July 28, 2019

3170 words 15 mins read

Paper Group ANR 277

Facial Keypoints Detection. Second-order Convolutional Neural Networks. Complexity Analysis Approach for Prefabricated Construction Products Using Uncertain Data Clustering. Track Everything: Limiting Prior Knowledge in Online Multi-Object Recognition. Semi-Supervised and Active Few-Shot Learning with Prototypical Networks. GM-Net: Learning Feature …

Facial Keypoints Detection


Title	Facial Keypoints Detection
Authors	Shenghao Shi
Abstract	Detect facial keypoints is a critical element in face recognition. However, there is difficulty to catch keypoints on the face due to complex influences from original images, and there is no guidance to suitable algorithms. In this paper, we study different algorithms that can be applied to locate keyponits. Specifically: our framework (1)prepare the data for further investigation (2)Using PCA and LBP to process the data (3) Apply different algorithms to analysis data, including linear regression models, tree based model, neural network and convolutional neural network, etc. Finally we will give our conclusion and further research topic. A comprehensive set of experiments on dataset demonstrates the effectiveness of our framework.
Tasks	Face Recognition
Published	2017-10-15
URL	http://arxiv.org/abs/1710.05279v1
PDF	http://arxiv.org/pdf/1710.05279v1.pdf
PWC	https://paperswithcode.com/paper/facial-keypoints-detection
Repo
Framework

Second-order Convolutional Neural Networks


Title	Second-order Convolutional Neural Networks
Authors	Kaicheng Yu, Mathieu Salzmann
Abstract	Convolutional Neural Networks (CNNs) have been successfully applied to many computer vision tasks, such as image classification. By performing linear combinations and element-wise nonlinear operations, these networks can be thought of as extracting solely first-order information from an input image. In the past, however, second-order statistics computed from handcrafted features, e.g., covariances, have proven highly effective in diverse recognition tasks. In this paper, we introduce a novel class of CNNs that exploit second-order statistics. To this end, we design a series of new layers that (i) extract a covariance matrix from convolutional activations, (ii) compute a parametric, second-order transformation of a matrix, and (iii) perform a parametric vectorization of a matrix. These operations can be assembled to form a Covariance Descriptor Unit (CDU), which replaces the fully-connected layers of standard CNNs. Our experiments demonstrate the benefits of our new architecture, which outperform the first-order CNNs, while relying on up to 90% fewer parameters.
Tasks	Image Classification
Published	2017-03-20
URL	http://arxiv.org/abs/1703.06817v1
PDF	http://arxiv.org/pdf/1703.06817v1.pdf
PWC	https://paperswithcode.com/paper/second-order-convolutional-neural-networks
Repo
Framework

Complexity Analysis Approach for Prefabricated Construction Products Using Uncertain Data Clustering


Title	Complexity Analysis Approach for Prefabricated Construction Products Using Uncertain Data Clustering
Authors	Wenying Ji, Simaan M. AbouRizk, Osmar R. Zaiane, Yitong Li
Abstract	This paper proposes an uncertain data clustering approach to quantitatively analyze the complexity of prefabricated construction components through the integration of quality performance-based measures with associated engineering design information. The proposed model is constructed in three steps, which (1) measure prefabricated construction product complexity (hereafter referred to as product complexity) by introducing a Bayesian-based nonconforming quality performance indicator; (2) score each type of product complexity by developing a Hellinger distance-based distribution similarity measurement; and (3) cluster products into homogeneous complexity groups by using the agglomerative hierarchical clustering technique. An illustrative example is provided to demonstrate the proposed approach, and a case study of an industrial company in Edmonton, Canada, is conducted to validate the feasibility and applicability of the proposed model. This research inventively defines and investigates product complexity from the perspective of product quality performance with design information associated. The research outcomes provide simplified, interpretable, and informative insights for practitioners to better analyze and manage product complexity. In addition to this practical contribution, a novel hierarchical clustering technique is devised. This technique is capable of clustering uncertain data (i.e., beta distributions) with lower computational complexity and has the potential to be generalized to cluster all types of uncertain data.
Tasks
Published	2017-10-29
URL	http://arxiv.org/abs/1710.10555v2
PDF	http://arxiv.org/pdf/1710.10555v2.pdf
PWC	https://paperswithcode.com/paper/complexity-analysis-approach-for
Repo
Framework

