improves by two orders of magnitude the performance over state-of-the-art methods, by significantly reducing the number of outliers in the putative matching. We model the frontier points’ correspondence problem as constrained flow optimization, requiring small differences between their coordinates over consecutive frames. Our approach is formulated as a Linear Integer Program and we show that due to the nature of our problem, it can be solved efficiently in an iterative manner. Our method was validated on four standard datasets providing accurate calibrations across very different viewpoints.
Tasks	Calibration
Published	2017-04-14
URL	http://arxiv.org/abs/1704.04360v1
PDF	http://arxiv.org/pdf/1704.04360v1.pdf
PWC	https://paperswithcode.com/paper/camera-calibration-by-global-constraints-on
Repo
Framework

Non-negative Matrix Factorization: Robust Extraction of Extended Structures


Title	Non-negative Matrix Factorization: Robust Extraction of Extended Structures
Authors	Bīn Rén, Laurent Pueyo, Guangtun Ben Zhu, John Debes, Gaspard Duchêne
Abstract	We apply the vectorized Non-negative Matrix Factorization (NMF) method to post-processing of direct imaging data for exoplanetary systems such as circumstellar disks. NMF is an iterative approach, which first creates a non-orthogonal and non-negative basis of components using given reference images, then models a target with the components. The constructed model is then rescaled with a factor to compensate for the contribution from a disk. We compare NMF with existing methods (classical reference differential imaging method, and the Karhunen-Lo`eve image projection algorithm) using synthetic circumstellar disks, and demonstrate the superiority of NMF: with no need for prior selection of references, NMF can detect fainter circumstellar disks, better preserve low order disk morphology, and does not require forward modeling. As an application to a well-known disk example, we process the archival Hubble Space Telescope (HST) STIS coronagraphic observations of HD~181327 with different methods and compare them. NMF is able to extract some circumstellar material inside the primary ring for the first time. In the appendix, we mathematically investigate the stability of NMF components during iteration, and the linearity of NMF modeling.
Tasks
Published	2017-12-29
URL	http://arxiv.org/abs/1712.10317v2
PDF	http://arxiv.org/pdf/1712.10317v2.pdf
PWC	https://paperswithcode.com/paper/non-negative-matrix-factorization-robust
Repo
Framework

Egocentric Hand Detection Via Dynamic Region Growing


Title	Egocentric Hand Detection Via Dynamic Region Growing
Authors	Shao Huang, Weiqiang Wang, Shengfeng He, Rynson W. H. Lau
Abstract	Egocentric videos, which mainly record the activities carried out by the users of the wearable cameras, have drawn much research attentions in recent years. Due to its lengthy content, a large number of ego-related applications have been developed to abstract the captured videos. As the users are accustomed to interacting with the target objects using their own hands while their hands usually appear within their visual fields during the interaction, an egocentric hand detection step is involved in tasks like gesture recognition, action recognition and social interaction understanding. In this work, we propose a dynamic region growing approach for hand region detection in egocentric videos, by jointly considering hand-related motion and egocentric cues. We first determine seed regions that most likely belong to the hand, by analyzing the motion patterns across successive frames. The hand regions can then be located by extending from the seed regions, according to the scores computed for the adjacent superpixels. These scores are derived from four egocentric cues: contrast, location, position consistency and appearance continuity. We discuss how to apply the proposed method in real-life scenarios, where multiple hands irregularly appear and disappear from the videos. Experimental results on public datasets show that the proposed method achieves superior performance compared with the state-of-the-art methods, especially in complicated scenarios.
Tasks	Gesture Recognition, Temporal Action Localization
Published	2017-11-10
URL	http://arxiv.org/abs/1711.03677v1
PDF	http://arxiv.org/pdf/1711.03677v1.pdf
PWC	https://paperswithcode.com/paper/egocentric-hand-detection-via-dynamic-region
Repo
Framework

Adaptive Cost Function for Pointcloud Registration


Title	Adaptive Cost Function for Pointcloud Registration
Authors	Johan Ekekrantz, John Folkesson, Patric Jensfelt
Abstract	In this paper we introduce an adaptive cost function for pointcloud registration. The algorithm automatically estimates the sensor noise, which is important for generalization across different sensors and environments. Through experiments on real and synthetic data, we show significant improvements in accuracy and robustness over state-of-the-art solutions.
Tasks
Published	2017-04-25
URL	http://arxiv.org/abs/1704.07910v1
PDF	http://arxiv.org/pdf/1704.07910v1.pdf
PWC	https://paperswithcode.com/paper/adaptive-cost-function-for-pointcloud
Repo
Framework

