July 27, 2019

3296 words 16 mins read

Paper Group ANR 575

Quantum Computation via Sparse Distributed Representation. Enhancing approximation abilities of neural networks by training derivatives. Object Discovery via Cohesion Measurement. ScaleNet: Guiding Object Proposal Generation in Supermarkets and Beyond. Toward Streaming Synapse Detection with Compositional ConvNets. Deep Networks for Compressed Imag …

Quantum Computation via Sparse Distributed Representation


Title	Quantum Computation via Sparse Distributed Representation
Authors	Gerard J. Rinkus
Abstract	Quantum superposition says that any physical system simultaneously exists in all of its possible states, the number of which is exponential in the number of entities composing the system. The strength of presence of each possible state in the superposition, i.e., its probability of being observed, is represented by its probability amplitude coefficient. The assumption that these coefficients must be represented physically disjointly from each other, i.e., localistically, is nearly universal in the quantum theory/computing literature. Alternatively, these coefficients can be represented using sparse distributed representations (SDR), wherein each coefficient is represented by small subset of an overall population of units, and the subsets can overlap. Specifically, I consider an SDR model in which the overall population consists of Q WTA clusters, each with K binary units. Each coefficient is represented by a set of Q units, one per cluster. Thus, K^Q coefficients can be represented with KQ units. Thus, the particular world state, X, whose coefficient’s representation, R(X), is the set of Q units active at time t has the max probability and the probability of every other state, Y_i, at time t, is measured by R(Y_i)‘s intersection with R(X). Thus, R(X) simultaneously represents both the particular state, X, and the probability distribution over all states. Thus, set intersection may be used to classically implement quantum superposition. If algorithms exist for which the time it takes to store (learn) new representations and to find the closest-matching stored representation (probabilistic inference) remains constant as additional representations are stored, this meets the criterion of quantum computing. Such an algorithm has already been described: it achieves this “quantum speed-up” without esoteric hardware, and in fact, on a single-processor, classical (Von Neumann) computer.
Tasks
Published	2017-07-15
URL	http://arxiv.org/abs/1707.05660v1
PDF	http://arxiv.org/pdf/1707.05660v1.pdf
PWC	https://paperswithcode.com/paper/quantum-computation-via-sparse-distributed
Repo
Framework

Enhancing approximation abilities of neural networks by training derivatives


Title	Enhancing approximation abilities of neural networks by training derivatives
Authors	V. I. Avrutskiy
Abstract	A method to increase the precision of feedforward networks is proposed. It requires a prior knowledge of a target function derivatives of several orders and uses this information in gradient based training. Forward pass calculates not only the values of the output layer of a network but also their derivatives. The deviations of those derivatives from the target ones are used in an extended cost function and then backward pass calculates the gradient of the extended cost with respect to weights, which can then be used by any weights update algorithm. Despite a substantial increase in arithmetic operations per pattern (if compared to the conventional training), the extended cost allows to obtain 140–1000 times more accurate approximation for simple cases if the total number of operations is equal. This precision also happens to be out of reach for the regular cost function. The method fits well into the procedure of solving differential equations with neural networks. Unlike training a network to match some target mapping, which requires an explicit use of the target derivatives in the extended cost function, the cost function for solving a differential equation is based on the deviation of the equation’s residual from zero and thus can be extended by differentiating the equation itself, which does not require any prior knowledge. Solving an equation with such a cost resulted in 13 times more accurate result and could be done with 3 times larger grid step. GPU-efficient algorithm for calculating the gradient of the extended cost function is proposed.
Tasks
Published	2017-12-12
URL	https://arxiv.org/abs/1712.04473v3
PDF	https://arxiv.org/pdf/1712.04473v3.pdf
PWC	https://paperswithcode.com/paper/enhancing-approximation-abilities-of-neural
Repo
Framework