Track Everything: Limiting Prior Knowledge in Online Multi-Object Recognition


Title	Track Everything: Limiting Prior Knowledge in Online Multi-Object Recognition
Authors	Sebastien C. Wong, Victor Stamatescu, Adam Gatt, David Kearney, Ivan Lee, Mark D. McDonnell
Abstract	This paper addresses the problem of online tracking and classification of multiple objects in an image sequence. Our proposed solution is to first track all objects in the scene without relying on object-specific prior knowledge, which in other systems can take the form of hand-crafted features or user-based track initialization. We then classify the tracked objects with a fast-learning image classifier that is based on a shallow convolutional neural network architecture and demonstrate that object recognition improves when this is combined with object state information from the tracking algorithm. We argue that by transferring the use of prior knowledge from the detection and tracking stages to the classification stage we can design a robust, general purpose object recognition system with the ability to detect and track a variety of object types. We describe our biologically inspired implementation, which adaptively learns the shape and motion of tracked objects, and apply it to the Neovision2 Tower benchmark data set, which contains multiple object types. An experimental evaluation demonstrates that our approach is competitive with state-of-the-art video object recognition systems that do make use of object-specific prior knowledge in detection and tracking, while providing additional practical advantages by virtue of its generality.
Tasks	Object Recognition
Published	2017-04-21
URL	http://arxiv.org/abs/1704.06415v1
PDF	http://arxiv.org/pdf/1704.06415v1.pdf
PWC	https://paperswithcode.com/paper/track-everything-limiting-prior-knowledge-in
Repo
Framework

Semi-Supervised and Active Few-Shot Learning with Prototypical Networks


Title	Semi-Supervised and Active Few-Shot Learning with Prototypical Networks
Authors	Rinu Boney, Alexander Ilin
Abstract	We consider the problem of semi-supervised few-shot classification where a classifier needs to adapt to new tasks using a few labeled examples and (potentially many) unlabeled examples. We propose a clustering approach to the problem. The features extracted with Prototypical Networks are clustered using $K$-means with the few labeled examples guiding the clustering process. We note that in many real-world applications the adaptation performance can be significantly improved by requesting the few labels through user feedback. We demonstrate good performance of the active adaptation strategy using image data.
Tasks	Few-Shot Learning
Published	2017-11-29
URL	http://arxiv.org/abs/1711.10856v2
PDF	http://arxiv.org/pdf/1711.10856v2.pdf
PWC	https://paperswithcode.com/paper/semi-supervised-and-active-few-shot-learning
Repo
Framework

GM-Net: Learning Features with More Efficiency


Title	GM-Net: Learning Features with More Efficiency
Authors	Yujia Chen, Ce Li
Abstract	Deep Convolutional Neural Networks (CNNs) are capable of learning unprecedentedly effective features from images. Some researchers have struggled to enhance the parameters’ efficiency using grouped convolution. However, the relation between the optimal number of convolutional groups and the recognition performance remains an open problem. In this paper, we propose a series of Basic Units (BUs) and a two-level merging strategy to construct deep CNNs, referred to as a joint Grouped Merging Net (GM-Net), which can produce joint grouped and reused deep features while maintaining the feature discriminability for classification tasks. Our GM-Net architectures with the proposed BU_A (dense connection) and BU_B (straight mapping) lead to significant reduction in the number of network parameters and obtain performance improvement in image classification tasks. Extensive experiments are conducted to validate the superior performance of the GM-Net than the state-of-the-arts on the benchmark datasets, e.g., MNIST, CIFAR-10, CIFAR-100 and SVHN.
Tasks	Image Classification
Published	2017-06-21
URL	http://arxiv.org/abs/1706.06792v1
PDF	http://arxiv.org/pdf/1706.06792v1.pdf
PWC	https://paperswithcode.com/paper/gm-net-learning-features-with-more-efficiency
Repo
Framework

