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 general definition of convex potential functions is given for discontinuity-preserving MRF restoration models. This gives a class of Bayesian (image) MRF models which satisfy several desirable analytical and computational properties for regularization of ill-posed problems. The relationship between potential functions in MRF models and their discontinuity-preserving property is discussed and an important guideline is derived for devising potential functions in MRF models to be adaptive to discontinuities.

Convex MRF potential functions

Accuracy and efficiency are two conflicting challenges for face detection, since effective models tend to be computationally prohibitive. To address these two conflicting challenges, our core idea is to shrink the input image and focus on detecting small faces. Specifically, we propose a novel face detector, dubbed the name Densely Connected Face Proposal Network (DCFPN), with high performance as well as real-time speed on the CPU devices. On the one hand, we subtly design a lightweight-but-powerful fully convolutional network with the consideration of efficiency and accuracy. On the other hand, we use the dense anchor strategy and propose a fair L1 loss function to handle small faces well. As a consequence, our method can detect faces at 30 FPS on a single 2.60 GHz CPU core and 250 FPS using a GPU for the VGA-resolution images. We achieve state-of-the-art performance on the AFW, PASCAL face and FDDB datasets.

Detecting Face with Densely Connected Face Proposal Network

Proton exchange membrane (PEM) fuel cell uninterrupted power supply (UPS) has been getting much attention recently. Fuel cell UPS needs another bridge power to smooth from the utility to the fuel cell because the fuel cell stack takes a certain time to start up. Batteries play the role conventionally. Ultracapacitor has many advantages compared with batteries excepts a problem: ultracapacitor voltage drops sharply while discharging. This paper studied a dynamic discharge structure model for ultracapacitor application in a 3 kW base station UPS. The duration of holding valid voltage by the dynamic discharge structure is more than twice comparing to the static discharge structure. Also the dynamic discharge structure has a better efficiency than the static discharge structure using a DC/DC converter to extend the duration.

A dynamic discharge structure for ultracapacitor application in the fuel cell UPS

Deep learning on graphs has recently achieved remarkable success on a variety of tasks while such success relies heavily on the massive and carefully labeled data. However, precise annotations are generally very expensive and time-consuming. To address this problem, self-supervised learning (SSL) is emerging as a new paradigm for extracting informative knowledge through well-designed pretext tasks without relying on manual labels. In this survey, we extend the concept of SSL, which first emerged in the fields of computer vision and natural language processing, to present a timely and comprehensive review of the existing SSL techniques for graph data. Specifically, we divide existing graph SSL methods into three categories: contrastive, generative, and predictive. More importantly, unlike many other surveys that only provide a high-level description of published research, we present an additional mathematical summary of the existing works in a unified framework. Furthermore, to facilitate methodological development and empirical comparisons, we also summarize the commonly used datasets, evaluation metrics, downstream tasks, and open-source implementations of various algorithms. Finally, we discuss the technical challenges and potential future directions for improving graph self-supervised learning.

Self-supervised on Graphs: Contrastive, Generative, or Predictive.

This paper mainly considers the MeshFace verification problem with dense watermarks. A dense watermark often covers the crucial parts of face photo, thus degenerating the performance in the existing face verification system. The key to solving it is to preserve the ID information while removing the dense watermark. In this paper, we propose an improved GAN model, named De-mark GAN, for MeshFace verification. It consists of one generator and one global-internal discriminator. The generator is an encoderdecoder architecture with a pixel reconstruction loss and a feature loss. It maps a MeshFace photo to a representation vector, and then decodes the vector to a RGB ID photo. The succedent global-internal discriminator integrates a global discriminator and an internal discriminator with a global loss and internal loss, respectively. It can ensure the generated image quality and preserve the the ID information of recovered ID photos. Experimental results show that the verification benefits well from the recovered ID photos with high quality and our proposed De-mark GAN can achieve a competitive result in both image quality and verification.

Stan Z. Li

Papers

Convex MRF potential functions

Detecting Face with Densely Connected Face Proposal Network

A dynamic discharge structure for ultracapacitor application in the fuel cell UPS

Self-supervised on Graphs: Contrastive, Generative, or Predictive.

De-Mark GAN: Removing Dense Watermark with Generative Adversarial Network