January 26, 2020

3363 words 16 mins read

Paper Group ANR 1370

Transfer feature generating networks with semantic classes structure for zero-shot learning. Hybrid Channel Based Pedestrian Detection. Path Length Bounds for Gradient Descent and Flow. Deep Kernel Learning via Random Fourier Features. Wasserstein GANs for MR Imaging: from Paired to Unpaired Training. Discovery of Bias and Strategic Behavior in Cro …

Transfer feature generating networks with semantic classes structure for zero-shot learning


Title	Transfer feature generating networks with semantic classes structure for zero-shot learning
Authors	Guangfeng Lin, Wanjun Chen, Kaiyang Liao, Xiaobing Kang, Caixia Fan
Abstract	Feature generating networks face to the most important question, which is the fitting difference (inconsistence) of the distribution between the generated feature and the real data. This inconsistence further influence the performance of the networks model, because training samples from seen classes is disjointed with testing samples from unseen classes in zero-shot learning (ZSL). In generalization zero-shot learning (GZSL), testing samples come from not only seen classes but also unseen classes for closer to the practical situation. Therefore, most of feature generating networks difficultly obtain satisfactory performance for the challenging GZSL by adversarial learning the distribution of semantic classes. To alleviate the negative influence of this inconsistence for ZSL and GZSL, transfer feature generating networks with semantic classes structure (TFGNSCS) is proposed to construct networks model for improving the performance of ZSL and GZSL. TFGNSCS can not only consider the semantic structure relationship between seen and unseen classes, but also learn the difference of generating features by transferring classification model information from seen to unseen classes in networks. The proposed method can integrate the transfer loss, the classification loss and the Wasserstein distance loss to generate enough CNN features, on which softmax classifiers are trained for ZSL and GZSL. Experiments demonstrate that the performance of TFGNSCS outperforms that of the state of the arts on four challenging datasets, which are CUB,FLO,SUN, AWA in GZSL.
Tasks	Zero-Shot Learning
Published	2019-03-06
URL	https://arxiv.org/abs/1903.02204v2
PDF	https://arxiv.org/pdf/1903.02204v2.pdf
PWC	https://paperswithcode.com/paper/transfer-feature-generating-networks-with
Repo
Framework

Hybrid Channel Based Pedestrian Detection


Title	Hybrid Channel Based Pedestrian Detection
Authors	Fiseha B. Tesema, Hong Wu, Mingjian Chen, Junpeng Lin, William Zhu, Kaizhu Huang
Abstract	Pedestrian detection has achieved great improvements with the help of Convolutional Neural Networks (CNNs). CNN can learn high-level features from input images, but the insufficient spatial resolution of CNN feature channels (feature maps) may cause a loss of information, which is harmful especially to small instances. In this paper, we propose a new pedestrian detection framework, which extends the successful RPN+BF framework to combine handcrafted features and CNN features. RoI-pooling is used to extract features from both handcrafted channels (e.g. HOG+LUV, CheckerBoards or RotatedFilters) and CNN channels. Since handcrafted channels always have higher spatial resolution than CNN channels, we apply RoI-pooling with larger output resolution to handcrafted channels to keep more detailed information. Our ablation experiments show that the developed handcrafted features can reach better detection accuracy than the CNN features extracted from the VGG-16 net, and a performance gain can be achieved by combining them. Experimental results on Caltech pedestrian dataset with the original annotations and the improved annotations demonstrate the effectiveness of the proposed approach. When using a more advanced RPN in our framework, our approach can be further improved and get competitive results on both benchmarks.
Tasks	Pedestrian Detection
Published	2019-12-28
URL	https://arxiv.org/abs/1912.12431v2
PDF	https://arxiv.org/pdf/1912.12431v2.pdf
PWC	https://paperswithcode.com/paper/hybrid-channel-based-pedestrian-detection
Repo
Framework

