July 29, 2019

3106 words 15 mins read

Paper Group ANR 114

Extracting 3D Vascular Structures from Microscopy Images using Convolutional Recurrent Networks. Large Scale Evolution of Convolutional Neural Networks Using Volunteer Computing. Robust method for finding sparse solutions to linear inverse problems using an L2 regularization. A Deep Cascade Network for Unaligned Face Attribute Classification. From …

Extracting 3D Vascular Structures from Microscopy Images using Convolutional Recurrent Networks


Title	Extracting 3D Vascular Structures from Microscopy Images using Convolutional Recurrent Networks
Authors	Russell Bates, Benjamin Irving, Bostjan Markelc, Jakob Kaeppler, Ruth Muschel, Vicente Grau, Julia A. Schnabel
Abstract	Vasculature is known to be of key biological significance, especially in the study of cancer. As such, considerable effort has been focused on the automated measurement and analysis of vasculature in medical and pre-clinical images. In tumors in particular, the vascular networks may be extremely irregular and the appearance of the individual vessels may not conform to classical descriptions of vascular appearance. Typically, vessels are extracted by either a segmentation and thinning pipeline, or by direct tracking. Neither of these methods are well suited to microscopy images of tumor vasculature. In order to address this we propose a method to directly extract a medial representation of the vessels using Convolutional Neural Networks. We then show that these two-dimensional centerlines can be meaningfully extended into 3D in anisotropic and complex microscopy images using the recently popularized Convolutional Long Short-Term Memory units (ConvLSTM). We demonstrate the effectiveness of this hybrid convolutional-recurrent architecture over both 2D and 3D convolutional comparators.
Tasks
Published	2017-05-26
URL	http://arxiv.org/abs/1705.09597v1
PDF	http://arxiv.org/pdf/1705.09597v1.pdf
PWC	https://paperswithcode.com/paper/extracting-3d-vascular-structures-from
Repo
Framework

Large Scale Evolution of Convolutional Neural Networks Using Volunteer Computing


Title	Large Scale Evolution of Convolutional Neural Networks Using Volunteer Computing
Authors	Travis Desell
Abstract	This work presents a new algorithm called evolutionary exploration of augmenting convolutional topologies (EXACT), which is capable of evolving the structure of convolutional neural networks (CNNs). EXACT is in part modeled after the neuroevolution of augmenting topologies (NEAT) algorithm, with notable exceptions to allow it to scale to large scale distributed computing environments and evolve networks with convolutional filters. In addition to multithreaded and MPI versions, EXACT has been implemented as part of a BOINC volunteer computing project, allowing large scale evolution. During a period of two months, over 4,500 volunteered computers on the Citizen Science Grid trained over 120,000 CNNs and evolved networks reaching 98.32% test data accuracy on the MNIST handwritten digits dataset. These results are even stronger as the backpropagation strategy used to train the CNNs was fairly rudimentary (ReLU units, L2 regularization and Nesterov momentum) and these were initial test runs done without refinement of the backpropagation hyperparameters. Further, the EXACT evolutionary strategy is independent of the method used to train the CNNs, so they could be further improved by advanced techniques like elastic distortions, pretraining and dropout. The evolved networks are also quite interesting, showing “organic” structures and significant differences from standard human designed architectures.
Tasks	L2 Regularization
Published	2017-03-15
URL	http://arxiv.org/abs/1703.05422v1
PDF	http://arxiv.org/pdf/1703.05422v1.pdf
PWC	https://paperswithcode.com/paper/large-scale-evolution-of-convolutional-neural
Repo
Framework

Robust method for finding sparse solutions to linear inverse problems using an L2 regularization


Title	Robust method for finding sparse solutions to linear inverse problems using an L2 regularization
Authors	Gonzalo H Otazu
Abstract	We analyzed the performance of a biologically inspired algorithm called the Corrected Projections Algorithm (CPA) when a sparseness constraint is required to unambiguously reconstruct an observed signal using atoms from an overcomplete dictionary. By changing the geometry of the estimation problem, CPA gives an analytical expression for a binary variable that indicates the presence or absence of a dictionary atom using an L2 regularizer. The regularized solution can be implemented using an efficient real-time Kalman-filter type of algorithm. The smoother L2 regularization of CPA makes it very robust to noise, and CPA outperforms other methods in identifying known atoms in the presence of strong novel atoms in the signal.
Tasks	L2 Regularization
Published	2017-01-03
URL	http://arxiv.org/abs/1701.00573v3
PDF	http://arxiv.org/pdf/1701.00573v3.pdf
PWC	https://paperswithcode.com/paper/robust-method-for-finding-sparse-solutions-to
Repo
Framework

