July 27, 2019

2983 words 15 mins read

Paper Group ANR 569

Robust polynomial regression up to the information theoretic limit. Statistical learning of rational wavelet transform for natural images. Analysing Congestion Problems in Multi-agent Reinforcement Learning. Local System Voting Feature for Machine Translation System Combination. Convolutional Networks with MuxOut Layers as Multi-rate Systems for Im …

Robust polynomial regression up to the information theoretic limit


Title	Robust polynomial regression up to the information theoretic limit
Authors	Daniel Kane, Sushrut Karmalkar, Eric Price
Abstract	We consider the problem of robust polynomial regression, where one receives samples $(x_i, y_i)$ that are usually within $\sigma$ of a polynomial $y = p(x)$, but have a $\rho$ chance of being arbitrary adversarial outliers. Previously, it was known how to efficiently estimate $p$ only when $\rho < \frac{1}{\log d}$. We give an algorithm that works for the entire feasible range of $\rho < 1/2$, while simultaneously improving other parameters of the problem. We complement our algorithm, which gives a factor 2 approximation, with impossibility results that show, for example, that a $1.09$ approximation is impossible even with infinitely many samples.
Tasks
Published	2017-08-10
URL	http://arxiv.org/abs/1708.03257v1
PDF	http://arxiv.org/pdf/1708.03257v1.pdf
PWC	https://paperswithcode.com/paper/robust-polynomial-regression-up-to-the
Repo
Framework

Statistical learning of rational wavelet transform for natural images


Title	Statistical learning of rational wavelet transform for natural images
Authors	Naushad Ansari, Anubha Gupta
Abstract	Motivated with the concept of transform learning and the utility of rational wavelet transform in audio and speech processing, this paper proposes Rational Wavelet Transform Learning in Statistical sense (RWLS) for natural images. The proposed RWLS design is carried out via lifting framework and is shown to have a closed form solution. The efficacy of the learned transform is demonstrated in the application of compressed sensing (CS) based reconstruction. The learned RWLS is observed to perform better than the existing standard dyadic wavelet transforms.
Tasks
Published	2017-05-02
URL	http://arxiv.org/abs/1705.00821v1
PDF	http://arxiv.org/pdf/1705.00821v1.pdf
PWC	https://paperswithcode.com/paper/statistical-learning-of-rational-wavelet
Repo
Framework

Analysing Congestion Problems in Multi-agent Reinforcement Learning


Title	Analysing Congestion Problems in Multi-agent Reinforcement Learning
Authors	Roxana Rădulescu, Peter Vrancx, Ann Nowé
Abstract	Congestion problems are omnipresent in today’s complex networks and represent a challenge in many research domains. In the context of Multi-agent Reinforcement Learning (MARL), approaches like difference rewards and resource abstraction have shown promising results in tackling such problems. Resource abstraction was shown to be an ideal candidate for solving large-scale resource allocation problems in a fully decentralized manner. However, its performance and applicability strongly depends on some, until now, undocumented assumptions. Two of the main congestion benchmark problems considered in the literature are: the Beach Problem Domain and the Traffic Lane Domain. In both settings the highest system utility is achieved when overcrowding one resource and keeping the rest at optimum capacity. We analyse how abstract grouping can promote this behaviour and how feasible it is to apply this approach in a real-world domain (i.e., what assumptions need to be satisfied and what knowledge is necessary). We introduce a new test problem, the Road Network Domain (RND), where the resources are no longer independent, but rather part of a network (e.g., road network), thus choosing one path will also impact the load on other paths having common road segments. We demonstrate the application of state-of-the-art MARL methods for this new congestion model and analyse their performance. RND allows us to highlight an important limitation of resource abstraction and show that the difference rewards approach manages to better capture and inform the agents about the dynamics of the environment.
Tasks	Multi-agent Reinforcement Learning
Published	2017-02-28
URL	http://arxiv.org/abs/1702.08736v2
PDF	http://arxiv.org/pdf/1702.08736v2.pdf
PWC	https://paperswithcode.com/paper/analysing-congestion-problems-in-multi-agent
Repo
Framework