Object Discovery via Cohesion Measurement


Title	Object Discovery via Cohesion Measurement
Authors	Guanjun Guo, Hanzi Wang, Wan-Lei Zhao, Yan Yan, Xuelong Li
Abstract	Color and intensity are two important components in an image. Usually, groups of image pixels, which are similar in color or intensity, are an informative representation for an object. They are therefore particularly suitable for computer vision tasks, such as saliency detection and object proposal generation. However, image pixels, which share a similar real-world color, may be quite different since colors are often distorted by intensity. In this paper, we reinvestigate the affinity matrices originally used in image segmentation methods based on spectral clustering. A new affinity matrix, which is robust to color distortions, is formulated for object discovery. Moreover, a Cohesion Measurement (CM) for object regions is also derived based on the formulated affinity matrix. Based on the new Cohesion Measurement, a novel object discovery method is proposed to discover objects latent in an image by utilizing the eigenvectors of the affinity matrix. Then we apply the proposed method to both saliency detection and object proposal generation. Experimental results on several evaluation benchmarks demonstrate that the proposed CM based method has achieved promising performance for these two tasks.
Tasks	Object Proposal Generation, Saliency Detection, Semantic Segmentation
Published	2017-04-28
URL	http://arxiv.org/abs/1704.08944v1
PDF	http://arxiv.org/pdf/1704.08944v1.pdf
PWC	https://paperswithcode.com/paper/object-discovery-via-cohesion-measurement
Repo
Framework

ScaleNet: Guiding Object Proposal Generation in Supermarkets and Beyond


Title	ScaleNet: Guiding Object Proposal Generation in Supermarkets and Beyond
Authors	Siyuan Qiao, Wei Shen, Weichao Qiu, Chenxi Liu, Alan Yuille
Abstract	Motivated by product detection in supermarkets, this paper studies the problem of object proposal generation in supermarket images and other natural images. We argue that estimation of object scales in images is helpful for generating object proposals, especially for supermarket images where object scales are usually within a small range. Therefore, we propose to estimate object scales of images before generating object proposals. The proposed method for predicting object scales is called ScaleNet. To validate the effectiveness of ScaleNet, we build three supermarket datasets, two of which are real-world datasets used for testing and the other one is a synthetic dataset used for training. In short, we extend the previous state-of-the-art object proposal methods by adding a scale prediction phase. The resulted method outperforms the previous state-of-the-art on the supermarket datasets by a large margin. We also show that the approach works for object proposal on other natural images and it outperforms the previous state-of-the-art object proposal methods on the MS COCO dataset. The supermarket datasets, the virtual supermarkets, and the tools for creating more synthetic datasets will be made public.
Tasks	Object Proposal Generation
Published	2017-04-22
URL	http://arxiv.org/abs/1704.06752v1
PDF	http://arxiv.org/pdf/1704.06752v1.pdf
PWC	https://paperswithcode.com/paper/scalenet-guiding-object-proposal-generation
Repo
Framework

Toward Streaming Synapse Detection with Compositional ConvNets


Title	Toward Streaming Synapse Detection with Compositional ConvNets
Authors	Shibani Santurkar, David Budden, Alexander Matveev, Heather Berlin, Hayk Saribekyan, Yaron Meirovitch, Nir Shavit
Abstract	Connectomics is an emerging field in neuroscience that aims to reconstruct the 3-dimensional morphology of neurons from electron microscopy (EM) images. Recent studies have successfully demonstrated the use of convolutional neural networks (ConvNets) for segmenting cell membranes to individuate neurons. However, there has been comparatively little success in high-throughput identification of the intercellular synaptic connections required for deriving connectivity graphs. In this study, we take a compositional approach to segmenting synapses, modeling them explicitly as an intercellular cleft co-located with an asymmetric vesicle density along a cell membrane. Instead of requiring a deep network to learn all natural combinations of this compositionality, we train lighter networks to model the simpler marginal distributions of membranes, clefts and vesicles from just 100 electron microscopy samples. These feature maps are then combined with simple rules-based heuristics derived from prior biological knowledge. Our approach to synapse detection is both more accurate than previous state-of-the-art (7% higher recall and 5% higher F1-score) and yields a 20-fold speed-up compared to the previous fastest implementations. We demonstrate by reconstructing the first complete, directed connectome from the largest available anisotropic microscopy dataset (245 GB) of mouse somatosensory cortex (S1) in just 9.7 hours on a single shared-memory CPU system. We believe that this work marks an important step toward the goal of a microscope-pace streaming connectomics pipeline.
Tasks
Published	2017-02-23
URL	http://arxiv.org/abs/1702.07386v1
PDF	http://arxiv.org/pdf/1702.07386v1.pdf
PWC	https://paperswithcode.com/paper/toward-streaming-synapse-detection-with
Repo
Framework