Novel Sensor Scheduling Scheme for Intruder Tracking in Energy Efficient Sensor Networks


Title	Novel Sensor Scheduling Scheme for Intruder Tracking in Energy Efficient Sensor Networks
Authors	Raghuram Bharadwaj Diddigi, Prabuchandran K. J., Shalabh Bhatnagar
Abstract	We consider the problem of tracking an intruder using a network of wireless sensors. For tracking the intruder at each instant, the optimal number and the right configuration of sensors has to be powered. As powering the sensors consumes energy, there is a trade off between accurately tracking the position of the intruder at each instant and the energy consumption of sensors. This problem has been formulated in the framework of Partially Observable Markov Decision Process (POMDP). Even for the state-of-the-art algorithm in the literature, the curse of dimensionality renders the problem intractable. In this paper, we formulate the Intrusion Detection (ID) problem with a suitable state-action space in the framework of POMDP and develop a Reinforcement Learning (RL) algorithm utilizing the Upper Confidence Tree Search (UCT) method to solve the ID problem. Through simulations, we show that our algorithm performs and scales well with the increasing state and action spaces.
Tasks	Intrusion Detection
Published	2017-08-27
URL	http://arxiv.org/abs/1708.08113v3
PDF	http://arxiv.org/pdf/1708.08113v3.pdf
PWC	https://paperswithcode.com/paper/novel-sensor-scheduling-scheme-for-intruder
Repo
Framework


Title	Fast Change Point Detection on Dynamic Social Networks
Authors	Yu Wang, Aniket Chakrabarti, David Sivakoff, Srinivasan Parthasarathy
Abstract	A number of real world problems in many domains (e.g. sociology, biology, political science and communication networks) can be modeled as dynamic networks with nodes representing entities of interest and edges representing interactions among the entities at different points in time. A common representation for such models is the snapshot model - where a network is defined at logical time-stamps. An important problem under this model is change point detection. In this work we devise an effective and efficient three-step-approach for detecting change points in dynamic networks under the snapshot model. Our algorithm achieves up to 9X speedup over the state-of-the-art while improving quality on both synthetic and real world networks.
Tasks	Change Point Detection
Published	2017-05-20
URL	http://arxiv.org/abs/1705.07325v2
PDF	http://arxiv.org/pdf/1705.07325v2.pdf
PWC	https://paperswithcode.com/paper/fast-change-point-detection-on-dynamic-social
Repo
Framework

What Does Explainable AI Really Mean? A New Conceptualization of Perspectives


Title	What Does Explainable AI Really Mean? A New Conceptualization of Perspectives
Authors	Derek Doran, Sarah Schulz, Tarek R. Besold
Abstract	We characterize three notions of explainable AI that cut across research fields: opaque systems that offer no insight into its algo- rithmic mechanisms; interpretable systems where users can mathemat- ically analyze its algorithmic mechanisms; and comprehensible systems that emit symbols enabling user-driven explanations of how a conclusion is reached. The paper is motivated by a corpus analysis of NIPS, ACL, COGSCI, and ICCV/ECCV paper titles showing differences in how work on explainable AI is positioned in various fields. We close by introducing a fourth notion: truly explainable systems, where automated reasoning is central to output crafted explanations without requiring human post processing as final step of the generative process.
Tasks
Published	2017-10-02
URL	http://arxiv.org/abs/1710.00794v1
PDF	http://arxiv.org/pdf/1710.00794v1.pdf
PWC	https://paperswithcode.com/paper/what-does-explainable-ai-really-mean-a-new
Repo
Framework

Discovery Radiomics via Evolutionary Deep Radiomic Sequencer Discovery for Pathologically-Proven Lung Cancer Detection