Local System Voting Feature for Machine Translation System Combination


Title	Local System Voting Feature for Machine Translation System Combination
Authors	Markus Freitag, Jan-Thorsten Peter, Stephan Peitz, Minwei Feng, Hermann Ney
Abstract	In this paper, we enhance the traditional confusion network system combination approach with an additional model trained by a neural network. This work is motivated by the fact that the commonly used binary system voting models only assign each input system a global weight which is responsible for the global impact of each input system on all translations. This prevents individual systems with low system weights from having influence on the system combination output, although in some situations this could be helpful. Further, words which have only been seen by one or few systems rarely have a chance of being present in the combined output. We train a local system voting model by a neural network which is based on the words themselves and the combinatorial occurrences of the different system outputs. This gives system combination the option to prefer other systems at different word positions even for the same sentence.
Tasks	Machine Translation
Published	2017-02-10
URL	http://arxiv.org/abs/1702.03033v1
PDF	http://arxiv.org/pdf/1702.03033v1.pdf
PWC	https://paperswithcode.com/paper/local-system-voting-feature-for-machine
Repo
Framework

Convolutional Networks with MuxOut Layers as Multi-rate Systems for Image Upscaling


Title	Convolutional Networks with MuxOut Layers as Multi-rate Systems for Image Upscaling
Authors	Pablo Navarrete Michelini, Hanwen Liu
Abstract	We interpret convolutional networks as adaptive filters and combine them with so-called MuxOut layers to efficiently upscale low resolution images. We formalize this interpretation by deriving a linear and space-variant structure of a convolutional network when its activations are fixed. We introduce general purpose algorithms to analyze a network and show its overall filter effect for each given location. We use this analysis to evaluate two types of image upscalers: deterministic upscalers that target the recovery of details from original content; and second, a new generation of upscalers that can sample the distribution of upscale aliases (images that share the same downscale version) that look like real content.
Tasks
Published	2017-05-22
URL	http://arxiv.org/abs/1705.07772v1
PDF	http://arxiv.org/pdf/1705.07772v1.pdf
PWC	https://paperswithcode.com/paper/convolutional-networks-with-muxout-layers-as
Repo
Framework

Automatic Handgun Detection Alarm in Videos Using Deep Learning


Title	Automatic Handgun Detection Alarm in Videos Using Deep Learning
Authors	Roberto Olmos, Siham Tabik, Francisco Herrera
Abstract	Current surveillance and control systems still require human supervision and intervention. This work presents a novel automatic handgun detection system in videos appropriate for both, surveillance and control purposes. We reformulate this detection problem into the problem of minimizing false positives and solve it by building the key training data-set guided by the results of a deep Convolutional Neural Networks (CNN) classifier, then assessing the best classification model under two approaches, the sliding window approach and region proposal approach. The most promising results are obtained by Faster R-CNN based model trained on our new database. The best detector show a high potential even in low quality youtube videos and provides satisfactory results as automatic alarm system. Among 30 scenes, it successfully activates the alarm after five successive true positives in less than 0.2 seconds, in 27 scenes. We also define a new metric, Alarm Activation per Interval (AApI), to assess the performance of a detection model as an automatic detection system in videos.
Tasks
Published	2017-02-16
URL	http://arxiv.org/abs/1702.05147v1
PDF	http://arxiv.org/pdf/1702.05147v1.pdf
PWC	https://paperswithcode.com/paper/automatic-handgun-detection-alarm-in-videos
Repo
Framework

Learning RGB-D Salient Object Detection using background enclosure, depth contrast, and top-down features


Title	Learning RGB-D Salient Object Detection using background enclosure, depth contrast, and top-down features
Authors	Riku Shigematsu, David Feng, Shaodi You, Nick Barnes
Abstract	Recently, deep Convolutional Neural Networks (CNN) have demonstrated strong performance on RGB salient object detection. Although, depth information can help improve detection results, the exploration of CNNs for RGB-D salient object detection remains limited. Here we propose a novel deep CNN architecture for RGB-D salient object detection that exploits high-level, mid-level, and low level features. Further, we present novel depth features that capture the ideas of background enclosure and depth contrast that are suitable for a learned approach. We show improved results compared to state-of-the-art RGB-D salient object detection methods. We also show that the low-level and mid-level depth features both contribute to improvements in the results. Especially, F-Score of our method is 0.848 on RGBD1000 dataset, which is 10.7% better than the second place.
Tasks	Object Detection, Salient Object Detection
Published	2017-05-10
URL	http://arxiv.org/abs/1705.03607v1
PDF	http://arxiv.org/pdf/1705.03607v1.pdf
PWC	https://paperswithcode.com/paper/learning-rgb-d-salient-object-detection-using
Repo
Framework

