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

One of problems with incremental learning approaches is that the quality of learning samples cannot be controlled since they are provided on-line. Current incremental learning algorithms ignore the issue by accepting each sample unconditionally and assimilating it into the existing recognition system. However, improper sample, caused by a partial occlusion, badly illumination condition and unusual pose, deteriorates the overall performance of the recognition system significantly. In order to overcome this issue, in this paper, based on hypothesis and verification paradigm, we propose a criterion for sample selection, and present a novel system for automatically evaluating the qualities of new added samples during the incremental learning procedure. Following this, a subspace is learned by using only the samples that are considered to be good after verification. The high computation cost, incurred by inclusion of sample verification into incremental learning framework, is greatly reduced using relative distance filtering. The experimental results demonstrated the superiority of our approach, in both recognition accuracy and robustness.

Enhancing incremental learning/recognition via efficient neighborhood estimation

Crowd counting from single images using recursive multi-pathway zooming and foreground enhancement

Verfahren zum Bestimmen einer optimalen Brennweite eines Bildaufnahmesystems, wobei fur jedes Bild einer Sequenz von Bildern die Schritte ausgefuhrt werden: A method for determining an optimum focal length of an image pickup system, wherein the steps are performed for each image of a sequence of images: Auswahlen eines interessierenden Bereichs in dem Bild (200); Selecting a region of interest in the image (200); Auswahlen einer interessierenden Farbebene (202); Selecting a color plane of interest (202); Filtern (206-210) von Pixelwerten der interessierenden Farbebene innerhalb des interessierenden Bereichs, so das ein gefiltertes Gebiet erzeugt wird, wobei Kanteninformationen extrahiert werden, wobei die Kanteninformationen fur die Bestimmung nutzlich sind, ob sich das Bildaufnahmesystem im Fokus befindet; Filtering (206-210) of pixel values ​​of the interest color plane within the region of interest, so that a filtered field is generated, edge information is extracted, the edge information useful for determining whether the image capturing system is in focus; Bestimmen (212) eines mittleren Absolutwerts des gefilterten Gebiets; Determining (212) a mean absolute value of the filtered area; Bestimmen (112; 124), ob der mittlere Absolutwert fur das gefilterte Gebiet groser als ein Prozentsatz des grosten zuvor berechneten mittleren Absolutwerts eines anderen Bildes ist; Determining (112; 124) whether the mean absolute value for the filtered region is greater than a percentage of the largest previously calculated mean absolute value of another image; Einstellen (108, 120) einer optimalen Brennweite auf die Brennweite, bei welcher das Bild aufgenommen wurde, sofern (104-JA) der mittlere Absolutwert fur das gefilterte Gebiet groser als der groste zuvor berechnete mittlere Absolutwert ist; Setting (108, 120) an optimal focal length to the focal length at which the picture was taken, provided that (104-YES), the mean absolute value is larger for the filtered area than the largest previously calculated average absolute value; und and Ausgeben (126) der optimalen Brennweite, wenn... Outputting (126) the optimum focal length if ...

Verfahren und Einrichtung zum automatischen Fokussieren in einem Bildaufnahmesystem unter Verwendung symmetrischer FIR-Filter Method and apparatus for automatically focusing in an image pickup system using symmetric FIR filters

In content-based video analysis, scene clustering is an important step toward automated understanding of video semantics, identification of video events, and indexing and retrieval of relevant video contents. Many methods have been proposed to cluster video shots into scenes by using conventional k-means clustering and hierarchical clustering methods. However, "noise" shots analysis has not been fully investigated and incorporated in the clustering procedure. In this paper, we propose a Gaussian mixture model based clustering method incorporating noise analysis. The proposed method can identify noise shots and predict the scene types of new coming shots with satisfactory results.

Model-based video scene clustering with noise analysis

We propose in this paper a doubly weighted sub- space learning approach for face representation and recognition. Motivated by the fact that some face samples and parts are more effectual in characterizing and recognizing faces, we construct two weighting matrices based on pairwise similarity of face samples within a same class and discriminant score of each pixel within a face sample to duly emphasize both the between-sample and within-sample features. We then incorporate these two weighting matrices into three popular subspace learning methods, namely principal component analysis, linear discriminant analysis, and nonnegative matrix factorization, to obtain the discriminative features of faces for recognition. Moreover, the proposed doubly weighted technique can be readily extended to other newly pro- posed subspace learning algorithms to improve their performance. Experimental results show that the proposed approach can ef- fectively enhance the discriminant power of the extracted face features and outperform existing, nonweighted subspace learning algorithms. The performance gain is even more apparent for cases with imbalanced training samples.

Yap-Peng Tan

Papers

Enhancing incremental learning/recognition via efficient neighborhood estimation

Crowd counting from single images using recursive multi-pathway zooming and foreground enhancement

Verfahren und Einrichtung zum automatischen Fokussieren in einem Bildaufnahmesystem unter Verwendung symmetrischer FIR-Filter Method and apparatus for automatically focusing in an image pickup system using symmetric FIR filters

Model-based video scene clustering with noise analysis

A Doubly Weighted Approach for Appearance-Based