Path Length Bounds for Gradient Descent and Flow


Title	Path Length Bounds for Gradient Descent and Flow
Authors	Chirag Gupta, Sivaraman Balakrishnan, Aaditya Ramdas
Abstract	We provide path length bounds on gradient descent (GD) and flow (GF) curves for various classes of smooth convex and nonconvex functions. We make six distinct contributions: (a) we prove a meta-theorem that if the iterates of GD exhibit linear convergence towards an optimal set, then its path length is upper bounded by the distance to the optimal set multiplied by a function of the rate of convergence, (b) under the Polyak-Lojasiewicz (PL) condition (a generalization of strong convexity that allows for certain nonconvex functions), we show that the aforementioned multiplicative factor is at most $\sqrt{\kappa}$, where $\kappa$ denotes the condition number of the function, (c) we show an $\widetilde\Omega(\sqrt{d} \wedge \kappa^{1/4})$, times the length of the direct path, lower bound on the worst-case path length for PL functions, (d) for the special case of quadratics, we show that the bound is $\Theta(\min{\sqrt{d},\sqrt{\log \kappa}})$ and in some cases can be independent of $\kappa$, (e) under the weaker assumption of just convexity, where there is no natural notion of a condition number, we prove that the path length can be at most $2^{4d\log d}$ times the length of the direct path, (f) finally, for separable quasiconvex (QC) functions the path length is both upper and lower bounded by ${\Theta}(\sqrt{d})$ times the length of the direct path.
Tasks
Published	2019-08-02
URL	https://arxiv.org/abs/1908.01089v2
PDF	https://arxiv.org/pdf/1908.01089v2.pdf
PWC	https://paperswithcode.com/paper/path-length-bounds-for-gradient-descent-and
Repo
Framework

Deep Kernel Learning via Random Fourier Features


Title	Deep Kernel Learning via Random Fourier Features
Authors	Jiaxuan Xie, Fanghui Liu, Kaijie Wang, Xiaolin Huang
Abstract	Kernel learning methods are among the most effective learning methods and have been vigorously studied in the past decades. However, when tackling with complicated tasks, classical kernel methods are not flexible or “rich” enough to describe the data and hence could not yield satisfactory performance. In this paper, via Random Fourier Features (RFF), we successfully incorporate the deep architecture into kernel learning, which significantly boosts the flexibility and richness of kernel machines while keeps kernels’ advantage of pairwise handling small data. With RFF, we could establish a deep structure and make every kernel in RFF layers could be trained end-to-end. Since RFF with different distributions could represent different kernels, our model has the capability of finding suitable kernels for each layer, which is much more flexible than traditional kernel-based methods where the kernel is pre-selected. This fact also helps yield a more sophisticated kernel cascade connection in the architecture. On small datasets (less than 1000 samples), for which deep learning is generally not suitable due to overfitting, our method achieves superior performance compared to advanced kernel methods. On large-scale datasets, including non-image and image classification tasks, our method also has competitive performance.
Tasks	Image Classification
Published	2019-10-07
URL	https://arxiv.org/abs/1910.02660v1
PDF	https://arxiv.org/pdf/1910.02660v1.pdf
PWC	https://paperswithcode.com/paper/deep-kernel-learning-via-random-fourier
Repo
Framework

Wasserstein GANs for MR Imaging: from Paired to Unpaired Training


Title	Wasserstein GANs for MR Imaging: from Paired to Unpaired Training
Authors	Ke Lei, Morteza Mardani, John M. Pauly, Shreyas S. Vasawanala
Abstract	Lack of ground-truth MR images (labels) impedes the common supervised training of deep networks for image reconstruction. To cope with this challenge, this paper leverages WGANs for unpaired training of reconstruction networks, where the inputs are the undersampled naively reconstructed images from one dataset, and the outputs are high-quality images from another dataset. The generator network is an unrolled neural network with a cascade of residual blocks and data consistency modules. The discriminator is also a multilayer CNN that plays the role of a critic scoring the quality of reconstructed images. Our extensive experiments with knee MRI datasets demonstrate unpaired WGAN training with minimal supervision is a viable option when there exists insufficient or no fully-sampled training label images that match the input images. Also, supervised paired training with additional WGAN loss achieves better and faster reconstruction compared to wavelet-based compressed sensing.
Tasks	Image Reconstruction
Published	2019-10-15
URL	https://arxiv.org/abs/1910.07048v1
PDF	https://arxiv.org/pdf/1910.07048v1.pdf
PWC	https://paperswithcode.com/paper/wasserstein-gans-for-mr-imaging-from-paired
Repo
Framework

Discovery of Bias and Strategic Behavior in Crowdsourced Performance Assessment


Title	Discovery of Bias and Strategic Behavior in Crowdsourced Performance Assessment
Authors	Yifei Huang, Matt Shum, Xi Wu, Jason Zezhong Xiao
Abstract	With the industry trend of shifting from a traditional hierarchical approach to flatter management structure, crowdsourced performance assessment gained mainstream popularity. One fundamental challenge of crowdsourced performance assessment is the risks that personal interest can introduce distortions of facts, especially when the system is used to determine merit pay or promotion. In this paper, we developed a method to identify bias and strategic behavior in crowdsourced performance assessment, using a rich dataset collected from a professional service firm in China. We find a pattern of “discriminatory generosity” on the part of peer evaluation, where raters downgrade their peer coworkers who have passed objective promotion requirements while overrating their peer coworkers who have not yet passed. This introduces two types of biases: the first aimed against more competent competitors, and the other favoring less eligible peers which can serve as a mask of the first bias. This paper also aims to bring angles of fairness-aware data mining to talent and management computing. Historical decision records, such as performance ratings, often contain subjective judgment which is prone to bias and strategic behavior. For practitioners of predictive talent analytics, it is important to investigate potential bias and strategic behavior underlying historical decision records.
Tasks
Published	2019-08-05
URL	https://arxiv.org/abs/1908.01718v2
PDF	https://arxiv.org/pdf/1908.01718v2.pdf
PWC	https://paperswithcode.com/paper/discovery-of-bias-and-strategic-behavior-in
Repo
Framework