Quantum Artificial Life in an IBM Quantum Computer


Title	Quantum Artificial Life in an IBM Quantum Computer
Authors	U. Alvarez-Rodriguez, M. Sanz, L. Lamata, E. Solano
Abstract	We present the first experimental realization of a quantum artificial life algorithm in a quantum computer. The quantum biomimetic protocol encodes tailored quantum behaviors belonging to living systems, namely, self-replication, mutation, interaction between individuals, and death, into the cloud quantum computer IBM ibmqx4. In this experiment, entanglement spreads throughout generations of individuals, where genuine quantum information features are inherited through genealogical networks. As a pioneering proof-of-principle, experimental data fits the ideal model with accuracy. Thereafter, these and other models of quantum artificial life, for which no classical device may predict its quantum supremacy evolution, can be further explored in novel generations of quantum computers. Quantum biomimetics, quantum machine learning, and quantum artificial intelligence will move forward hand in hand through more elaborate levels of quantum complexity.
Tasks	Artificial Life, Quantum Machine Learning
Published	2017-11-26
URL	http://arxiv.org/abs/1711.09442v2
PDF	http://arxiv.org/pdf/1711.09442v2.pdf
PWC	https://paperswithcode.com/paper/quantum-artificial-life-in-an-ibm-quantum
Repo
Framework

A New Measure of Conditional Dependence


Title	A New Measure of Conditional Dependence
Authors	Jalal Etesami, Kun Zhang, Negar Kiyavash
Abstract	Measuring conditional dependencies among the variables of a network is of great interest to many disciplines. This paper studies some shortcomings of the existing dependency measures in detecting direct causal influences or their lack of ability for group selection to capture strong dependencies and accordingly introduces a new statistical dependency measure to overcome them. This measure is inspired by Dobrushin’s coefficients and based on the fact that there is no dependency between $X$ and $Y$ given another variable $Z$, if and only if the conditional distribution of $Y$ given $X=x$ and $Z=z$ does not change when $X$ takes another realization $x'$ while $Z$ takes the same realization $z$. We show the advantages of this measure over the related measures in the literature. Moreover, we establish the connection between our measure and the integral probability metric (IPM) that helps to develop estimators of the measure with lower complexity compared to other relevant information theoretic based measures. Finally, we show the performance of this measure through numerical simulations.
Tasks
Published	2017-03-31
URL	http://arxiv.org/abs/1704.00607v2
PDF	http://arxiv.org/pdf/1704.00607v2.pdf
PWC	https://paperswithcode.com/paper/a-new-measure-of-conditional-dependence
Repo
Framework

On the Optimization Landscape of Tensor Decompositions


Title	On the Optimization Landscape of Tensor Decompositions
Authors	Rong Ge, Tengyu Ma
Abstract	Non-convex optimization with local search heuristics has been widely used in machine learning, achieving many state-of-art results. It becomes increasingly important to understand why they can work for these NP-hard problems on typical data. The landscape of many objective functions in learning has been conjectured to have the geometric property that “all local optima are (approximately) global optima”, and thus they can be solved efficiently by local search algorithms. However, establishing such property can be very difficult. In this paper, we analyze the optimization landscape of the random over-complete tensor decomposition problem, which has many applications in unsupervised learning, especially in learning latent variable models. In practice, it can be efficiently solved by gradient ascent on a non-convex objective. We show that for any small constant $\epsilon > 0$, among the set of points with function values $(1+\epsilon)$-factor larger than the expectation of the function, all the local maxima are approximate global maxima. Previously, the best-known result only characterizes the geometry in small neighborhoods around the true components. Our result implies that even with an initialization that is barely better than the random guess, the gradient ascent algorithm is guaranteed to solve this problem. Our main technique uses Kac-Rice formula and random matrix theory. To our best knowledge, this is the first time when Kac-Rice formula is successfully applied to counting the number of local minima of a highly-structured random polynomial with dependent coefficients.
Tasks	Latent Variable Models
Published	2017-06-18
URL	http://arxiv.org/abs/1706.05598v1
PDF	http://arxiv.org/pdf/1706.05598v1.pdf
PWC	https://paperswithcode.com/paper/on-the-optimization-landscape-of-tensor
Repo
Framework

An inexact subsampled proximal Newton-type method for large-scale machine learning


Title	An inexact subsampled proximal Newton-type method for large-scale machine learning
Authors	Xuanqing Liu, Cho-Jui Hsieh, Jason D. Lee, Yuekai Sun
Abstract	We propose a fast proximal Newton-type algorithm for minimizing regularized finite sums that returns an $\epsilon$-suboptimal point in $\tilde{\mathcal{O}}(d(n + \sqrt{\kappa d})\log(\frac{1}{\epsilon}))$ FLOPS, where $n$ is number of samples, $d$ is feature dimension, and $\kappa$ is the condition number. As long as $n > d$, the proposed method is more efficient than state-of-the-art accelerated stochastic first-order methods for non-smooth regularizers which requires $\tilde{\mathcal{O}}(d(n + \sqrt{\kappa n})\log(\frac{1}{\epsilon}))$ FLOPS. The key idea is to form the subsampled Newton subproblem in a way that preserves the finite sum structure of the objective, thereby allowing us to leverage recent developments in stochastic first-order methods to solve the subproblem. Experimental results verify that the proposed algorithm outperforms previous algorithms for $\ell_1$-regularized logistic regression on real datasets.
Tasks
Published	2017-08-28
URL	http://arxiv.org/abs/1708.08552v1
PDF	http://arxiv.org/pdf/1708.08552v1.pdf
PWC	https://paperswithcode.com/paper/an-inexact-subsampled-proximal-newton-type
Repo
Framework

