January 28, 2020

2945 words 14 mins read

Paper Group ANR 794

Joint Diacritization, Lemmatization, Normalization, and Fine-Grained Morphological Tagging. Trace-back Along Capsules and Its Application on Semantic Segmentation. Multi-Product Dynamic Pricing in High-Dimensions with Heterogenous Price Sensitivity. Predicting human decisions with behavioral theories and machine learning. Deep Reinforcement Learnin …

Joint Diacritization, Lemmatization, Normalization, and Fine-Grained Morphological Tagging


Title	Joint Diacritization, Lemmatization, Normalization, and Fine-Grained Morphological Tagging
Authors	Nasser Zalmout, Nizar Habash
Abstract	Semitic languages can be highly ambiguous, having several interpretations of the same surface forms, and morphologically rich, having many morphemes that realize several morphological features. This is further exacerbated for dialectal content, which is more prone to noise and lacks a standard orthography. The morphological features can be lexicalized, like lemmas and diacritized forms, or non-lexicalized, like gender, number, and part-of-speech tags, among others. Joint modeling of the lexicalized and non-lexicalized features can identify more intricate morphological patterns, which provide better context modeling, and further disambiguate ambiguous lexical choices. However, the different modeling granularity can make joint modeling more difficult. Our approach models the different features jointly, whether lexicalized (on the character-level), where we also model surface form normalization, or non-lexicalized (on the word-level). We use Arabic as a test case, and achieve state-of-the-art results for Modern Standard Arabic, with 20% relative error reduction, and Egyptian Arabic (a dialectal variant of Arabic), with 11% reduction.
Tasks	Lemmatization, Morphological Tagging
Published	2019-10-05
URL	https://arxiv.org/abs/1910.02267v1
PDF	https://arxiv.org/pdf/1910.02267v1.pdf
PWC	https://paperswithcode.com/paper/joint-diacritization-lemmatization
Repo
Framework

Trace-back Along Capsules and Its Application on Semantic Segmentation


Title	Trace-back Along Capsules and Its Application on Semantic Segmentation
Authors	Tao Sun, Zhewei Wang, C. D. Smith, Jundong Liu
Abstract	In this paper, we propose a capsule-based neural network model to solve the semantic segmentation problem. By taking advantage of the extractable part-whole dependencies available in capsule layers, we derive the probabilities of the class labels for individual capsules through a recursive, layer-by-layer procedure. We model this procedure as a traceback pipeline and take it as a central piece to build an end-to-end segmentation network. Under the proposed framework, image-level class labels and object boundaries are jointly sought in an explicit manner, which poses a significant advantage over the state-of-the-art fully convolutional network (FCN) solutions. Experiments conducted on modified MNIST and neuroimages demonstrate that our model considerably enhance the segmentation performance compared to the leading FCN variant.
Tasks	Semantic Segmentation
Published	2019-01-09
URL	http://arxiv.org/abs/1901.02920v1
PDF	http://arxiv.org/pdf/1901.02920v1.pdf
PWC	https://paperswithcode.com/paper/trace-back-along-capsules-and-its-application
Repo
Framework

Multi-Product Dynamic Pricing in High-Dimensions with Heterogenous Price Sensitivity


Title	Multi-Product Dynamic Pricing in High-Dimensions with Heterogenous Price Sensitivity
Authors	Adel Javanmard, Hamid Nazerzadeh, Simeng Shao
Abstract	We consider the problem of multi-product dynamic pricing, in a contextual setting, for a seller of differentiated products. In this environment, the customers arrive over time and products are described by high-dimensional feature vectors. Each customer chooses a product according to the widely used Multinomial Logit (MNL) choice model and her utility depends on the product features as well as the prices offered. Our model allows for heterogenous price sensitivities for products. The seller a-priori does not know the parameters of the choice model but can learn them through interactions with the customers. The seller’s goal is to design a pricing policy that maximizes her cumulative revenue. This model is motivated by online marketplaces such as Airbnb platform and online advertising. We measure the performance of a pricing policy in terms of regret, which is the expected revenue loss with respect to a clairvoyant policy that knows the parameters of the choice model in advance and always sets the revenue-maximizing prices. We propose a pricing policy, named M3P, that achieves a $T$-period regret of $O(\log(Td) ( \sqrt{T}+ d\log(T)))$ under heterogenous price sensitivity for products with features of dimension $d$. We also prove that no policy can achieve worst-case $T$-regret better than $\Omega(\sqrt{T})$.
Tasks
Published	2019-01-04
URL	https://arxiv.org/abs/1901.01030v2
PDF	https://arxiv.org/pdf/1901.01030v2.pdf
PWC	https://paperswithcode.com/paper/multi-product-dynamic-pricing-in-high
Repo
Framework

