We present YOLO, a new approach to object detection. Prior work on object detection repurposes classifiers to perform detection. Instead, we frame object detection as a regression problem to spatially separated bounding boxes and associated class probabilities. A single neural network predicts bounding boxes and class probabilities directly from full images in one evaluation. Since the whole detection pipeline is a single network, it can be optimized end-to-end directly on detection performance. Our unified architecture is extremely fast. Our base YOLO model processes images in real-time at 45 frames per second. A smaller version of the network, Fast YOLO, processes an astounding 155 frames per second while still achieving double the mAP of other real-time detectors. Compared to state-of-the-art detection systems, YOLO makes more localization errors but is less likely to predict false positives on background. Finally, YOLO learns very general representations of objects. It outperforms other detection methods, including DPM and R-CNN, when generalizing from natural images to other domains like artwork.

/pdf/you-only-look-once-unified-real-time-object-detection-3gan6roe1o.pdf

You Only Look Once: Unified, Real-Time Object Detection

Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

We consider the problem of automatically recognizing human faces from frontal views with varying expression and illumination, as well as occlusion and disguise. We cast the recognition problem as one of classifying among multiple linear regression models and argue that new theory from sparse signal representation offers the key to addressing this problem. Based on a sparse representation computed by C1-minimization, we propose a general classification algorithm for (image-based) object recognition. This new framework provides new insights into two crucial issues in face recognition: feature extraction and robustness to occlusion. For feature extraction, we show that if sparsity in the recognition problem is properly harnessed, the choice of features is no longer critical. What is critical, however, is whether the number of features is sufficiently large and whether the sparse representation is correctly computed. Unconventional features such as downsampled images and random projections perform just as well as conventional features such as eigenfaces and Laplacianfaces, as long as the dimension of the feature space surpasses certain threshold, predicted by the theory of sparse representation. This framework can handle errors due to occlusion and corruption uniformly by exploiting the fact that these errors are often sparse with respect to the standard (pixel) basis. The theory of sparse representation helps predict how much occlusion the recognition algorithm can handle and how to choose the training images to maximize robustness to occlusion. We conduct extensive experiments on publicly available databases to verify the efficacy of the proposed algorithm and corroborate the above claims.

/pdf/robust-face-recognition-via-sparse-representation-4bfqv6y74o.pdf

Robust Face Recognition via Sparse Representation

Computational single-cell RNA-seq (scRNA-seq) methods have been successfully applied to experiments representing a single condition, technology, or species to discover and define cellular phenotypes. However, identifying subpopulations of cells that are present across multiple data sets remains challenging. Here, we introduce an analytical strategy for integrating scRNA-seq data sets based on common sources of variation, enabling the identification of shared populations across data sets and downstream comparative analysis. We apply this approach, implemented in our R toolkit Seurat (http://satijalab.org/seurat/), to align scRNA-seq data sets of peripheral blood mononuclear cells under resting and stimulated conditions, hematopoietic progenitors sequenced using two profiling technologies, and pancreatic cell 'atlases' generated from human and mouse islets. In each case, we learn distinct or transitional cell states jointly across data sets, while boosting statistical power through integrated analysis. Our approach facilitates general comparisons of scRNA-seq data sets, potentially deepening our understanding of how distinct cell states respond to perturbation, disease, and evolution.

/pdf/integrating-single-cell-transcriptomic-data-across-different-3dtsi5w7ob.pdf

Integrating single-cell transcriptomic data across different conditions, technologies, and species.

A system using feature optimization and neural learning techniques is presented for detection of upright fronta l faces. The design of the system takes advantages of the existing techniques and avoid their shortcomings. Statistic al pattern recognition (PR) techniques are used to optimize th e feature selection. A neural network (NN) method is used to learn a complex mapping function for the classification, given the optimized feature set. The optimization of feature set reduces the burden of the subsequent NN classifier and improves its performance in learning speed and classification rates. The use of the NN for classification avoids the need for the simplification of classifier function, as pra cticed in the PR approach, for the mathematical tractability at the sacrifice of the performance. Experimental results show that our system produces higher detection and lower missing rates than several existing state-of-the-art face dete ction systems, with an average false detection rate.

Face detection using neural learning with optimized feature set

Face Recognition, Near-Infrared.

Person re-identification task has been greatly boosted by deep convolutional neural networks (CNNs) in recent years. The core of which is to enlarge the inter-class distinction as well as reduce the intra-class variance. However, to achieve this, existing deep models prefer to adopt image pairs or triplets to form verification loss, which is inefficient and unstable since the number of training pairs or triplets grows rapidly as the number of training data grows. Moreover, their performance is limited since they ignore the fact that different dimension of embedding may play different importance. In this paper, we propose to employ identification loss with center loss to train a deep model for person re-identification. The training process is efficient since it does not require image pairs or triplets for training while the inter-class distinction and intra-class variance are well handled. To boost the performance, a new feature reweighting (FRW) layer is designed to explicitly emphasize the importance of each embedding dimension, thus leading to an improved embedding. Experiments on several benchmark datasets have shown the superiority of our method over the state-of-the-art alternatives on both accuracy and speed.

Deep Person Re-Identification with Improved Embedding and Efficient Training

In this chapter, we introduce concepts and algorithms of shape and texture based deformable models, more speciflcally Active Shape Models (ASM), Active Appearance models (AAM) and Morphable Models, for facial image analysis. Such models, learned from training ex- amples, allow admissible deformations under statistical constraints on the shape and/or texture of the pattern of interests. As such, the de- formation is in accordance with the speciflc constraints on the pattern. Based on analysis of problems with the standard ASM and AAM, we further describe enhanced models and algorithms, namely Direct Ap- pearance Models (DAM) and Texture Constrained ASM (TC-ASM), for

/pdf/shape-and-texture-based-deformable-models-for-facial-image-4yuw5aaf1k.pdf

Shape and Texture Based Deformable Models for Facial Image Analysis

—The rapid development of mobile Internet and sharing economy brings the prosperity of spatial crowdsourcing. Spatial crowdsourcing (SC) applications assign various tasks based on workers’ location information. However, SC-servers are often untrustworthy and the exposure of users’ locations raises privacy concerns. In this paper, we design a framework Geo-MOEA (Multi-Objective Evolutionary Algorithm with Geo-obfuscation) to protect location privacy of workers involved on SC platform in mobile networks environment. We propose an adaptive regionalized obfuscation approach with inference error bounds based on geo-indistinguishability (a strong notion of differential privacy), which is suitable for the context of large-scale location data and task allocations. This enables each worker to report a pseudo-location that is adaptively generated with a personalized inference error threshold. Moreover, we introduce MOEA to optimize the trade-off between SC service availability and privacy protection while conﬁrming theoretically the most general condition on protection location sets for larger search space. Finally, the experimental results on two public datasets show that our Geo-MOEA approach achieves up to 20% reduction in service quality loss while guaranteeing differential and geo-distortion location privacy.

Stan Z. Li

Papers

Face detection using neural learning with optimized feature set

Face Recognition, Near-Infrared.

Deep Person Re-Identification with Improved Embedding and Efficient Training

Shape and Texture Based Deformable Models for Facial Image Analysis

Geo-obfuscation Mechanisms for Spatial Crowdsourcing via Multi-Objective Evolutionary Optimization