DBRec: Dual-Bridging Recommendation via Discovering Latent Groups


Title	DBRec: Dual-Bridging Recommendation via Discovering Latent Groups
Authors	Jingwei Ma, Jiahui Wen, Mingyang Zhong, Liangchen Liu, Chaojie Li, Weitong Chen, Yin Yang, Honghui Tu, Xue Li
Abstract	In recommender systems, the user-item interaction data is usually sparse and not sufficient for learning comprehensive user/item representations for recommendation. To address this problem, we propose a novel dual-bridging recommendation model (DBRec). DBRec performs latent user/item group discovery simultaneously with collaborative filtering, and interacts group information with users/items for bridging similar users/items. Therefore, a user’s preference over an unobserved item, in DBRec, can be bridged by the users within the same group who have rated the item, or the user-rated items that share the same group with the unobserved item. In addition, we propose to jointly learn user-user group (item-item group) hierarchies, so that we can effectively discover latent groups and learn compact user/item representations. We jointly integrate collaborative filtering, latent group discovering and hierarchical modelling into a unified framework, so that all the model parameters can be learned toward the optimization of the objective function. We validate the effectiveness of the proposed model with two real datasets, and demonstrate its advantage over the state-of-the-art recommendation models with extensive experiments.
Tasks	Recommendation Systems
Published	2019-09-27
URL	https://arxiv.org/abs/1909.12301v2
PDF	https://arxiv.org/pdf/1909.12301v2.pdf
PWC	https://paperswithcode.com/paper/dbrec-dual-bridging-recommendation-via
Repo
Framework

Closed-Loop Adaptation for Weakly-Supervised Semantic Segmentation


Title	Closed-Loop Adaptation for Weakly-Supervised Semantic Segmentation
Authors	Zhengqiang Zhang, Shujian Yu, Shi Yin, Qinmu Peng, Xinge You
Abstract	Weakly-supervised semantic segmentation aims to assign each pixel a semantic category under weak supervisions, such as image-level tags. Most of existing weakly-supervised semantic segmentation methods do not use any feedback from segmentation output and can be considered as open-loop systems. They are prone to accumulated errors because of the static seeds and the sensitive structure information. In this paper, we propose a generic self-adaptation mechanism for existing weakly-supervised semantic segmentation methods by introducing two feedback chains, thus constituting a closed-loop system. Specifically, the first chain iteratively produces dynamic seeds by incorporating cross-image structure information, whereas the second chain further expands seed regions by a customized random walk process to reconcile inner-image structure information characterized by superpixels. Experiments on PASCAL VOC 2012 suggest that our network outperforms state-of-the-art methods with significantly less computational and memory burden.
Tasks	Semantic Segmentation, Weakly-Supervised Semantic Segmentation
Published	2019-05-29
URL	https://arxiv.org/abs/1905.12190v1
PDF	https://arxiv.org/pdf/1905.12190v1.pdf
PWC	https://paperswithcode.com/paper/closed-loop-adaptation-for-weakly-supervised
Repo
Framework

Bandlimiting Neural Networks Against Adversarial Attacks


Title	Bandlimiting Neural Networks Against Adversarial Attacks
Authors	Yuping Lin, Kasra Ahmadi K. A., Hui Jiang
Abstract	In this paper, we study the adversarial attack and defence problem in deep learning from the perspective of Fourier analysis. We first explicitly compute the Fourier transform of deep ReLU neural networks and show that there exist decaying but non-zero high frequency components in the Fourier spectrum of neural networks. We demonstrate that the vulnerability of neural networks towards adversarial samples can be attributed to these insignificant but non-zero high frequency components. Based on this analysis, we propose to use a simple post-averaging technique to smooth out these high frequency components to improve the robustness of neural networks against adversarial attacks. Experimental results on the ImageNet dataset have shown that our proposed method is universally effective to defend many existing adversarial attacking methods proposed in the literature, including FGSM, PGD, DeepFool and C&W attacks. Our post-averaging method is simple since it does not require any re-training, and meanwhile it can successfully defend over 95% of the adversarial samples generated by these methods without introducing any significant performance degradation (less than 1%) on the original clean images.
Tasks	Adversarial Attack
Published	2019-05-30
URL	https://arxiv.org/abs/1905.12797v1
PDF	https://arxiv.org/pdf/1905.12797v1.pdf
PWC	https://paperswithcode.com/paper/bandlimiting-neural-networks-against
Repo
Framework