Regret Bounds and Regimes of Optimality for User-User and Item-Item Collaborative Filtering


Title	Regret Bounds and Regimes of Optimality for User-User and Item-Item Collaborative Filtering
Authors	Guy Bresler, Mina Karzand
Abstract	We consider an online model for recommendation systems, with each user being recommended an item at each time-step and providing ‘like’ or ‘dislike’ feedback. Each user may be recommended a given item at most once. A latent variable model specifies the user preferences: both users and items are clustered into types. All users of a given type have identical preferences for the items, and similarly, items of a given type are either all liked or all disliked by a given user. We assume that the matrix encoding the preferences of each user type for each item type is randomly generated; in this way, the model captures structure in both the item and user spaces, the amount of structure depending on the number of each of the types. The measure of performance of the recommendation system is the expected number of disliked recommendations per user, defined as expected regret. We propose two algorithms inspired by user-user and item-item collaborative filtering (CF), modified to explicitly make exploratory recommendations, and prove performance guarantees in terms of their expected regret. For two regimes of model parameters, with structure only in item space or only in user space, we prove information-theoretic lower bounds on regret that match our upper bounds up to logarithmic factors. Our analysis elucidates system operating regimes in which existing CF algorithms are nearly optimal.
Tasks	Recommendation Systems
Published	2017-11-06
URL	https://arxiv.org/abs/1711.02198v2
PDF	https://arxiv.org/pdf/1711.02198v2.pdf
PWC	https://paperswithcode.com/paper/regret-bounds-and-regimes-of-optimality-for
Repo
Framework

Towards Applying the OPRA Theory to Shape Similarity


Title	Towards Applying the OPRA Theory to Shape Similarity
Authors	Christopher H. Dorr, Reinhard Moratz
Abstract	The motivation for using qualitative shape descriptions is as follows: qualitative shape descriptions can implicitly act as a schema for measuring the similarity of shapes, which has the potential to be cognitively adequate. Then, shapes which are similar to each other would also be similar for a pattern recognition algorithm. There is substantial work in pattern recognition and computer vision dealing with shape similarity. Here with our approach to qualitative shape descriptions and shape similarity, the focus is on achieving a representation using only simple predicates that a human could even apply without computer support.
Tasks
Published	2017-05-07
URL	http://arxiv.org/abs/1705.02653v1
PDF	http://arxiv.org/pdf/1705.02653v1.pdf
PWC	https://paperswithcode.com/paper/towards-applying-the-opra-theory-to-shape
Repo
Framework

Object-Part Attention Model for Fine-grained Image Classification


Title	Object-Part Attention Model for Fine-grained Image Classification
Authors	Yuxin Peng, Xiangteng He, Junjie Zhao
Abstract	Fine-grained image classification is to recognize hundreds of subcategories belonging to the same basic-level category, such as 200 subcategories belonging to the bird, which is highly challenging due to large variance in the same subcategory and small variance among different subcategories. Existing methods generally first locate the objects or parts and then discriminate which subcategory the image belongs to. However, they mainly have two limitations: (1) Relying on object or part annotations which are heavily labor consuming. (2) Ignoring the spatial relationships between the object and its parts as well as among these parts, both of which are significantly helpful for finding discriminative parts. Therefore, this paper proposes the object-part attention model (OPAM) for weakly supervised fine-grained image classification, and the main novelties are: (1) Object-part attention model integrates two level attentions: object-level attention localizes objects of images, and part-level attention selects discriminative parts of object. Both are jointly employed to learn multi-view and multi-scale features to enhance their mutual promotions. (2) Object-part spatial constraint model combines two spatial constraints: object spatial constraint ensures selected parts highly representative, and part spatial constraint eliminates redundancy and enhances discrimination of selected parts. Both are jointly employed to exploit the subtle and local differences for distinguishing the subcategories. Importantly, neither object nor part annotations are used in our proposed approach, which avoids the heavy labor consumption of labeling. Comparing with more than 10 state-of-the-art methods on 4 widely-used datasets, our OPAM approach achieves the best performance.
Tasks	Fine-Grained Image Classification, Image Classification
Published	2017-04-06
URL	http://arxiv.org/abs/1704.01740v2
PDF	http://arxiv.org/pdf/1704.01740v2.pdf
PWC	https://paperswithcode.com/paper/object-part-attention-model-for-fine-grained
Repo
Framework

