We propose a deep convolutional neural network architecture codenamed Inception that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14). The main hallmark of this architecture is the improved utilization of the computing resources inside the network. By a carefully crafted design, we increased the depth and width of the network while keeping the computational budget constant. To optimize quality, the architectural decisions were based on the Hebbian principle and the intuition of multi-scale processing. One particular incarnation used in our submission for ILSVRC14 is called GoogLeNet, a 22 layers deep network, the quality of which is assessed in the context of classification and detection.

/pdf/going-deeper-with-convolutions-1yobw2o2ds.pdf

Going deeper with convolutions

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

We will review some of the major results in random graphs and some of the more challenging open problems. We will cover algorithmic and structural questions. We will touch on newer models, including those related to the WWW.

Random graphs

There are a huge number of features which are said to improve Convolutional Neural Network (CNN) accuracy. Practical testing of combinations of such features on large datasets, and theoretical justification of the result, is required. Some features operate on certain models exclusively and for certain problems exclusively, or only for small-scale datasets; while some features, such as batch-normalization and residual-connections, are applicable to the majority of models, tasks, and datasets. We assume that such universal features include Weighted-Residual-Connections (WRC), Cross-Stage-Partial-connections (CSP), Cross mini-Batch Normalization (CmBN), Self-adversarial-training (SAT) and Mish-activation. We use new features: WRC, CSP, CmBN, SAT, Mish activation, Mosaic data augmentation, CmBN, DropBlock regularization, and CIoU loss, and combine some of them to achieve state-of-the-art results: 43.5% AP (65.7% AP50) for the MS COCO dataset at a realtime speed of ~65 FPS on Tesla V100. Source code is at this https URL

YOLOv4: Optimal Speed and Accuracy of Object Detection

“Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告

Power demand forecasting is a critical task to achieve efficiency and reliability in the smart grid in terms of demand response and resource allocation. This paper proposes PowerLSTM, a power demand forecasting model based on Long Short-Term Memory (LSTM) neural network. We calculate the feature significance and compact our model by capturing the features with the most important weights. Based on our preliminary study using a public dataset, compared to two recent works based on Gradient Boosting Tree (GBT) and Support Vector Regression (SVR), PowerLSTM demonstrates a decrease of 21.80% and 28.57% in forecasting error, respectively. Our study also reveals that metering/forecasting granularity at once every 30 min can bring higher accuracy than other practical granularity options.

PowerLSTM: Power Demand Forecasting Using Long Short-Term Memory Neural Network

Given an unreliable visual patterns and insufficient query information, content-based image retrieval is often suboptimal and requires image re-ranking using auxiliary information. In this paper, we propose a discriminative multi-view interactive image re-ranking (DMINTIR), which integrates user relevance feedback capturing users’ intentions and multiple features that sufficiently describe the images. In DMINTIR, heterogeneous property features are incorporated in the multi-view learning scheme to exploit their complementarities. In addition, a discriminatively learned weight vector is obtained to reassign updated scores and target images for re-ranking. Compared with other multi-view learning techniques, our scheme not only generates a compact representation in the latent space from the redundant multi-view features but also maximally preserves the discriminative information in feature encoding by the large-margin principle. Furthermore, the generalization error bound of the proposed algorithm is theoretically analyzed and shown to be improved by the interactions between the latent space and discriminant function learning. Experimental results on two benchmark data sets demonstrate that our approach boosts baseline retrieval quality and is competitive with the other state-of-the-art re-ranking strategies.

Discriminative Multi-View Interactive Image Re-Ranking

Images are usually associated with multiple labels and comprised of multiple views, due to each image containing several objects (eg a pedestrian, bicycle and tree) and multiple visual features (eg color, texture and shape) Currently available tools tend to use either labels or features for classification, but both are necessary to describe the image properly There have been recent successes in using vector-valued functions, which construct matrix-valued kernels, to explore the multilabel structure in the output space This has motivated us to develop multi-view vector-valued manifold regularization (MV3MR) in order to integrate multiple features MV3MR exploits the complementary properties of different features, and discovers the intrinsic local geometry of the compact support shared by different features, under the theme of manifold regularization We validate the effectiveness of the proposed MV3MR methodology for image classification by conducting extensive experiments on two challenge datasets, PASCAL VOC' 07 and MIR Flickr

/pdf/vector-valued-multi-view-semi-supervised-learning-for-multi-4klq7csg9f.pdf

Vector-valued multi-view semi-supervised learning for multi-label image classification

An effective and efficient architecture performance evaluation scheme is essential for the success of Neural Architecture Search (NAS). To save computational cost, most of existing NAS algorithms often train and evaluate intermediate neural architectures on a small proxy dataset with limited training epochs. But it is difficult to expect an accurate performance estimation of an architecture in such a coarse evaluation way. This paper advocates a new neural architecture evaluation scheme, which aims to determine which architecture would perform better instead of accurately predict the absolute architecture performance. Therefore, we propose a \textbf{relativistic} architecture performance predictor in NAS (ReNAS). We encode neural architectures into feature tensors, and further refining the representations with the predictor. The proposed relativistic performance predictor can be deployed in discrete searching methods to search for the desired architectures without additional evaluation. Experimental results on NAS-Bench-101 dataset suggests that, sampling 424 ($0.1\%$ of the entire search space) neural architectures and their corresponding validation performance is already enough for learning an accurate architecture performance predictor. The accuracies of our searched neural architectures on NAS-Bench-101 and NAS-Bench-201 datasets are higher than that of the state-of-the-art methods and show the priority of the proposed method.

ReNAS:Relativistic Evaluation of Neural Architecture Search

Online review fraud has evolved in sophistication by launching intelligent campaigns where a group of coordinated participants work together to deliver deceptive reviews for the designated targets. Such collusive fraud is considered much harder to defend against as these campaign participants are capable of evading detection by shaping their behaviors collectively so as not to appear suspicious. The present work complements existing studies by exploring more subtle behavioral trails connected with collusive review fraud. A novel statistical model is proposed to further characterize, recognize, and forecast collusive fraud in online reviews. The proposed model is completely unsupervised, which bypasses the difficulty of manual annotation required for supervised modeling. It is also highly flexible to incorporate collusion characteristics available for better modeling and prediction. Experiments on two real-world datasets demonstrate the effectiveness of the proposed method and the improvements in learning and predictive abilities.

/pdf/towards-collusive-fraud-detection-in-online-reviews-adn5n9cp1o.pdf

Chang Xu

Papers

PowerLSTM: Power Demand Forecasting Using Long Short-Term Memory Neural Network

Discriminative Multi-View Interactive Image Re-Ranking

Vector-valued multi-view semi-supervised learning for multi-label image classification

ReNAS:Relativistic Evaluation of Neural Architecture Search

Towards Collusive Fraud Detection in Online Reviews