Deep Networks for Compressed Image Sensing


Title	Deep Networks for Compressed Image Sensing
Authors	Wuzhen Shi, Feng Jiang, Shengping Zhang, Debin Zhao
Abstract	The compressed sensing (CS) theory has been successfully applied to image compression in the past few years as most image signals are sparse in a certain domain. Several CS reconstruction models have been recently proposed and obtained superior performance. However, there still exist two important challenges within the CS theory. The first one is how to design a sampling mechanism to achieve an optimal sampling efficiency, and the second one is how to perform the reconstruction to get the highest quality to achieve an optimal signal recovery. In this paper, we try to deal with these two problems with a deep network. First of all, we train a sampling matrix via the network training instead of using a traditional manually designed one, which is much appropriate for our deep network based reconstruct process. Then, we propose a deep network to recover the image, which imitates traditional compressed sensing reconstruction processes. Experimental results demonstrate that our deep networks based CS reconstruction method offers a very significant quality improvement compared against state of the art ones.
Tasks	Image Compression
Published	2017-07-22
URL	http://arxiv.org/abs/1707.07119v1
PDF	http://arxiv.org/pdf/1707.07119v1.pdf
PWC	https://paperswithcode.com/paper/deep-networks-for-compressed-image-sensing
Repo
Framework

Semantic 3D Occupancy Mapping through Efficient High Order CRFs


Title	Semantic 3D Occupancy Mapping through Efficient High Order CRFs
Authors	Shichao Yang, Yulan Huang, Sebastian Scherer
Abstract	Semantic 3D mapping can be used for many applications such as robot navigation and virtual interaction. In recent years, there has been great progress in semantic segmentation and geometric 3D mapping. However, it is still challenging to combine these two tasks for accurate and large-scale semantic mapping from images. In the paper, we propose an incremental and (near) real-time semantic mapping system. A 3D scrolling occupancy grid map is built to represent the world, which is memory and computationally efficient and bounded for large scale environments. We utilize the CNN segmentation as prior prediction and further optimize 3D grid labels through a novel CRF model. Superpixels are utilized to enforce smoothness and form robust P N high order potential. An efficient mean field inference is developed for the graph optimization. We evaluate our system on the KITTI dataset and improve the segmentation accuracy by 10% over existing systems.
Tasks	Robot Navigation, Semantic Segmentation
Published	2017-07-24
URL	http://arxiv.org/abs/1707.07388v1
PDF	http://arxiv.org/pdf/1707.07388v1.pdf
PWC	https://paperswithcode.com/paper/semantic-3d-occupancy-mapping-through
Repo
Framework

Co-Clustering for Multitask Learning


Title	Co-Clustering for Multitask Learning
Authors	Keerthiram Murugesan, Jaime Carbonell, Yiming Yang
Abstract	This paper presents a new multitask learning framework that learns a shared representation among the tasks, incorporating both task and feature clusters. The jointly-induced clusters yield a shared latent subspace where task relationships are learned more effectively and more generally than in state-of-the-art multitask learning methods. The proposed general framework enables the derivation of more specific or restricted state-of-the-art multitask methods. The paper also proposes a highly-scalable multitask learning algorithm, based on the new framework, using conjugate gradient descent and generalized \textit{Sylvester equations}. Experimental results on synthetic and benchmark datasets show that the proposed method systematically outperforms several state-of-the-art multitask learning methods.
Tasks
Published	2017-03-03
URL	http://arxiv.org/abs/1703.00994v1
PDF	http://arxiv.org/pdf/1703.00994v1.pdf
PWC	https://paperswithcode.com/paper/co-clustering-for-multitask-learning
Repo
Framework

Joint POS Tagging and Dependency Parsing with Transition-based Neural Networks


Title	Joint POS Tagging and Dependency Parsing with Transition-based Neural Networks
Authors	Liner Yang, Meishan Zhang, Yang Liu, Nan Yu, Maosong Sun, Guohong Fu
Abstract	While part-of-speech (POS) tagging and dependency parsing are observed to be closely related, existing work on joint modeling with manually crafted feature templates suffers from the feature sparsity and incompleteness problems. In this paper, we propose an approach to joint POS tagging and dependency parsing using transition-based neural networks. Three neural network based classifiers are designed to resolve shift/reduce, tagging, and labeling conflicts. Experiments show that our approach significantly outperforms previous methods for joint POS tagging and dependency parsing across a variety of natural languages.
Tasks	Dependency Parsing, Part-Of-Speech Tagging
Published	2017-04-25
URL	http://arxiv.org/abs/1704.07616v1
PDF	http://arxiv.org/pdf/1704.07616v1.pdf
PWC	https://paperswithcode.com/paper/joint-pos-tagging-and-dependency-parsing-with
Repo
Framework