A Deep Cascade Network for Unaligned Face Attribute Classification


Title	A Deep Cascade Network for Unaligned Face Attribute Classification
Authors	Hui Ding, Hao Zhou, Shaohua Kevin Zhou, Rama Chellappa
Abstract	Humans focus attention on different face regions when recognizing face attributes. Most existing face attribute classification methods use the whole image as input. Moreover, some of these methods rely on fiducial landmarks to provide defined face parts. In this paper, we propose a cascade network that simultaneously learns to localize face regions specific to attributes and performs attribute classification without alignment. First, a weakly-supervised face region localization network is designed to automatically detect regions (or parts) specific to attributes. Then multiple part-based networks and a whole-image-based network are separately constructed and combined together by the region switch layer and attribute relation layer for final attribute classification. A multi-net learning method and hint-based model compression is further proposed to get an effective localization model and a compact classification model, respectively. Our approach achieves significantly better performance than state-of-the-art methods on unaligned CelebA dataset, reducing the classification error by 30.9%.
Tasks	Model Compression
Published	2017-09-12
URL	http://arxiv.org/abs/1709.03851v2
PDF	http://arxiv.org/pdf/1709.03851v2.pdf
PWC	https://paperswithcode.com/paper/a-deep-cascade-network-for-unaligned-face
Repo
Framework

From Bayesian Sparsity to Gated Recurrent Nets


Title	From Bayesian Sparsity to Gated Recurrent Nets
Authors	Hao He, Bo Xin, David Wipf
Abstract	The iterations of many first-order algorithms, when applied to minimizing common regularized regression functions, often resemble neural network layers with pre-specified weights. This observation has prompted the development of learning-based approaches that purport to replace these iterations with enhanced surrogates forged as DNN models from available training data. For example, important NP-hard sparse estimation problems have recently benefitted from this genre of upgrade, with simple feedforward or recurrent networks ousting proximal gradient-based iterations. Analogously, this paper demonstrates that more powerful Bayesian algorithms for promoting sparsity, which rely on complex multi-loop majorization-minimization techniques, mirror the structure of more sophisticated long short-term memory (LSTM) networks, or alternative gated feedback networks previously designed for sequence prediction. As part of this development, we examine the parallels between latent variable trajectories operating across multiple time-scales during optimization, and the activations within deep network structures designed to adaptively model such characteristic sequences. The resulting insights lead to a novel sparse estimation system that, when granted training data, can estimate optimal solutions efficiently in regimes where other algorithms fail, including practical direction-of-arrival (DOA) and 3D geometry recovery problems. The underlying principles we expose are also suggestive of a learning process for a richer class of multi-loop algorithms in other domains.
Tasks
Published	2017-06-09
URL	http://arxiv.org/abs/1706.02815v2
PDF	http://arxiv.org/pdf/1706.02815v2.pdf
PWC	https://paperswithcode.com/paper/from-bayesian-sparsity-to-gated-recurrent
Repo
Framework

Recurrent Collective Classification


Title	Recurrent Collective Classification
Authors	Shuangfei Fan, Bert Huang
Abstract	We propose a new method for training iterative collective classifiers for labeling nodes in network data. The iterative classification algorithm (ICA) is a canonical method for incorporating relational information into classification. Yet, existing methods for training ICA models rely on the assumption that relational features reflect the true labels of the nodes. This unrealistic assumption introduces a bias that is inconsistent with the actual prediction algorithm. In this paper, we introduce recurrent collective classification (RCC), a variant of ICA analogous to recurrent neural network prediction. RCC accommodates any differentiable local classifier and relational feature functions. We provide gradient-based strategies for optimizing over model parameters to more directly minimize the loss function. In our experiments, this direct loss minimization translates to improved accuracy and robustness on real network data. We demonstrate the robustness of RCC in settings where local classification is very noisy, settings that are particularly challenging for ICA.
Tasks
Published	2017-03-19
URL	http://arxiv.org/abs/1703.06514v1
PDF	http://arxiv.org/pdf/1703.06514v1.pdf
PWC	https://paperswithcode.com/paper/recurrent-collective-classification
Repo
Framework