Predicting human decisions with behavioral theories and machine learning


Title	Predicting human decisions with behavioral theories and machine learning
Authors	Ori Plonsky, Reut Apel, Eyal Ert, Moshe Tennenholtz, David Bourgin, Joshua C. Peterson, Daniel Reichman, Thomas L. Griffiths, Stuart J. Russell, Evan C. Carter, James F. Cavanagh, Ido Erev
Abstract	Behavioral decision theories aim to explain human behavior. Can they help predict it? An open tournament for prediction of human choices in fundamental economic decision tasks is presented. The results suggest that integration of certain behavioral theories as features in machine learning systems provides the best predictions. Surprisingly, the most useful theories for prediction build on basic properties of human and animal learning and are very different from mainstream decision theories that focus on deviations from rational choice. Moreover, we find that theoretical features should be based not only on qualitative behavioral insights (e.g. loss aversion), but also on quantitative behavioral foresights generated by functional descriptive models (e.g. Prospect Theory). Our analysis prescribes a recipe for derivation of explainable, useful predictions of human decisions.
Tasks
Published	2019-04-15
URL	http://arxiv.org/abs/1904.06866v1
PDF	http://arxiv.org/pdf/1904.06866v1.pdf
PWC	https://paperswithcode.com/paper/predicting-human-decisions-with-behavioral
Repo
Framework

Deep Reinforcement Learning-Based Channel Allocation for Wireless LANs with Graph Convolutional Networks


Title	Deep Reinforcement Learning-Based Channel Allocation for Wireless LANs with Graph Convolutional Networks
Authors	Kota Nakashima, Shotaro Kamiya, Kazuki Ohtsu, Koji Yamamoto, Takayuki Nishio, Masahiro Morikura
Abstract	Last year, IEEE 802.11 Extremely High Throughput Study Group (EHT Study Group) was established to initiate discussions on new IEEE 802.11 features. Coordinated control methods of the access points (APs) in the wireless local area networks (WLANs) are discussed in EHT Study Group. The present study proposes a deep reinforcement learning-based channel allocation scheme using graph convolutional networks (GCNs). As a deep reinforcement learning method, we use a well-known method double deep Q-network. In densely deployed WLANs, the number of the available topologies of APs is extremely high, and thus we extract the features of the topological structures based on GCNs. We apply GCNs to a contention graph where APs within their carrier sensing ranges are connected to extract the features of carrier sensing relationships. Additionally, to improve the learning speed especially in an early stage of learning, we employ a game theory-based method to collect the training data independently of the neural network model. The simulation results indicate that the proposed method can appropriately control the channels when compared to extant methods.
Tasks
Published	2019-05-17
URL	https://arxiv.org/abs/1905.07144v1
PDF	https://arxiv.org/pdf/1905.07144v1.pdf
PWC	https://paperswithcode.com/paper/deep-reinforcement-learning-based-channel
Repo
Framework