Learning to Represent Mechanics via Long-term Extrapolation and Interpolation


Title	Learning to Represent Mechanics via Long-term Extrapolation and Interpolation
Authors	Sébastien Ehrhardt, Aron Monszpart, Andrea Vedaldi, Niloy Mitra
Abstract	While the basic laws of Newtonian mechanics are well understood, explaining a physical scenario still requires manually modeling the problem with suitable equations and associated parameters. In order to adopt such models for artificial intelligence, researchers have handcrafted the relevant states, and then used neural networks to learn the state transitions using simulation runs as training data. Unfortunately, such approaches can be unsuitable for modeling complex real-world scenarios, where manually authoring relevant state spaces tend to be challenging. In this work, we investigate if neural networks can implicitly learn physical states of real-world mechanical processes only based on visual data, and thus enable long-term physical extrapolation. We develop a recurrent neural network architecture for this task and also characterize resultant uncertainties in the form of evolving variance estimates. We evaluate our setup to extrapolate motion of a rolling ball on bowl of varying shape and orientation using only images as input, and report competitive results with approaches that assume access to internal physics models and parameters.
Tasks
Published	2017-06-06
URL	http://arxiv.org/abs/1706.02179v2
PDF	http://arxiv.org/pdf/1706.02179v2.pdf
PWC	https://paperswithcode.com/paper/learning-to-represent-mechanics-via-long-term
Repo
Framework

Robust 3D Action Recognition through Sampling Local Appearances and Global Distributions


Title	Robust 3D Action Recognition through Sampling Local Appearances and Global Distributions
Authors	Mengyuan Liu, Hong Liu, Chen Chen
Abstract	3D action recognition has broad applications in human-computer interaction and intelligent surveillance. However, recognizing similar actions remains challenging since previous literature fails to capture motion and shape cues effectively from noisy depth data. In this paper, we propose a novel two-layer Bag-of-Visual-Words (BoVW) model, which suppresses the noise disturbances and jointly encodes both motion and shape cues. First, background clutter is removed by a background modeling method that is designed for depth data. Then, motion and shape cues are jointly used to generate robust and distinctive spatial-temporal interest points (STIPs): motion-based STIPs and shape-based STIPs. In the first layer of our model, a multi-scale 3D local steering kernel (M3DLSK) descriptor is proposed to describe local appearances of cuboids around motion-based STIPs. In the second layer, a spatial-temporal vector (STV) descriptor is proposed to describe the spatial-temporal distributions of shape-based STIPs. Using the Bag-of-Visual-Words (BoVW) model, motion and shape cues are combined to form a fused action representation. Our model performs favorably compared with common STIP detection and description methods. Thorough experiments verify that our model is effective in distinguishing similar actions and robust to background clutter, partial occlusions and pepper noise.
Tasks	3D Human Action Recognition, Temporal Action Localization
Published	2017-12-04
URL	http://arxiv.org/abs/1712.01090v2
PDF	http://arxiv.org/pdf/1712.01090v2.pdf
PWC	https://paperswithcode.com/paper/robust-3d-action-recognition-through-sampling
Repo
Framework

Inferring Human Activities Using Robust Privileged Probabilistic Learning


Title	Inferring Human Activities Using Robust Privileged Probabilistic Learning
Authors	Michalis Vrigkas, Evangelos Kazakos, Christophoros Nikou, Ioannis A. Kakadiaris
Abstract	Classification models may often suffer from “structure imbalance” between training and testing data that may occur due to the deficient data collection process. This imbalance can be represented by the learning using privileged information (LUPI) paradigm. In this paper, we present a supervised probabilistic classification approach that integrates LUPI into a hidden conditional random field (HCRF) model. The proposed model is called LUPI-HCRF and is able to cope with additional information that is only available during training. Moreover, the proposed method employes Student’s t-distribution to provide robustness to outliers by modeling the conditional distribution of the privileged information. Experimental results in three publicly available datasets demonstrate the effectiveness of the proposed approach and improve the state-of-the-art in the LUPI framework for recognizing human activities.
Tasks
Published	2017-08-31
URL	http://arxiv.org/abs/1708.09825v1
PDF	http://arxiv.org/pdf/1708.09825v1.pdf
PWC	https://paperswithcode.com/paper/inferring-human-activities-using-robust
Repo
Framework