Domain Adaptation Meets Disentangled Representation Learning and Style Transfer


Title	Domain Adaptation Meets Disentangled Representation Learning and Style Transfer
Authors	Hoang Tran Vu, Ching-Chun Huang
Abstract	Many methods have been proposed to solve the domain adaptation problem recently. However, the success of them implicitly funds on the assumption that the information of domains are fully transferrable. If the assumption is not satisfied, the effect of negative transfer may degrade domain adaptation. In this paper, a better learning network has been proposed by considering three tasks - domain adaptation, disentangled representation, and style transfer simultaneously. Firstly, the learned features are disentangled into common parts and specific parts. The common parts represent the transferrable features, which are suitable for domain adaptation with less negative transfer. Conversely, the specific parts characterize the unique style of each individual domain. Based on this, the new concept of feature exchange across domains, which can not only enhance the transferability of common features but also be useful for image style transfer, is introduced. These designs allow us to introduce five types of training objectives to realize the three challenging tasks at the same time. The experimental results show that our architecture can be adaptive well to full transfer learning and partial transfer learning upon a well-learned disentangled representation. Besides, the trained network also demonstrates high potential to generate style-transferred images.
Tasks	Domain Adaptation, Representation Learning, Style Transfer, Transfer Learning
Published	2017-12-25
URL	http://arxiv.org/abs/1712.09025v4
PDF	http://arxiv.org/pdf/1712.09025v4.pdf
PWC	https://paperswithcode.com/paper/domain-adaptation-meets-disentangled
Repo
Framework

Guiding the search in continuous state-action spaces by learning an action sampling distribution from off-target samples


Title	Guiding the search in continuous state-action spaces by learning an action sampling distribution from off-target samples
Authors	Beomjoon Kim, Leslie Pack Kaelbling, Tomas Lozano-Perez
Abstract	In robotics, it is essential to be able to plan efficiently in high-dimensional continuous state-action spaces for long horizons. For such complex planning problems, unguided uniform sampling of actions until a path to a goal is found is hopelessly inefficient, and gradient-based approaches often fall short when the optimization manifold of a given problem is not smooth. In this paper we present an approach that guides the search of a state-space planner, such as A*, by learning an action-sampling distribution that can generalize across different instances of a planning problem. The motivation is that, unlike typical learning approaches for planning for continuous action space that estimate a policy, an estimated action sampler is more robust to error since it has a planner to fall back on. We use a Generative Adversarial Network (GAN), and address an important issue: search experience consists of a relatively large number of actions that are not on a solution path and a relatively small number of actions that actually are on a solution path. We introduce a new technique, based on an importance-ratio estimation method, for using samples from a non-target distribution to make GAN learning more data-efficient. We provide theoretical guarantees and empirical evaluation in three challenging continuous robot planning problems to illustrate the effectiveness of our algorithm.
Tasks
Published	2017-11-04
URL	http://arxiv.org/abs/1711.01391v1
PDF	http://arxiv.org/pdf/1711.01391v1.pdf
PWC	https://paperswithcode.com/paper/guiding-the-search-in-continuous-state-action
Repo
Framework

Self-supervised Learning of Pose Embeddings from Spatiotemporal Relations in Videos


Title	Self-supervised Learning of Pose Embeddings from Spatiotemporal Relations in Videos
Authors	Ömer Sümer, Tobias Dencker, Björn Ommer
Abstract	Human pose analysis is presently dominated by deep convolutional networks trained with extensive manual annotations of joint locations and beyond. To avoid the need for expensive labeling, we exploit spatiotemporal relations in training videos for self-supervised learning of pose embeddings. The key idea is to combine temporal ordering and spatial placement estimation as auxiliary tasks for learning pose similarities in a Siamese convolutional network. Since the self-supervised sampling of both tasks from natural videos can result in ambiguous and incorrect training labels, our method employs a curriculum learning idea that starts training with the most reliable data samples and gradually increases the difficulty. To further refine the training process we mine repetitive poses in individual videos which provide reliable labels while removing inconsistencies. Our pose embeddings capture visual characteristics of human pose that can boost existing supervised representations in human pose estimation and retrieval. We report quantitative and qualitative results on these tasks in Olympic Sports, Leeds Pose Sports and MPII Human Pose datasets.
Tasks	Pose Estimation
Published	2017-08-07
URL	http://arxiv.org/abs/1708.02179v1
PDF	http://arxiv.org/pdf/1708.02179v1.pdf
PWC	https://paperswithcode.com/paper/self-supervised-learning-of-pose-embeddings
Repo
Framework

From which world is your graph?