Attribute-Guided Coupled GAN for Cross-Resolution Face Recognition


Title	Attribute-Guided Coupled GAN for Cross-Resolution Face Recognition
Authors	Veeru Talreja, Fariborz Taherkhani, Matthew C Valenti, Nasser M Nasrabadi
Abstract	In this paper, we propose a novel attribute-guided cross-resolution (low-resolution to high-resolution) face recognition framework that leverages a coupled generative adversarial network (GAN) structure with adversarial training to find the hidden relationship between the low-resolution and high-resolution images in a latent common embedding subspace. The coupled GAN framework consists of two sub-networks, one dedicated to the low-resolution domain and the other dedicated to the high-resolution domain. Each sub-network aims to find a projection that maximizes the pair-wise correlation between the two feature domains in a common embedding subspace. In addition to projecting the images into a common subspace, the coupled network also predicts facial attributes to improve the cross-resolution face recognition. Specifically, our proposed coupled framework exploits facial attributes to further maximize the pair-wise correlation by implicitly matching facial attributes of the low and high-resolution images during the training, which leads to a more discriminative embedding subspace resulting in performance enhancement for cross-resolution face recognition. The efficacy of our approach compared with the state-of-the-art is demonstrated using the LFWA, Celeb-A, SCFace and UCCS datasets.
Tasks	Face Recognition
Published	2019-08-05
URL	https://arxiv.org/abs/1908.01790v1
PDF	https://arxiv.org/pdf/1908.01790v1.pdf
PWC	https://paperswithcode.com/paper/attribute-guided-coupled-gan-for-cross
Repo
Framework

CAMAL: Context-Aware Multi-scale Attention framework for Lightweight Visual Place Recognition


Title	CAMAL: Context-Aware Multi-scale Attention framework for Lightweight Visual Place Recognition
Authors	Ahmad Khaliq, Shoaib Ehsan, Michael Milford, Klaus McDonald-Maier
Abstract	In the last few years, Deep Convolutional Neural Networks (D-CNNs) have shown state-of-the-art performances for Visual Place Recognition (VPR). Their prestigious generalization power has played a vital role in identifying persistent image regions under changing conditions and viewpoints. However, against the computation intensive D-CNNs based VPR algorithms, lightweight VPR techniques are preferred for resource-constraints mobile robots. This paper presents a lightweight CNN-based VPR technique that captures multi-layer context-aware attentions robust under changing environment and viewpoints. Evaluation of challenging benchmark datasets reveals better performance at low memory and resources utilization over state-of-the-art contemporary VPR methodologies.
Tasks	Visual Place Recognition
Published	2019-09-18
URL	https://arxiv.org/abs/1909.08153v1
PDF	https://arxiv.org/pdf/1909.08153v1.pdf
PWC	https://paperswithcode.com/paper/camal-context-aware-multi-scale-attention
Repo
Framework

Attention-Aware Age-Agnostic Visual Place Recognition


Title	Attention-Aware Age-Agnostic Visual Place Recognition
Authors	Ziqi Wang, Jiahui Li, Seyran Khademi, Jan van Gemert
Abstract	A cross-domain visual place recognition (VPR) task is proposed in this work, i.e., matching images of the same architectures depicted in different domains. VPR is commonly treated as an image retrieval task, where a query image from an unknown location is matched with relevant instances from geo-tagged gallery database. Different from conventional VPR settings where the query images and gallery images come from the same domain, we propose a more common but challenging setup where the query images are collected under a new unseen condition. The two domains involved in this work are contemporary street view images of Amsterdam from the Mapillary dataset (source domain) and historical images of the same city from Beeldbank dataset (target domain). We tailored an age-invariant feature learning CNN that can focus on domain invariant objects and learn to match images based on a weakly supervised ranking loss. We propose an attention aggregation module that is robust to domain discrepancy between the train and the test data. Further, a multi-kernel maximum mean discrepancy (MK-MMD) domain adaptation loss is adopted to improve the cross-domain ranking performance. Both attention and adaptation modules are unsupervised while the ranking loss uses weak supervision. Visual inspection shows that the attention module focuses on built forms while the dramatically changing environment are less weighed. Our proposed CNN achieves state of the art results (99% accuracy) on the single-domain VPR task and 20% accuracy at its best on the cross-domain VPR task, revealing the difficulty of age-invariant VPR.
Tasks	Domain Adaptation, Image Retrieval, Visual Place Recognition
Published	2019-09-11
URL	https://arxiv.org/abs/1909.05163v1
PDF	https://arxiv.org/pdf/1909.05163v1.pdf
PWC	https://paperswithcode.com/paper/attention-aware-age-agnostic-visual-place
Repo
Framework