Deep Learning Based Detection and Correction of Cardiac MR Motion Artefacts During Reconstruction for High-Quality Segmentation


Title	Deep Learning Based Detection and Correction of Cardiac MR Motion Artefacts During Reconstruction for High-Quality Segmentation
Authors	Ilkay Oksuz, James R. Clough, Bram Ruijsink, Esther Puyol Anton, Aurelien Bustin, Gastao Cruz, Claudia Prieto, Andrew P. King, Julia A. Schnabel
Abstract	Segmenting anatomical structures in medical images has been successfully addressed with deep learning methods for a range of applications. However, this success is heavily dependent on the quality of the image that is being segmented. A commonly neglected point in the medical image analysis community is the vast amount of clinical images that have severe image artefacts due to organ motion, movement of the patient and/or image acquisition related issues. In this paper, we discuss the implications of image motion artefacts on cardiac MR segmentation and compare a variety of approaches for jointly correcting for artefacts and segmenting the cardiac cavity. We propose to use a segmentation network coupled with this in an end-to-end framework. Our training optimises three different tasks: 1) image artefact detection, 2) artefact correction and 3) image segmentation. We train the reconstruction network to automatically correct for motion-related artefacts using synthetically corrupted cardiac MR k-space data and uncorrected reconstructed images. Using a test set of 500 2D+time cine MR acquisitions from the UK Biobank data set, we achieve demonstrably good image quality and high segmentation accuracy in the presence of synthetic motion artefacts. We quantitatively compare our method with a variety of techniques for jointly recovering image quality and performing image segmentation. We showcase better performance compared to state-of-the-art image correction techniques. Moreover, our method preserves the quality of uncorrupted images and therefore can be utilised as a global image reconstruction algorithm.
Tasks	Image Reconstruction, Semantic Segmentation
Published	2019-10-11
URL	https://arxiv.org/abs/1910.05370v3
PDF	https://arxiv.org/pdf/1910.05370v3.pdf
PWC	https://paperswithcode.com/paper/deep-learning-based-detection-and-correction
Repo
Framework

Exploring Confidence Measures for Word Spotting in Heterogeneous Datasets


Title	Exploring Confidence Measures for Word Spotting in Heterogeneous Datasets
Authors	Fabian Wolf, Philipp Oberdiek, Gernot A. Fink
Abstract	In recent years, convolutional neural networks (CNNs) took over the field of document analysis and they became the predominant model for word spotting. Especially attribute CNNs, which learn the mapping between a word image and an attribute representation, showed exceptional performances. The drawback of this approach is the overconfidence of neural networks when used out of their training distribution. In this paper, we explore different metrics for quantifying the confidence of a CNN in its predictions, specifically on the retrieval problem of word spotting. With these confidence measures, we limit the inability of a retrieval list to reject certain candidates. We investigate four different approaches that are either based on the network’s attribute estimations or make use of a surrogate model. Our approach also aims at answering the question for which part of a dataset the retrieval system gives reliable results. We further show that there exists a direct relation between the proposed confidence measures and the quality of an estimated attribute representation.
Tasks
Published	2019-03-26
URL	http://arxiv.org/abs/1903.10930v1
PDF	http://arxiv.org/pdf/1903.10930v1.pdf
PWC	https://paperswithcode.com/paper/exploring-confidence-measures-for-word
Repo
Framework

Geometric Disentanglement for Generative Latent Shape Models


Title	Geometric Disentanglement for Generative Latent Shape Models
Authors	Tristan Aumentado-Armstrong, Stavros Tsogkas, Allan Jepson, Sven Dickinson
Abstract	Representing 3D shape is a fundamental problem in artificial intelligence, which has numerous applications within computer vision and graphics. One avenue that has recently begun to be explored is the use of latent representations of generative models. However, it remains an open problem to learn a generative model of shape that is interpretable and easily manipulated, particularly in the absence of supervised labels. In this paper, we propose an unsupervised approach to partitioning the latent space of a variational autoencoder for 3D point clouds in a natural way, using only geometric information. Our method makes use of tools from spectral differential geometry to separate intrinsic and extrinsic shape information, and then considers several hierarchical disentanglement penalties for dividing the latent space in this manner, including a novel one that penalizes the Jacobian of the latent representation of the decoded output with respect to the latent encoding. We show that the resulting representation exhibits intuitive and interpretable behavior, enabling tasks such as pose transfer and pose-aware shape retrieval that cannot easily be performed by models with an entangled representation.
Tasks	Pose Transfer
Published	2019-08-18
URL	https://arxiv.org/abs/1908.06386v1
PDF	https://arxiv.org/pdf/1908.06386v1.pdf
PWC	https://paperswithcode.com/paper/geometric-disentanglement-for-generative
Repo
Framework