Title	From which world is your graph?
Authors	Cheng Li, Felix Wong, Zhenming Liu, Varun Kanade
Abstract	Discovering statistical structure from links is a fundamental problem in the analysis of social networks. Choosing a misspecified model, or equivalently, an incorrect inference algorithm will result in an invalid analysis or even falsely uncover patterns that are in fact artifacts of the model. This work focuses on unifying two of the most widely used link-formation models: the stochastic blockmodel (SBM) and the small world (or latent space) model (SWM). Integrating techniques from kernel learning, spectral graph theory, and nonlinear dimensionality reduction, we develop the first statistically sound polynomial-time algorithm to discover latent patterns in sparse graphs for both models. When the network comes from an SBM, the algorithm outputs a block structure. When it is from an SWM, the algorithm outputs estimates of each node’s latent position.
Tasks	Dimensionality Reduction
Published	2017-11-03
URL	http://arxiv.org/abs/1711.00982v1
PDF	http://arxiv.org/pdf/1711.00982v1.pdf
PWC	https://paperswithcode.com/paper/from-which-world-is-your-graph
Repo
Framework

Searching for Biophysically Realistic Parameters for Dynamic Neuron Models by Genetic Algorithms from Calcium Imaging Recording


Title	Searching for Biophysically Realistic Parameters for Dynamic Neuron Models by Genetic Algorithms from Calcium Imaging Recording
Authors	Magdalena Fuchs, Manuel Zimmer, Radu Grosu, Ramin M. Hasani
Abstract	Individual Neurons in the nervous systems exploit various dynamics. To capture these dynamics for single neurons, we tune the parameters of an electrophysiological model of nerve cells, to fit experimental data obtained by calcium imaging. A search for the biophysical parameters of this model is performed by means of a genetic algorithm, where the model neuron is exposed to a predefined input current representing overall inputs from other parts of the nervous system. The algorithm is then constrained for keeping the ion-channel currents within reasonable ranges, while producing the best fit to a calcium imaging time series of the AVA interneuron, from the brain of the soil-worm, C. elegans. Our settings enable us to project a set of biophysical parameters to the the neuron kinetics observed in neuronal imaging.
Tasks	Time Series
Published	2017-11-04
URL	http://arxiv.org/abs/1711.01436v1
PDF	http://arxiv.org/pdf/1711.01436v1.pdf
PWC	https://paperswithcode.com/paper/searching-for-biophysically-realistic
Repo
Framework

The Feeling of Success: Does Touch Sensing Help Predict Grasp Outcomes?


Title	The Feeling of Success: Does Touch Sensing Help Predict Grasp Outcomes?
Authors	Roberto Calandra, Andrew Owens, Manu Upadhyaya, Wenzhen Yuan, Justin Lin, Edward H. Adelson, Sergey Levine
Abstract	A successful grasp requires careful balancing of the contact forces. Deducing whether a particular grasp will be successful from indirect measurements, such as vision, is therefore quite challenging, and direct sensing of contacts through touch sensing provides an appealing avenue toward more successful and consistent robotic grasping. However, in order to fully evaluate the value of touch sensing for grasp outcome prediction, we must understand how touch sensing can influence outcome prediction accuracy when combined with other modalities. Doing so using conventional model-based techniques is exceptionally difficult. In this work, we investigate the question of whether touch sensing aids in predicting grasp outcomes within a multimodal sensing framework that combines vision and touch. To that end, we collected more than 9,000 grasping trials using a two-finger gripper equipped with GelSight high-resolution tactile sensors on each finger, and evaluated visuo-tactile deep neural network models to directly predict grasp outcomes from either modality individually, and from both modalities together. Our experimental results indicate that incorporating tactile readings substantially improve grasping performance.
Tasks	Robotic Grasping
Published	2017-10-16
URL	http://arxiv.org/abs/1710.05512v1
PDF	http://arxiv.org/pdf/1710.05512v1.pdf
PWC	https://paperswithcode.com/paper/the-feeling-of-success-does-touch-sensing
Repo
Framework

