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

Convolutional neural networks (CNNs) have been widely used in computer vision community, significantly improving the state-of-the-art. In most of the available CNNs, the softmax loss function is used as the supervision signal to train the deep model. In order to enhance the discriminative power of the deeply learned features, this paper proposes a new supervision signal, called center loss, for face recognition task. Specifically, the center loss simultaneously learns a center for deep features of each class and penalizes the distances between the deep features and their corresponding class centers. More importantly, we prove that the proposed center loss function is trainable and easy to optimize in the CNNs. With the joint supervision of softmax loss and center loss, we can train a robust CNNs to obtain the deep features with the two key learning objectives, inter-class dispension and intra-class compactness as much as possible, which are very essential to face recognition. It is encouraging to see that our CNNs (with such joint supervision) achieve the state-of-the-art accuracy on several important face recognition benchmarks, Labeled Faces in the Wild (LFW), YouTube Faces (YTF), and MegaFace Challenge. Especially, our new approach achieves the best results on MegaFace (the largest public domain face benchmark) under the protocol of small training set (contains under 500000 images and under 20000 persons), significantly improving the previous results and setting new state-of-the-art for both face recognition and face verification tasks.

/pdf/a-discriminative-feature-learning-approach-for-deep-face-2zrw7nm451.pdf

A Discriminative Feature Learning Approach for Deep Face Recognition

The PASCAL Visual Object Classes Challenge

This paper addresses deep face recognition (FR) problem under open-set protocol, where ideal face features are expected to have smaller maximal intra-class distance than minimal inter-class distance under a suitably chosen metric space. However, few existing algorithms can effectively achieve this criterion. To this end, we propose the angular softmax (A-Softmax) loss that enables convolutional neural networks (CNNs) to learn angularly discriminative features. Geometrically, A-Softmax loss can be viewed as imposing discriminative constraints on a hypersphere manifold, which intrinsically matches the prior that faces also lie on a manifold. Moreover, the size of angular margin can be quantitatively adjusted by a parameter m. We further derive specific m to approximate the ideal feature criterion. Extensive analysis and experiments on Labeled Face in the Wild (LFW), Youtube Faces (YTF) and MegaFace Challenge 1 show the superiority of A-Softmax loss in FR tasks.

/pdf/sphereface-deep-hypersphere-embedding-for-face-recognition-bof1bk9snh.pdf

SphereFace: Deep Hypersphere Embedding for Face Recognition

A scheme is developed for classifying the types of motion perceived by a humanlike robot. It is assumed that the robot receives visual images of the scene using a perspective system model. Equations, theorems, concepts, clues, etc., relating the objects, their positions, and their motion to their images on the focal plane are presented. >

http://ieeexplore.ieee.org/iel2/815/3148/00100651.pdf

Robot vision

In this paper, we propose a semi-supervised approach for representative selection, which finds a small set of representatives that can well summarize a large data collection. Given labeled source data and big unlabeled target data, we aim to find representatives in the target data, which can not only represent and associate data points belonging to each labeled category, but also discover novel categories in the target data, if any. To leverage labeled source data, we guide representative selection from labeled source to unlabeled target. We propose a joint optimization framework which alternately optimizes (1) representative selection in the target data and (2) discriminative feature learning from both the source and the target for better representative selection. Experiments on image and video datasets demonstrate that our proposed approach not only finds better representatives, but also can discover novel categories in the target data that are not in the source.

/pdf/joint-representative-selection-and-feature-learning-a-semi-2lyw6u2hsh.pdf

Joint Representative Selection and Feature Learning: A Semi-Supervised Approach

Demosaicking process is generally performed to reconstruct full color images from color filter array samples acquired by digital cameras. Over the past recent years, a large number of demosaicking algorithms have been proposed in the literature. When comparing the performances of different demosaicking algorithms, some existing work might use different experimental settings and test images. The objective of this paper is to show that different experimental settings and test images could affect the comparison results substantially. In particular, a series of experiments have been conducted to examine and demonstrate the effects of three experimental settings-CFA arrangement, image size, and image luminance-on demosaicking performance. It is advocated that for a fair comparison of different demosaicking algorithms, these performance factors should be taken into consideration

Performance Factors for Evaluating Color Filter Array Demosaicking Algorithms

This paper presents a new method for estimating the relative compression distortion among images encoded from the same original. Increasingly, many compressed versions of the same image are available over the Internet, but users may not have access to the original to measure their objective quality. We propose to cross-check each image against the quantization constraints of another version and obtain a conservative estimation of the difference in mean squared error (ΔMSE), indicating the relative objective quality between these images. Our proposed method is able to judge the relative quality correctly among compressed images with PSNR difference of as little as 0.5 dB, and it is applicable to images in mixed compression formats, such as JPEG and JPEG2000.

Estimating relative objective quality among images compressed from the same original

Retrieving similar video clips from large video database requires high query efficiency, precision and recall, which remains a challenging problem since the traditional query algorithms are inefficient and time-consuming. In this paper, we adopt the high-dimensional index structure vector-approximation file (VA-file) to organize the video database, and propose a new similarity measure which takes the temporal order among the video representations into account to improve the accuracy of query. Based on the VA-file and similarity measure, a new video clip retrieval algorithm is proposed in our method to achieve high query efficiency by using restricted sliding window to construct candidate video clips. Experimental results show that the proposed video retrieval method is efficient and effective

Efficient Video Clip Retrieval Using Index Structure

We present an automated and complete camera-based monitoring system that makes use of low-level color features to perform detection, tracking and recognition of multiple people in video sequence. Specifically, the system employs a novel coverage check-up method to segment detected foreground regions into isolated people and then localize each of them. During tracking, the appearances of people are modeled by their color histograms so that the system can keep aware of their identities and recognize them after occlusions by maximizing the joint likelihood. To make the recognition more robust against shadows or changes of background illumination, the system also incorporates a shadow removal scheme to suppress shadow effects and hence improve the quality of color histogram. The proposed system has been used to identify people who re-enter the field of view of a monitoring camera in a closed-environment. Experimental results of real video data demonstrate the efficacy of the proposed people monitoring system.

Yap-Peng Tan

Papers

Joint Representative Selection and Feature Learning: A Semi-Supervised Approach

Performance Factors for Evaluating Color Filter Array Demosaicking Algorithms

Estimating relative objective quality among images compressed from the same original

Efficient Video Clip Retrieval Using Index Structure

Robust color object tracking with application to people monitoring