Zero-Annotation Object Detection with Web Knowledge Transfer


Title	Zero-Annotation Object Detection with Web Knowledge Transfer
Authors	Qingyi Tao, Hao Yang, Jianfei Cai
Abstract	Object detection is one of the major problems in computer vision, and has been extensively studied. Most of the existing detection works rely on labor-intensive supervision, such as ground truth bounding boxes of objects or at least image-level annotations. On the contrary, we propose an object detection method that does not require any form of human annotation on target tasks, by exploiting freely available web images. In order to facilitate effective knowledge transfer from web images, we introduce a multi-instance multi-label domain adaption learning framework with two key innovations. First of all, we propose an instance-level adversarial domain adaptation network with attention on foreground objects to transfer the object appearances from web domain to target domain. Second, to preserve the class-specific semantic structure of transferred object features, we propose a simultaneous transfer mechanism to transfer the supervision across domains through pseudo strong label generation. With our end-to-end framework that simultaneously learns a weakly supervised detector and transfers knowledge across domains, we achieved significant improvements over baseline methods on the benchmark datasets.
Tasks	Domain Adaptation, Object Detection, Transfer Learning
Published	2017-11-16
URL	http://arxiv.org/abs/1711.05954v2
PDF	http://arxiv.org/pdf/1711.05954v2.pdf
PWC	https://paperswithcode.com/paper/zero-annotation-object-detection-with-web
Repo
Framework

Detection of Human Rights Violations in Images: Can Convolutional Neural Networks help?


Title	Detection of Human Rights Violations in Images: Can Convolutional Neural Networks help?
Authors	Grigorios Kalliatakis, Shoaib Ehsan, Maria Fasli, Ales Leonardis, Juergen Gall, Klaus D. McDonald-Maier
Abstract	After setting the performance benchmarks for image, video, speech and audio processing, deep convolutional networks have been core to the greatest advances in image recognition tasks in recent times. This raises the question of whether there are any benefit in targeting these remarkable deep architectures with the unattempted task of recognising human rights violations through digital images. Under this perspective, we introduce a new, well-sampled human rights-centric dataset called Human Rights Understanding (HRUN). We conduct a rigorous evaluation on a common ground by combining this dataset with different state-of-the-art deep convolutional architectures in order to achieve recognition of human rights violations. Experimental results on the HRUN dataset have shown that the best performing CNN architectures can achieve up to 88.10% mean average precision. Additionally, our experiments demonstrate that increasing the size of the training samples is crucial for achieving an improvement on mean average precision principally when utilising very deep networks.
Tasks
Published	2017-03-12
URL	http://arxiv.org/abs/1703.04103v2
PDF	http://arxiv.org/pdf/1703.04103v2.pdf
PWC	https://paperswithcode.com/paper/detection-of-human-rights-violations-in
Repo
Framework