Title	Discovery Radiomics via Evolutionary Deep Radiomic Sequencer Discovery for Pathologically-Proven Lung Cancer Detection
Authors	Mohammad Javad Shafiee, Audrey G. Chung, Farzad Khalvati, Masoom A. Haider, Alexander Wong
Abstract	While lung cancer is the second most diagnosed form of cancer in men and women, a sufficiently early diagnosis can be pivotal in patient survival rates. Imaging-based, or radiomics-driven, detection methods have been developed to aid diagnosticians, but largely rely on hand-crafted features which may not fully encapsulate the differences between cancerous and healthy tissue. Recently, the concept of discovery radiomics was introduced, where custom abstract features are discovered from readily available imaging data. We propose a novel evolutionary deep radiomic sequencer discovery approach based on evolutionary deep intelligence. Motivated by patient privacy concerns and the idea of operational artificial intelligence, the evolutionary deep radiomic sequencer discovery approach organically evolves increasingly more efficient deep radiomic sequencers that produce significantly more compact yet similarly descriptive radiomic sequences over multiple generations. As a result, this framework improves operational efficiency and enables diagnosis to be run locally at the radiologist’s computer while maintaining detection accuracy. We evaluated the evolved deep radiomic sequencer (EDRS) discovered via the proposed evolutionary deep radiomic sequencer discovery framework against state-of-the-art radiomics-driven and discovery radiomics methods using clinical lung CT data with pathologically-proven diagnostic data from the LIDC-IDRI dataset. The evolved deep radiomic sequencer shows improved sensitivity (93.42%), specificity (82.39%), and diagnostic accuracy (88.78%) relative to previous radiomics approaches.
Tasks
Published	2017-05-10
URL	http://arxiv.org/abs/1705.03572v2
PDF	http://arxiv.org/pdf/1705.03572v2.pdf
PWC	https://paperswithcode.com/paper/discovery-radiomics-via-evolutionary-deep
Repo
Framework


Title	MSCM-LiFe: Multi-scale cross modal linear feature for horizon detection in maritime images
Authors	D. K. Prasad, D. Rajan, C. K. Prasath, L. Rachmawati, E. Rajabaly, C. Quek
Abstract	This paper proposes a new method for horizon detection called the multi-scale cross modal linear feature. This method integrates three different concepts related to the presence of horizon in maritime images to increase the accuracy of horizon detection. Specifically it uses the persistence of horizon in multi-scale median filtering, and its detection as a linear feature commonly detected by two different methods, namely the Hough transform of edgemap and the intensity gradient. We demonstrate the performance of the method over 13 videos comprising of more than 3000 frames and show that the proposed method detects horizon with small error in most of the cases, outperforming three state-of-the-art methods.
Tasks
Published	2017-01-29
URL	http://arxiv.org/abs/1701.08378v1
PDF	http://arxiv.org/pdf/1701.08378v1.pdf
PWC	https://paperswithcode.com/paper/mscm-life-multi-scale-cross-modal-linear
Repo
Framework

Asymmetric Feature Maps with Application to Sketch Based Retrieval


Title	Asymmetric Feature Maps with Application to Sketch Based Retrieval
Authors	Giorgos Tolias, Ondřej Chum
Abstract	We propose a novel concept of asymmetric feature maps (AFM), which allows to evaluate multiple kernels between a query and database entries without increasing the memory requirements. To demonstrate the advantages of the AFM method, we derive a short vector image representation that, due to asymmetric feature maps, supports efficient scale and translation invariant sketch-based image retrieval. Unlike most of the short-code based retrieval systems, the proposed method provides the query localization in the retrieved image. The efficiency of the search is boosted by approximating a 2D translation search via trigonometric polynomial of scores by 1D projections. The projections are a special case of AFM. An order of magnitude speed-up is achieved compared to traditional trigonometric polynomials. The results are boosted by an image-based average query expansion, exceeding significantly the state of the art on standard benchmarks.
Tasks	Image Retrieval, Sketch-Based Image Retrieval
Published	2017-04-12
URL	http://arxiv.org/abs/1704.03946v1
PDF	http://arxiv.org/pdf/1704.03946v1.pdf
PWC	https://paperswithcode.com/paper/asymmetric-feature-maps-with-application-to
Repo
Framework

How close are the eigenvectors and eigenvalues of the sample and actual covariance matrices?