Detection, Recognition and Tracking of Moving Objects from Real-time Video via Visual Vocabulary Model and Species Inspired PSO


Title	Detection, Recognition and Tracking of Moving Objects from Real-time Video via Visual Vocabulary Model and Species Inspired PSO
Authors	Kumar S. Ray, Anit Chakraborty, Sayandip Dutta
Abstract	In this paper, we address the basic problem of recognizing moving objects in video images using Visual Vocabulary model and Bag of Words and track our object of interest in the subsequent video frames using species inspired PSO. Initially, the shadow free images are obtained by background modelling followed by foreground modeling to extract the blobs of our object of interest. Subsequently, we train a cubic SVM with human body datasets in accordance with our domain of interest for recognition and tracking. During training, using the principle of Bag of Words we extract necessary features of certain domains and objects for classification. Subsequently, matching these feature sets with those of the extracted object blobs that are obtained by subtracting the shadow free background from the foreground, we detect successfully our object of interest from the test domain. The performance of the classification by cubic SVM is satisfactorily represented by confusion matrix and ROC curve reflecting the accuracy of each module. After classification, our object of interest is tracked in the test domain using species inspired PSO. By combining the adaptive learning tools with the efficient classification of description, we achieve optimum accuracy in recognition of the moving objects. We evaluate our algorithm benchmark datasets: iLIDS, VIVID, Walking2, Woman. Comparative analysis of our algorithm against the existing state-of-the-art trackers shows very satisfactory and competitive results.
Tasks
Published	2017-06-02
URL	http://arxiv.org/abs/1707.05224v1
PDF	http://arxiv.org/pdf/1707.05224v1.pdf
PWC	https://paperswithcode.com/paper/detection-recognition-and-tracking-of-moving
Repo
Framework

Transformation-Based Models of Video Sequences


Title	Transformation-Based Models of Video Sequences
Authors	Joost van Amersfoort, Anitha Kannan, Marc’Aurelio Ranzato, Arthur Szlam, Du Tran, Soumith Chintala
Abstract	In this work we propose a simple unsupervised approach for next frame prediction in video. Instead of directly predicting the pixels in a frame given past frames, we predict the transformations needed for generating the next frame in a sequence, given the transformations of the past frames. This leads to sharper results, while using a smaller prediction model. In order to enable a fair comparison between different video frame prediction models, we also propose a new evaluation protocol. We use generated frames as input to a classifier trained with ground truth sequences. This criterion guarantees that models scoring high are those producing sequences which preserve discrim- inative features, as opposed to merely penalizing any deviation, plausible or not, from the ground truth. Our proposed approach compares favourably against more sophisticated ones on the UCF-101 data set, while also being more efficient in terms of the number of parameters and computational cost.
Tasks
Published	2017-01-29
URL	http://arxiv.org/abs/1701.08435v2
PDF	http://arxiv.org/pdf/1701.08435v2.pdf
PWC	https://paperswithcode.com/paper/transformation-based-models-of-video
Repo
Framework

Green-Blue Stripe Pattern for Range Sensing from a Single Image


Title	Green-Blue Stripe Pattern for Range Sensing from a Single Image
Authors	Changsoo Je, Kyuhyoung Choi, Sang Wook Lee
Abstract	In this paper, we present a novel method for rapid high-resolution range sensing using green-blue stripe pattern. We use green and blue for designing high-frequency stripe projection pattern. For accurate and reliable range recovery, we identify the stripe patterns by our color-stripe segmentation and unwrapping algorithms. The experimental result for a naked human face shows the effectiveness of our method.
Tasks
Published	2017-01-09
URL	http://arxiv.org/abs/1701.02123v1
PDF	http://arxiv.org/pdf/1701.02123v1.pdf
PWC	https://paperswithcode.com/paper/green-blue-stripe-pattern-for-range-sensing
Repo
Framework