Security, Privacy and Safety Evaluation of Dynamic and Static Fleets of Drones


Title	Security, Privacy and Safety Evaluation of Dynamic and Static Fleets of Drones
Authors	Raja Naeem Akram, Konstantinos Markantonakis, Keith Mayes, Oussama Habachi, Damien Sauveron, Andreas Steyven, Serge Chaumette
Abstract	Inter-connected objects, either via public or private networks are the near future of modern societies. Such inter-connected objects are referred to as Internet-of-Things (IoT) and/or Cyber-Physical Systems (CPS). One example of such a system is based on Unmanned Aerial Vehicles (UAVs). The fleet of such vehicles are prophesied to take on multiple roles involving mundane to high-sensitive, such as, prompt pizza or shopping deliveries to your homes to battlefield deployment for reconnaissance and combat missions. Drones, as we refer to UAVs in this paper, either can operate individually (solo missions) or part of a fleet (group missions), with and without constant connection with the base station. The base station acts as the command centre to manage the activities of the drones. However, an independent, localised and effective fleet control is required, potentially based on swarm intelligence, for the reasons: 1) increase in the number of drone fleets, 2) number of drones in a fleet might be multiple of tens, 3) time-criticality in making decisions by such fleets in the wild, 4) potential communication congestions/lag, and 5) in some cases working in challenging terrains that hinders or mandates-limited communication with control centre (i.e., operations spanning long period of times or military usage of such fleets in enemy territory). This self-ware, mission-focused and independent fleet of drones that potential utilises swarm intelligence for a) air-traffic and/or flight control management, b) obstacle avoidance, c) self-preservation while maintaining the mission criteria, d) collaboration with other fleets in the wild (autonomously) and e) assuring the security, privacy and safety of physical (drones itself) and virtual (data, software) assets. In this paper, we investigate the challenges faced by fleet of drones and propose a potential course of action on how to overcome them.
Tasks
Published	2017-08-18
URL	http://arxiv.org/abs/1708.05732v1
PDF	http://arxiv.org/pdf/1708.05732v1.pdf
PWC	https://paperswithcode.com/paper/security-privacy-and-safety-evaluation-of
Repo
Framework

Person Re-Identification by Deep Joint Learning of Multi-Loss Classification


Title	Person Re-Identification by Deep Joint Learning of Multi-Loss Classification
Authors	Wei Li, Xiatian Zhu, Shaogang Gong
Abstract	Existing person re-identification (re-id) methods rely mostly on either localised or global feature representation alone. This ignores their joint benefit and mutual complementary effects. In this work, we show the advantages of jointly learning local and global features in a Convolutional Neural Network (CNN) by aiming to discover correlated local and global features in different context. Specifically, we formulate a method for joint learning of local and global feature selection losses designed to optimise person re-id when using only generic matching metrics such as the L2 distance. We design a novel CNN architecture for Jointly Learning Multi-Loss (JLML) of local and global discriminative feature optimisation subject concurrently to the same re-id labelled information. Extensive comparative evaluations demonstrate the advantages of this new JLML model for person re-id over a wide range of state-of-the-art re-id methods on five benchmarks (VIPeR, GRID, CUHK01, CUHK03, Market-1501).
Tasks	Feature Selection, Person Re-Identification
Published	2017-05-12
URL	http://arxiv.org/abs/1705.04724v2
PDF	http://arxiv.org/pdf/1705.04724v2.pdf
PWC	https://paperswithcode.com/paper/person-re-identification-by-deep-joint
Repo
Framework

Deep Embedding Forest: Forest-based Serving with Deep Embedding Features


Title	Deep Embedding Forest: Forest-based Serving with Deep Embedding Features
Authors	Jie Zhu, Ying Shan, JC Mao, Dong Yu, Holakou Rahmanian, Yi Zhang
Abstract	Deep Neural Networks (DNN) have demonstrated superior ability to extract high level embedding vectors from low level features. Despite the success, the serving time is still the bottleneck due to expensive run-time computation of multiple layers of dense matrices. GPGPU, FPGA, or ASIC-based serving systems require additional hardware that are not in the mainstream design of most commercial applications. In contrast, tree or forest-based models are widely adopted because of low serving cost, but heavily depend on carefully engineered features. This work proposes a Deep Embedding Forest model that benefits from the best of both worlds. The model consists of a number of embedding layers and a forest/tree layer. The former maps high dimensional (hundreds of thousands to millions) and heterogeneous low-level features to the lower dimensional (thousands) vectors, and the latter ensures fast serving. Built on top of a representative DNN model called Deep Crossing, and two forest/tree-based models including XGBoost and LightGBM, a two-step Deep Embedding Forest algorithm is demonstrated to achieve on-par or slightly better performance as compared with the DNN counterpart, with only a fraction of serving time on conventional hardware. After comparing with a joint optimization algorithm called partial fuzzification, also proposed in this paper, it is concluded that the two-step Deep Embedding Forest has achieved near optimal performance. Experiments based on large scale data sets (up to 1 billion samples) from a major sponsored search engine proves the efficacy of the proposed model.
Tasks
Published	2017-03-15
URL	http://arxiv.org/abs/1703.05291v1
PDF	http://arxiv.org/pdf/1703.05291v1.pdf
PWC	https://paperswithcode.com/paper/deep-embedding-forest-forest-based-serving
Repo
Framework