An Online Optimization Approach for Multi-Agent Tracking of Dynamic Parameters in the Presence of Adversarial Noise


Title	An Online Optimization Approach for Multi-Agent Tracking of Dynamic Parameters in the Presence of Adversarial Noise
Authors	Shahin Shahrampour, Ali Jadbabaie
Abstract	This paper addresses tracking of a moving target in a multi-agent network. The target follows a linear dynamics corrupted by an adversarial noise, i.e., the noise is not generated from a statistical distribution. The location of the target at each time induces a global time-varying loss function, and the global loss is a sum of local losses, each of which is associated to one agent. Agents noisy observations could be nonlinear. We formulate this problem as a distributed online optimization where agents communicate with each other to track the minimizer of the global loss. We then propose a decentralized version of the Mirror Descent algorithm and provide the non-asymptotic analysis of the problem. Using the notion of dynamic regret, we measure the performance of our algorithm versus its offline counterpart in the centralized setting. We prove that the bound on dynamic regret scales inversely in the network spectral gap, and it represents the adversarial noise causing deviation with respect to the linear dynamics. Our result subsumes a number of results in the distributed optimization literature. Finally, in a numerical experiment, we verify that our algorithm can be simply implemented for multi-agent tracking with nonlinear observations.
Tasks	Distributed Optimization
Published	2017-02-21
URL	http://arxiv.org/abs/1702.06219v1
PDF	http://arxiv.org/pdf/1702.06219v1.pdf
PWC	https://paperswithcode.com/paper/an-online-optimization-approach-for-multi
Repo
Framework

Clustering-Based Quantisation for PDE-Based Image Compression


Title	Clustering-Based Quantisation for PDE-Based Image Compression
Authors	Laurent Hoeltgen, Pascal Peter, Michael Breuß
Abstract	Finding optimal data for inpainting is a key problem in the context of partial differential equation based image compression. The data that yields the most accurate reconstruction is real-valued. Thus, quantisation models are mandatory to allow an efficient encoding. These can also be understood as challenging data clustering problems. Although clustering approaches are well suited for this kind of compression codecs, very few works actually consider them. Each pixel has a global impact on the reconstruction and optimal data locations are strongly correlated with their corresponding colour values. These facts make it hard to predict which feature works best. In this paper we discuss quantisation strategies based on popular methods such as k-means. We are lead to the central question which kind of feature vectors are best suited for image compression. To this end we consider choices such as the pixel values, the histogram or the colour map. Our findings show that the number of colours can be reduced significantly without impacting the reconstruction quality. Surprisingly, these benefits do not directly translate to a good image compression performance. The gains in the compression ratio are lost due to increased storage costs. This suggests that it is integral to evaluate the clustering on both, the reconstruction error and the final file size.
Tasks	Image Compression
Published	2017-06-20
URL	http://arxiv.org/abs/1706.06347v1
PDF	http://arxiv.org/pdf/1706.06347v1.pdf
PWC	https://paperswithcode.com/paper/clustering-based-quantisation-for-pde-based
Repo
Framework

SUBIC: A supervised, structured binary code for image search


Title	SUBIC: A supervised, structured binary code for image search
Authors	Himalaya Jain, Joaquin Zepeda, Patrick Pérez, Rémi Gribonval
Abstract	For large-scale visual search, highly compressed yet meaningful representations of images are essential. Structured vector quantizers based on product quantization and its variants are usually employed to achieve such compression while minimizing the loss of accuracy. Yet, unlike binary hashing schemes, these unsupervised methods have not yet benefited from the supervision, end-to-end learning and novel architectures ushered in by the deep learning revolution. We hence propose herein a novel method to make deep convolutional neural networks produce supervised, compact, structured binary codes for visual search. Our method makes use of a novel block-softmax non-linearity and of batch-based entropy losses that together induce structure in the learned encodings. We show that our method outperforms state-of-the-art compact representations based on deep hashing or structured quantization in single and cross-domain category retrieval, instance retrieval and classification. We make our code and models publicly available online.
Tasks	Image Retrieval, Quantization
Published	2017-08-09
URL	http://arxiv.org/abs/1708.02932v1
PDF	http://arxiv.org/pdf/1708.02932v1.pdf
PWC	https://paperswithcode.com/paper/subic-a-supervised-structured-binary-code-for
Repo
Framework