Personalized HeartSteps: A Reinforcement Learning Algorithm for Optimizing Physical Activity


Title	Personalized HeartSteps: A Reinforcement Learning Algorithm for Optimizing Physical Activity
Authors	Peng Liao, Kristjan Greenewald, Predrag Klasnja, Susan Murphy
Abstract	With the recent evolution of mobile health technologies, health scientists are increasingly interested in developing just-in-time adaptive interventions (JITAIs), typically delivered via notification on mobile device and designed to help the user prevent negative health outcomes and promote the adoption and maintenance of healthy behaviors. A JITAI involves a sequence of decision rules (i.e., treatment policy) that takes the user’s current context as input and specifies whether and what type of an intervention should be provided at the moment. In this paper, we develop a Reinforcement Learning (RL) algorithm that continuously learns and improves the treatment policy embedded in the JITAI as the data is being collected from the user. This work is motivated by our collaboration on designing the RL algorithm in HeartSteps V2 based on data from HeartSteps V1. HeartSteps is a physical activity mobile health application. The RL algorithm developed in this paper is being used in HeartSteps V2 to decide, five times per day, whether to deliver a context-tailored activity suggestion.
Tasks
Published	2019-09-08
URL	https://arxiv.org/abs/1909.03539v1
PDF	https://arxiv.org/pdf/1909.03539v1.pdf
PWC	https://paperswithcode.com/paper/personalized-heartsteps-a-reinforcement
Repo
Framework

Evolving neural networks to follow trajectories of arbitrary complexity


Title	Evolving neural networks to follow trajectories of arbitrary complexity
Authors	Benjamin Inden, Jürgen Jost
Abstract	Many experiments have been performed that use evolutionary algorithms for learning the topology and connection weights of a neural network that controls a robot or virtual agent. These experiments are not only performed to better understand basic biological principles, but also with the hope that with further progress of the methods, they will become competitive for automatically creating robot behaviors of interest. However, current methods are limited with respect to the (Kolmogorov) complexity of evolved behavior. Using the evolution of robot trajectories as an example, we show that by adding four features, namely (1) freezing of previously evolved structure, (2) temporal scaffolding, (3) a homogeneous transfer function for output nodes, and (4) mutations that create new pathways to outputs, to standard methods for the evolution of neural networks, we can achieve an approximately linear growth of the complexity of behavior over thousands of generations. Overall, evolved complexity is up to two orders of magnitude over that achieved by standard methods in the experiments reported here, with the major limiting factor for further growth being the available run time. Thus, the set of methods proposed here promises to be a useful addition to various current neuroevolution methods.
Tasks
Published	2019-05-21
URL	https://arxiv.org/abs/1905.08885v1
PDF	https://arxiv.org/pdf/1905.08885v1.pdf
PWC	https://paperswithcode.com/paper/evolving-neural-networks-to-follow
Repo
Framework

DLocRL: A Deep Learning Pipeline for Fine-Grained Location Recognition and Linking in Tweets


Title	DLocRL: A Deep Learning Pipeline for Fine-Grained Location Recognition and Linking in Tweets
Authors	Canwen Xu, Jing Li, Xiangyang Luo, Jiaxin Pei, Chenliang Li, Donghong Ji
Abstract	In recent years, with the prevalence of social media and smart devices, people causally reveal their locations such as shops, hotels, and restaurants in their tweets. Recognizing and linking such fine-grained location mentions to well-defined location profiles are beneficial for retrieval and recommendation systems. In this paper, we propose DLocRL, a new deep learning pipeline for fine-grained location recognition and linking in tweets, and verify its effectiveness on a real-world Twitter dataset.
Tasks	Recommendation Systems, Representation Learning, Semantic Composition
Published	2019-01-21
URL	http://arxiv.org/abs/1901.07005v3
PDF	http://arxiv.org/pdf/1901.07005v3.pdf
PWC	https://paperswithcode.com/paper/dlocrl-a-deep-learning-pipeline-for-fine
Repo
Framework