Title	How close are the eigenvectors and eigenvalues of the sample and actual covariance matrices?
Authors	Andreas Loukas
Abstract	How many samples are sufficient to guarantee that the eigenvectors and eigenvalues of the sample covariance matrix are close to those of the actual covariance matrix? For a wide family of distributions, including distributions with finite second moment and distributions supported in a centered Euclidean ball, we prove that the inner product between eigenvectors of the sample and actual covariance matrices decreases proportionally to the respective eigenvalue distance. Our findings imply non-asymptotic concentration bounds for eigenvectors, eigenspaces, and eigenvalues. They also provide conditions for distinguishing principal components based on a constant number of samples.
Tasks
Published	2017-02-17
URL	http://arxiv.org/abs/1702.05443v1
PDF	http://arxiv.org/pdf/1702.05443v1.pdf
PWC	https://paperswithcode.com/paper/how-close-are-the-eigenvectors-and
Repo
Framework

Preference fusion and Condorcet’s Paradox under uncertainty


Title	Preference fusion and Condorcet’s Paradox under uncertainty
Authors	Yiru Zhang, Tassadit Bouadi, Arnaud Martin
Abstract	Facing an unknown situation, a person may not be able to firmly elicit his/her preferences over different alternatives, so he/she tends to express uncertain preferences. Given a community of different persons expressing their preferences over certain alternatives under uncertainty, to get a collective representative opinion of the whole community, a preference fusion process is required. The aim of this work is to propose a preference fusion method that copes with uncertainty and escape from the Condorcet paradox. To model preferences under uncertainty, we propose to develop a model of preferences based on belief function theory that accurately describes and captures the uncertainty associated with individual or collective preferences. This work improves and extends the previous results. This work improves and extends the contribution presented in a previous work. The benefits of our contribution are twofold. On the one hand, we propose a qualitative and expressive preference modeling strategy based on belief-function theory which scales better with the number of sources. On the other hand, we propose an incremental distance-based algorithm (using Jousselme distance) for the construction of the collective preference order to avoid the Condorcet Paradox.
Tasks
Published	2017-08-09
URL	http://arxiv.org/abs/1708.03259v1
PDF	http://arxiv.org/pdf/1708.03259v1.pdf
PWC	https://paperswithcode.com/paper/preference-fusion-and-condorcets-paradox
Repo
Framework

Maximum A Posteriori Inference in Sum-Product Networks


Title	Maximum A Posteriori Inference in Sum-Product Networks
Authors	Jun Mei, Yong Jiang, Kewei Tu
Abstract	Sum-product networks (SPNs) are a class of probabilistic graphical models that allow tractable marginal inference. However, the maximum a posteriori (MAP) inference in SPNs is NP-hard. We investigate MAP inference in SPNs from both theoretical and algorithmic perspectives. For the theoretical part, we reduce general MAP inference to its special case without evidence and hidden variables; we also show that it is NP-hard to approximate the MAP problem to $2^{n^\epsilon}$ for fixed $0 \leq \epsilon < 1$, where $n$ is the input size. For the algorithmic part, we first present an exact MAP solver that runs reasonably fast and could handle SPNs with up to 1k variables and 150k arcs in our experiments. We then present a new approximate MAP solver with a good balance between speed and accuracy, and our comprehensive experiments on real-world datasets show that it has better overall performance than existing approximate solvers.
Tasks
Published	2017-08-16
URL	http://arxiv.org/abs/1708.04846v3
PDF	http://arxiv.org/pdf/1708.04846v3.pdf
PWC	https://paperswithcode.com/paper/maximum-a-posteriori-inference-in-sum-product
Repo
Framework

Large-scale network motif analysis using compression


Title	Large-scale network motif analysis using compression
Authors	Peter Bloem, Steven de Rooij
Abstract	We introduce a new method for finding network motifs: interesting or informative subgraph patterns in a network. Subgraphs are motifs when their frequency in the data is high compared to the expected frequency under a null model. To compute this expectation, a full or approximate count of the occurrences of a motif is normally repeated on as many as 1000 random graphs sampled from the null model; a prohibitively expensive step. We use ideas from the Minimum Description Length (MDL) literature to define a new measure of motif relevance. With our method, samples from the null model are not required. Instead we compute the probability of the data under the null model and compare this to the probability under a specially designed alternative model. With this new relevance test, we can search for motifs by random sampling, rather than requiring an accurate count of all instances of a motif. This allows motif analysis to scale to networks with billions of links.
Tasks
Published	2017-01-08
URL	https://arxiv.org/abs/1701.02026v3
PDF	https://arxiv.org/pdf/1701.02026v3.pdf
PWC	https://paperswithcode.com/paper/finding-network-motifs-in-large-graphs-using
Repo
Framework