STAR: Spatio-Temporal Altimeter Waveform Retracking using Sparse Representation and Conditional Random Fields


Title	STAR: Spatio-Temporal Altimeter Waveform Retracking using Sparse Representation and Conditional Random Fields
Authors	Ribana Roscher, Bernd Uebbing, Jürgen Kusche
Abstract	Satellite radar altimetry is one of the most powerful techniques for measuring sea surface height variations, with applications ranging from operational oceanography to climate research. Over open oceans, altimeter return waveforms generally correspond to the Brown model, and by inversion, estimated shape parameters provide mean surface height and wind speed. However, in coastal areas or over inland waters, the waveform shape is often distorted by land influence, resulting in peaks or fast decaying trailing edges. As a result, derived sea surface heights are then less accurate and waveforms need to be reprocessed by sophisticated algorithms. To this end, this work suggests a novel Spatio-Temporal Altimetry Retracking (STAR) technique. We show that STAR enables the derivation of sea surface heights over the open ocean as well as over coastal regions of at least the same quality as compared to existing retracking methods, but for a larger number of cycles and thus retaining more useful data. Novel elements of our method are (a) integrating information from spatially and temporally neighboring waveforms through a conditional random field approach, (b) sub-waveform detection, where relevant sub-waveforms are separated from corrupted or non-relevant parts through a sparse representation approach, and (c) identifying the final best set of sea surfaces heights from multiple likely heights using Dijkstra’s algorithm. We apply STAR to data from the Jason-1, Jason-2 and Envisat missions for study sites in the Gulf of Trieste, Italy and in the coastal region of the Ganges-Brahmaputra-Meghna estuary, Bangladesh. We compare to several established and recent retracking methods, as well as to tide gauge data. Our experiments suggest that the obtained sea surface heights are significantly less affected by outliers when compared to results obtained by other approaches.
Tasks
Published	2017-09-22
URL	http://arxiv.org/abs/1709.07681v1
PDF	http://arxiv.org/pdf/1709.07681v1.pdf
PWC	https://paperswithcode.com/paper/star-spatio-temporal-altimeter-waveform
Repo
Framework

Supervised Learning in Automatic Channel Selection for Epileptic Seizure Detection


Title	Supervised Learning in Automatic Channel Selection for Epileptic Seizure Detection
Authors	Nhan Truong, Levin Kuhlmann, Mohammad Reza Bonyadi, Jiawei Yang, Andrew Faulks, Omid Kavehei
Abstract	Detecting seizure using brain neuroactivations recorded by intracranial electroencephalogram (iEEG) has been widely used for monitoring, diagnosing, and closed-loop therapy of epileptic patients, however, computational efficiency gains are needed if state-of-the-art methods are to be implemented in implanted devices. We present a novel method for automatic seizure detection based on iEEG data that outperforms current state-of-the-art seizure detection methods in terms of computational efficiency while maintaining the accuracy. The proposed algorithm incorporates an automatic channel selection (ACS) engine as a pre-processing stage to the seizure detection procedure. The ACS engine consists of supervised classifiers which aim to find iEEGchannelswhich contribute the most to a seizure. Seizure detection stage involves feature extraction and classification. Feature extraction is performed in both frequency and time domains where spectral power and correlation between channel pairs are calculated. Random Forest is used in classification of interictal, ictal and early ictal periods of iEEG signals. Seizure detection in this paper is retrospective and patient-specific. iEEG data is accessed via Kaggle, provided by International Epilepsy Electro-physiology Portal. The dataset includes a training set of 6.5 hours of interictal data and 41 minin ictal data and a test set of 9.14 hours. Compared to the state-of-the-art on the same dataset, we achieve 49.4% increase in computational efficiency and 400 mins better in average for detection delay. The proposed model is able to detect a seizure onset at 91.95% sensitivity and 94.05% specificity with a mean detection delay of 2.77 s. The area under the curve (AUC) is 96.44%, that is comparable to the current state-of-the-art with AUC of 96.29%.
Tasks	Seizure Detection
Published	2017-01-31
URL	http://arxiv.org/abs/1701.08968v1
PDF	http://arxiv.org/pdf/1701.08968v1.pdf
PWC	https://paperswithcode.com/paper/supervised-learning-in-automatic-channel
Repo
Framework

