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.

Most graph neural networks (GNNs) rely on the message passing paradigm to propagate node features and build interactions. Recent works point out that different graph learning tasks require different ranges of interactions between nodes. To investigate its underlying mechanism, we explore the capacity of GNNs to capture pairwise interactions between nodes under contexts with different complexities, especially for their graph-level and node-level applications in scientiﬁc domains like biochemistry and physics. When formulating pairwise interactions, we study two common graph construction methods in scientiﬁc domains, i.e., K-nearest neighbor (KNN) graphs and fully-connected (FC) graphs. Furthermore, we demonstrate that the inductive bias introduced by KNN-graphs and FC-graphs hinders GNNs to learn the most informative order of interactions. Such a phenomenon is broadly shared by several GNNs for different graph learning tasks and forbids GNNs to achieve the global minimum loss, so we name it a representation bottleneck . To overcome that, we propose a novel graph rewiring approach based on the pairwise interaction strengths to dynamically adjust the reception ﬁelds of each node. Extensive experiments in molecular property prediction and dynamic system forecast prove the superiority of our method over state-of-the-art GNN baselines. Besides, this paper provides a reasonable explanation of why subgraphs play an important role in the determination of graph properties.

Discovering the Representation Bottleneck of Graph Neural Networks from Multi-order Interactions

Manifold learning-based encoders have been playing important roles in nonlinear dimensionality reduction (NLDR) for data exploration. However, existing methods can often fail to preserve geometric, topological and/or distributional structures of data. In this paper, we propose a deep manifold learning framework, called deep manifold transformation (DMT) for unsupervised NLDR and embedding learning. DMT enhances deep neural networks by using cross-layer local geometry-preserving (LGP) constraints. The LGP constraints constitute the loss for deep manifold learning and serve as geometric regularizers for NLDR network training. Extensive experiments on synthetic and real-world data demonstrate that DMT networks outperform existing leading manifold-based NLDR methods in terms of preserving the structures of data.

Deep Manifold Transformation for Nonlinear Dimensionality Reduction

Deep graph clustering, which aims to group the nodes of a graph into disjoint clusters with deep neural networks, has achieved promising progress in recent years. However, the existing methods fail to scale to the large graph with million nodes. To solve this problem, a scalable deep graph clustering method (Dink-Net) is proposed with the idea of dilation and shrink. Firstly, by discriminating nodes, whether being corrupted by augmentations, representations are learned in a self-supervised manner. Meanwhile, the cluster centres are initialized as learnable neural parameters. Subsequently, the clustering distribution is optimized by minimizing the proposed cluster dilation loss and cluster shrink loss in an adversarial manner. By these settings, we unify the two-step clustering, i.e., representation learning and clustering optimization, into an end-to-end framework, guiding the network to learn clustering-friendly features. Besides, Dink-Net scales well to large graphs since the designed loss functions adopt the mini-batch data to optimize the clustering distribution even without performance drops. Both experimental results and theoretical analyses demonstrate the superiority of our method. Compared to the runner-up, Dink-Net achieves 9.62% NMI improvement on the ogbn-papers100M dataset with 111 million nodes and 1.6 billion edges. The source code is released at https://github.com/yueliu1999/Dink-Net. Besides, a collection (papers, codes, and datasets) of deep graph clustering is shared at https://github.com/yueliu1999/Awesome-Deep-Graph-Clustering.

Dink-Net: Neural Clustering on Large Graphs

The performance of generic pedestrian detector usually declines seriously for videos in novel scenes, which is one of the major bottlenecks for current pedestrian detection techniques. The conventional works improve pedestrian detection in video by mining new instances from detections and adapting the detector according to the collected instances. However, when treating the two tasks separately, the detector adaptation suffers from the defective output of instance mining. In this paper, we propose to jointly handle the instance mining and detector adaption using an adaptive structural model. The regularization function of the model is applied on detector to prevent overfitting in adaption, and the loss function is designed to evaluate the combination of mined instances set and detector. Particularly, we extend the Deformable Part Model (DPM) to adaptive DPM, where an adaptive feature transformation defined on low-level HOG cell is learned to reduce the domain shift, and the regularization function for the detector is conducted on the transformation. The loss of the instance set and detector is measured by a cost-flow network structure which incorporates both the appearance of frame-wise detections and their spatio-temporal continuity. We demonstrate an alternating minimization procedure to optimize the model. The proposed method is evaluated on ETHZ, PETS2009 and Caltech datasets, and outperforms baseline DPM by 7 % in terms of mean miss rate.

/pdf/adaptive-structural-model-for-video-based-pedestrian-150wj2yo9q.pdf

Adaptive Structural Model for Video Based Pedestrian Detection

these points must not be coplanar. We report in this article a real time algorithm TIM that can track and estimate hand gesture, providing reliably 5 degrees of freedom from a single camera for controlling of a robot head. The advantages of this algorithm are: it does not require camera calibration and the syetem will operate under any configuration; secondly it converges fast and reliably which means special hardware, such as a powerful parallel platform, may be dispensed with. Kalman filter is used to track feature points on the finger tips.

/pdf/visual-control-of-a-robot-head-21irf5rmwa.pdf

Stan Z. Li

Papers

Discovering the Representation Bottleneck of Graph Neural Networks from Multi-order Interactions

Deep Manifold Transformation for Nonlinear Dimensionality Reduction

Dink-Net: Neural Clustering on Large Graphs

Adaptive Structural Model for Video Based Pedestrian Detection

Visual Control of a Robot Head