Title	Automatic Fashion Knowledge Extraction from Social Media
Authors	Yunshan Ma, Lizi Liao, Tat-Seng Chua
Abstract	Fashion knowledge plays a pivotal role in helping people in their dressing. In this paper, we present a novel system to automatically harvest fashion knowledge from social media. It unifies three tasks of occasion, person and clothing discovery from multiple modalities of images, texts and metadata. A contextualized fashion concept learning model is applied to leverage the rich contextual information for improving the fashion concept learning performance. At the same time, to counter the label noise within training data, we employ a weak label modeling method to further boost the performance. We build a website to demonstrate the quality of fashion knowledge extracted by our system.
Tasks
Published	2019-08-12
URL	https://arxiv.org/abs/1908.04045v1
PDF	https://arxiv.org/pdf/1908.04045v1.pdf
PWC	https://paperswithcode.com/paper/automatic-fashion-knowledge-extraction-from
Repo
Framework

Rapid Light Field Depth Estimation with Semi-Global Matching


Title	Rapid Light Field Depth Estimation with Semi-Global Matching
Authors	Yuriy Anisimov, Oliver Wasenmüller, Didier Stricker
Abstract	Running time of the light field depth estimation algorithms is typically high. This assessment is based on the computational complexity of existing methods and the large amounts of data involved. The aim of our work is to develop a simple and fast algorithm for accurate depth computation. In this context, we propose an approach, which involves Semi-Global Matching for the processing of light field images. It forms on comparison of pixels’ correspondences with different metrics in the substantially bounded light field space. We show that our method is suitable for the fast production of a proper result in a variety of light field configurations
Tasks	Depth Estimation
Published	2019-07-31
URL	https://arxiv.org/abs/1907.13449v1
PDF	https://arxiv.org/pdf/1907.13449v1.pdf
PWC	https://paperswithcode.com/paper/rapid-light-field-depth-estimation-with-semi
Repo
Framework


Title	Learning to Recommend via Meta Parameter Partition
Authors	Liang Zhao, Yang Wang, Daxiang Dong, Hao Tian
Abstract	In this paper we propose to solve an important problem in recommendation – user cold start, based on meta leaning method. Previous meta learning approaches finetune all parameters for each new user, which is both computing and storage expensive. In contrast, we divide model parameters into fixed and adaptive parts and develop a two-stage meta learning algorithm to learn them separately. The fixed part, capturing user invariant features, is shared by all users and is learned during offline meta learning stage. The adaptive part, capturing user specific features, is learned during online meta learning stage. By decoupling user invariant parameters from user dependent parameters, the proposed approach is more efficient and storage cheaper than previous methods. It also has potential to deal with catastrophic forgetting while continually adapting for streaming coming users. Experiments on production data demonstrates that the proposed method converges faster and to a better performance than baseline methods. Meta-training without online meta model finetuning increases the AUC from 72.24% to 74.72% (2.48% absolute improvement). Online meta training achieves a further gain of 2.46% absolute improvement comparing with offline meta training.
Tasks	Meta-Learning
Published	2019-12-04
URL	https://arxiv.org/abs/1912.04108v1
PDF	https://arxiv.org/pdf/1912.04108v1.pdf
PWC	https://paperswithcode.com/paper/learning-to-recommend-via-meta-parameter
Repo
Framework

Action Recognition in Untrimmed Videos with Composite Self-Attention Two-Stream Framework


Title	Action Recognition in Untrimmed Videos with Composite Self-Attention Two-Stream Framework
Authors	Dong Cao, Lisha Xu, HaiBo Chen
Abstract	With the rapid development of deep learning algorithms, action recognition in video has achieved many important research results. One issue in action recognition, Zero-Shot Action Recognition (ZSAR), has recently attracted considerable attention, which classify new categories without any positive examples. Another difficulty in action recognition is that untrimmed data may seriously affect model performance. We propose a composite two-stream framework with a pre-trained model. Our proposed framework includes a classifier branch and a composite feature branch. The graph network model is adopted in each of the two branches, which effectively improves the feature extraction and reasoning ability of the framework. In the composite feature branch, a 3-channel self-attention models are constructed to weight each frame in the video and give more attention to the key frames. Each self-attention models channel outputs a set of attention weights to focus on a particular aspect of the video, and a set of attention weights corresponds to a one-dimensional vector. The 3-channel self-attention models can evaluate key frames from multiple aspects, and the output sets of attention weight vectors form an attention matrix, which effectively enhances the attention of key frames with strong correlation of action. This model can implement action recognition under zero-shot conditions, and has good recognition performance for untrimmed video data. Experimental results on relevant data sets confirm the validity of our model.
Tasks	Temporal Action Localization
Published	2019-08-04
URL	https://arxiv.org/abs/1908.04353v2
PDF	https://arxiv.org/pdf/1908.04353v2.pdf
PWC	https://paperswithcode.com/paper/action-recognition-in-untrimmed-videos-with
Repo
Framework