Transferrable Plausibility Model - A Probabilistic Interpretation of Mathematical Theory of Evidence


Title	Transferrable Plausibility Model - A Probabilistic Interpretation of Mathematical Theory of Evidence
Authors	Mieczysław Kłopotek
Abstract	This paper suggests a new interpretation of the Dempster-Shafer theory in terms of probabilistic interpretation of plausibility. A new rule of combination of independent evidence is shown and its preservation of interpretation is demonstrated.
Tasks
Published	2017-04-06
URL	http://arxiv.org/abs/1704.01742v1
PDF	http://arxiv.org/pdf/1704.01742v1.pdf
PWC	https://paperswithcode.com/paper/transferrable-plausibility-model-a
Repo
Framework

Abstractions for AI-Based User Interfaces and Systems


Title	Abstractions for AI-Based User Interfaces and Systems
Authors	Alex Renda, Harrison Goldstein, Sarah Bird, Chris Quirk, Adrian Sampson
Abstract	Novel user interfaces based on artificial intelligence, such as natural-language agents, present new categories of engineering challenges. These systems need to cope with uncertainty and ambiguity, interface with machine learning algorithms, and compose information from multiple users to make decisions. We propose to treat these challenges as language-design problems. We describe three programming language abstractions for three core problems in intelligent system design. First, hypothetical worlds support nondeterministic search over spaces of alternative actions. Second, a feature type system abstracts the interaction between applications and learning algorithms. Finally, constructs for collaborative execution extend hypothetical worlds across multiple machines while controlling access to private data. We envision these features as first steps toward a complete language for implementing AI-based interfaces and applications.
Tasks
Published	2017-09-14
URL	http://arxiv.org/abs/1709.04991v1
PDF	http://arxiv.org/pdf/1709.04991v1.pdf
PWC	https://paperswithcode.com/paper/abstractions-for-ai-based-user-interfaces-and
Repo
Framework

Stochastic Primal Dual Coordinate Method with Non-Uniform Sampling Based on Optimality Violations


Title	Stochastic Primal Dual Coordinate Method with Non-Uniform Sampling Based on Optimality Violations
Authors	Atsushi Shibagaki, Ichiro Takeuchi
Abstract	We study primal-dual type stochastic optimization algorithms with non-uniform sampling. Our main theoretical contribution in this paper is to present a convergence analysis of Stochastic Primal Dual Coordinate (SPDC) Method with arbitrary sampling. Based on this theoretical framework, we propose Optimality Violation-based Sampling SPDC (ovsSPDC), a non-uniform sampling method based on Optimality Violation. We also propose two efficient heuristic variants of ovsSPDC called ovsSDPC+ and ovsSDPC++. Through intensive numerical experiments, we demonstrate that the proposed method and its variants are faster than other state-of-the-art primal-dual type stochastic optimization methods.
Tasks	Stochastic Optimization
Published	2017-03-21
URL	http://arxiv.org/abs/1703.07056v1
PDF	http://arxiv.org/pdf/1703.07056v1.pdf
PWC	https://paperswithcode.com/paper/stochastic-primal-dual-coordinate-method-with
Repo
Framework