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 fast and efficient multiple layer background maintenance model is built to conserve the original and the current background separately. Fusing the properties of object motion in image pixels and the changes between the input video and the multiple background layers, this method could handle various sources of scene changes, including ghosts, abandon objects and illumination changes. An intelligent video surveillance system is developed to test the performance of the algorithm. Experiments are performed using long video sequences under different conditions indoor and outdoor. The results show that the proposed algorithm is effective and efficient in real-time and accurate background maintenance in complex environment.

/pdf/multiple-layer-based-background-maintenance-in-complex-156gll1jem.pdf

Multiple layer based background maintenance in complex environment

Graph clustering, which aims to divide the nodes in the graph into several distinct clusters, is a fundamental and challenging task. In recent years, deep graph clustering methods have been increasingly proposed and achieved promising performance. However, the corresponding survey paper is scarce and it is imminent to make a summary in this field. From this motivation, this paper makes the first comprehensive survey of deep graph clustering. Firstly, the detailed definition of deep graph clustering and the important baseline methods are introduced. Besides, the taxonomy of deep graph clustering methods is proposed based on four different criteria including graph type, network architecture, learning paradigm, and clustering method. In addition, through the careful analysis of the existing works, the challenges and opportunities from five perspectives are summarized. At last, the applications of deep graph clustering in four domains are presented. It is worth mentioning that a collection of state-of-the-art deep graph clustering methods including papers, codes, and datasets is available on GitHub. We hope this work will serve as a quick guide and help researchers to overcome challenges in this vibrant field.

A Survey of Deep Graph Clustering: Taxonomy, Challenge, and Application

Grain boundary misorientation is known to limit the critical current density of bulk high temperature superconductors. However, the effect of mechanical deformation on the texture evolution during powder-in-tube (PIT) processing remains unclear, especially on the microstructural level. In the present work, the micro- and meso-texture characteristics of PIT-processed (Bi, Pb)2Sr2Ca2Cu3O10 (Bi2223) superconductor tapes were investigated. The results for micro-texture show that a/b-axes texture does exist in PIT-processed tapes. From the meso-texture studies, it was found that a majority of the grain boundaries were formed by grains with a non-parallel c-axis. These grain boundaries generally have low mismatch angles of up to ~10°. High-angle misorientation boundaries ranging up to 45° are generally c-axis twist boundaries. Furthermore, about 40% of the grain boundaries could be coupled strongly.

Characteristics of micro-texture and meso-texture in (Bi, Pb)2Sr2Ca2Cu3O10 superconducting tapes

In this paper, we introduce a new audio medium, called audio texture, as a means of synthesizing long audio stream according to a given short example audio clip. The example clip is analyzed, and basic building patterns are extracted. Then an audio stream of arbitrary length is synthesized using a sequence of extracted building patterns. The patterns can be varied in the synthesis process to add variations to the generated sound. Audio textures are useful in applications such as background music, lullabies, game music, and screen saver sounds. A method is proposed for implementing audio textures. Preliminary results of audio textures are provided at our website for evaluation.

https://ieeexplore.ieee.org/iel5/7874/5743986/05744963.pdf

Audio textures

Using Markov random field (MRF) theory, a variety of computer vision problems can be modeled in terms of optimization based on the maximum a posteriori (MAP) criterion. The MAP configuration minimizes the energy of a posterior (Gibbs) distribution. When the label set is discrete, the minimization is combinatorial. This paper proposes to use the continuous relaxation labeling (RL) method for the minimization. The RL converts the original NP complete problem into one of polynomial complexity. Annealing may be combined into the RL process to improve the quality (globalness) of RL solutions. Performance comparison among four different RL algorithms is given.

Stan Z. Li

Papers

Multiple layer based background maintenance in complex environment

A Survey of Deep Graph Clustering: Taxonomy, Challenge, and Application

Characteristics of micro-texture and meso-texture in (Bi, Pb)2Sr2Ca2Cu3O10 superconducting tapes

Audio textures

Relaxation labeling of Markov random fields