Gaussian Process Learning via Fisher Scoring of Vecchia’s Approximation


Title	Gaussian Process Learning via Fisher Scoring of Vecchia’s Approximation
Authors	Joseph Guinness
Abstract	We derive a single pass algorithm for computing the gradient and Fisher information of Vecchia’s Gaussian process loglikelihood approximation, which provides a computationally efficient means for applying the Fisher scoring algorithm for maximizing the loglikelihood. The advantages of the optimization techniques are demonstrated in numerical examples and in an application to Argo ocean temperature data. The new methods are more accurate and much faster than an optimization method that uses only function evaluations, especially when the covariance function has many parameters. This allows practitioners to fit nonstationary models to large spatial and spatial-temporal datasets.
Tasks
Published	2019-05-20
URL	https://arxiv.org/abs/1905.08374v1
PDF	https://arxiv.org/pdf/1905.08374v1.pdf
PWC	https://paperswithcode.com/paper/gaussian-process-learning-via-fisher-scoring
Repo
Framework

Adversarially Approximated Autoencoder for Image Generation and Manipulation


Title	Adversarially Approximated Autoencoder for Image Generation and Manipulation
Authors	Wenju Xu, Shawn Keshmiri, Guanghui Wang
Abstract	Regularized autoencoders learn the latent codes, a structure with the regularization under the distribution, which enables them the capability to infer the latent codes given observations and generate new samples given the codes. However, they are sometimes ambiguous as they tend to produce reconstructions that are not necessarily faithful reproduction of the inputs. The main reason is to enforce the learned latent code distribution to match a prior distribution while the true distribution remains unknown. To improve the reconstruction quality and learn the latent space a manifold structure, this work present a novel approach using the adversarially approximated autoencoder (AAAE) to investigate the latent codes with adversarial approximation. Instead of regularizing the latent codes by penalizing on the distance between the distributions of the model and the target, AAAE learns the autoencoder flexibly and approximates the latent space with a simpler generator. The ratio is estimated using generative adversarial network (GAN) to enforce the similarity of the distributions. Additionally, the image space is regularized with an additional adversarial regularizer. The proposed approach unifies two deep generative models for both latent space inference and diverse generation. The learning scheme is realized without regularization on the latent codes, which also encourages faithful reconstruction. Extensive validation experiments on four real-world datasets demonstrate the superior performance of AAAE. In comparison to the state-of-the-art approaches, AAAE generates samples with better quality and shares the properties of regularized autoencoder with a nice latent manifold structure.
Tasks	Image Generation
Published	2019-02-14
URL	http://arxiv.org/abs/1902.05581v1
PDF	http://arxiv.org/pdf/1902.05581v1.pdf
PWC	https://paperswithcode.com/paper/adversarially-approximated-autoencoder-for
Repo
Framework

Generative models as parsimonious descriptions of sensorimotor loops


Title	Generative models as parsimonious descriptions of sensorimotor loops
Authors	Manuel Baltieri, Christopher L. Buckley
Abstract	The Bayesian brain hypothesis, predictive processing and variational free energy minimisation are typically used to describe perceptual processes based on accurate generative models of the world. However, generative models need not be veridical representations of the environment. We suggest that they can (and should) be used to describe sensorimotor relationships relevant for behaviour rather than precise accounts of the world.
Tasks
Published	2019-04-29
URL	http://arxiv.org/abs/1904.12937v1
PDF	http://arxiv.org/pdf/1904.12937v1.pdf
PWC	https://paperswithcode.com/paper/generative-models-as-parsimonious
Repo
Framework