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.

Boosting-based methods have recently led to the state-of-the-art face detection systems. In these systems, weak classifiers to be boosted are based on simple, local, Haar-like features. However, it can be empirically observed that in later stages of the boosting process, the non-face examples collected by bootstrapping become very similar to the face examples, and the classification error of Haar-like feature-based weak classifiers is thus very close to 50%. As a result, the performance of a face detector cannot be further improved. This paper proposed a solution to this problem, introducing a face detection method based on boosting in hierarchical feature spaces (both local and global). We argue that global features, like those derived from Principal Component Analysis, can be advantageously used in the later stages of boosting, when local features do not provide any further benefit, without affecting computational complexity. We show, based on statistics of face and non-face examples, that weak classifiers learned in hierarchical feature spaces are better boosted. Our methodology leads to a face detection system that achieves higher performance than the current state-of-the-art system, at a comparable speed.

http://publications.idiap.ch/downloads/reports/2003/rr-03-70.pdf

Real-Time Face Detection Using Boosting Learning in Hierarchical Feature Spaces

Recent years have witnessed remarkable advances in spatiotemporal predictive learning, incorporating auxiliary inputs, elaborate neural architectures, and sophisticated training strategies. Although impressive, the system complexity of mainstream methods is increasing as well, which may hinder the convenient applications. This paper proposes SimVP, a simple spatiotemporal predictive baseline model that is completely built upon convolutional networks without recurrent architectures and trained by common mean squared error loss in an end-to-end fashion. Without introducing any extra tricks and strategies, SimVP can achieve superior performance on various benchmark datasets. To further improve the performance, we derive variants with the gated spatiotemporal attention translator from SimVP that can achieve better performance. We demonstrate that SimVP has strong generalization and extensibility on real-world datasets through extensive experiments. The significant reduction in training cost makes it easier to scale to complex scenarios. We believe SimVP can serve as a solid baseline to benefit the spatiotemporal predictive learning community.

SimVP: Towards Simple yet Powerful Spatiotemporal Predictive Learning

Abstract Recognition of remote homologous structures is a necessary module in AlphaFold2 and is also essential for the exploration of protein folding pathways. Here, we propose a method, PAthreader, to recognize remote templates and explore folding pathways. Firstly, we design a three-track alignment between predicted distance profiles and structure profiles extracted from PDB and AlphaFold DB, to improve the recognition accuracy of remote templates. Secondly, we improve the performance of AlphaFold2 using the templates identified by PAthreader. Thirdly, we explore protein folding pathways based on our conjecture that dynamic folding information of protein is implicitly contained in its remote homologs. The results show that the average accuracy of PAthreader templates is 11.6% higher than that of HHsearch. In terms of structure modelling, PAthreader outperform AlphaFold2 and ranks first on the CAMEO blind test for the latest three months. Furthermore, we predict protein folding pathways for 37 proteins, in which the results of 7 proteins are almost consistent with those of biological experiments, and the other 30 human proteins have yet to be verified by biological experiments, revealing that folding information can be exploited from remote homologous structures. 

/pdf/protein-structure-and-folding-pathway-prediction-based-on-3jjj6opi.pdf

Protein structure and folding pathway prediction based on remote homologs recognition using PAthreader

The correlation filters for pattern recognition, have been extensively studied in the areas of automatic target recognition(ATR) and biometrics. Whereas the conventional correlation filters perform directly on image pixels, in this paper, we propose a novel method, called "feature correlation filter (FCF)", by extending the concept of correlation filter to feature spaces. The FCF preserves the benefits of conventional correlation filters, i.e., shift-invariant, occlusion-insensitive, and closed-form solution, and also inherits virtues of the feature representations. Moreover, since the size of feature is often much smaller than the size of image, the FCF method can significantly reduce the storage requirement in recognition system. The comparative results on CMU-PIE and the FRGC2.0 database show that the proposed FCFs can achieve noteworthy performance improvement compared with their conventional counterpart.

/pdf/feature-correlation-filter-for-face-recognition-4e01z8j5a1.pdf

Feature correlation filter for face recognition

In this paper, we propose a method to apply the popular cascade classifier into face recognition to improve the computational efficiency while keeping high recognition rate. In large scale face recognition systems, because the probability of feature templates coming from different subjects is very high, most of the matching pairs will be rejected by the early stages of the cascade. Therefore, the cascade can improve the matching speed significantly. On the other hand, using the nested structure of the cascade, we could drop some stages at the end of feature to reduce the memory and bandwidth usage in some resources intensive system while not sacrificing the performance too much. The cascade is learned by two steps. Firstly, some kind of prepared features are grouped into several nested stages. And then, the threshold of each stage is learned to achieve user defined verification rate (VR). In the paper, we take a landmark based Gabor+LDA face recognition system as baseline to illustrate the process and advantages of the proposed method. However, the use of this method is very generic and not limited in face recognition, which can be easily generalized to other biometrics as a post-processing module. Experiments on the FERET database show the good performance of our baseline and an experiment on a self-collected large scale database illustrates that the cascade can improve the matching speed significantly.

Stan Z. Li

Papers

Real-Time Face Detection Using Boosting Learning in Hierarchical Feature Spaces

SimVP: Towards Simple yet Powerful Spatiotemporal Predictive Learning

Protein structure and folding pathway prediction based on remote homologs recognition using PAthreader

Feature correlation filter for face recognition

Fast Matching by 2 Lines of Code for Large Scale Face Recognition Systems