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

This paper contributes a new high quality dataset for person re-identification, named "Market-1501". Generally, current datasets: 1) are limited in scale, 2) consist of hand-drawn bboxes, which are unavailable under realistic settings, 3) have only one ground truth and one query image for each identity (close environment). To tackle these problems, the proposed Market-1501 dataset is featured in three aspects. First, it contains over 32,000 annotated bboxes, plus a distractor set of over 500K images, making it the largest person re-id dataset to date. Second, images in Market-1501 dataset are produced using the Deformable Part Model (DPM) as pedestrian detector. Third, our dataset is collected in an open system, where each identity has multiple images under each camera. As a minor contribution, inspired by recent advances in large-scale image search, this paper proposes an unsupervised Bag-of-Words descriptor. We view person re-identification as a special task of image search. In experiment, we show that the proposed descriptor yields competitive accuracy on VIPeR, CUHK03, and Market-1501 datasets, and is scalable on the large-scale 500k dataset.

/pdf/scalable-person-re-identification-a-benchmark-iiee63lja2.pdf

Scalable Person Re-identification: A Benchmark

The author's preface gives an outline: "This book is about weakconvergence methods in metric spaces, with applications sufficient to show their power and utility. The Introduction motivates the definitions and indicates how the theory will yield solutions to problems arising outside it. Chapter 1 sets out the basic general theorems, which are then specialized in Chapter 2 to the space C[0, l ] of continuous functions on the unit interval and in Chapter 3 to the space D [0, 1 ] of functions with discontinuities of the first kind. The results of the first three chapters are used in Chapter 4 to derive a variety of limit theorems for dependent sequences of random variables. " The book develops and expands on Donsker's 1951 and 1952 papers on the invariance principle and empirical distributions. The basic random variables remain real-valued although, of course, measures on C[0, l ] and D[0, l ] are vitally used. Within this framework, there are various possibilities for a different and apparently better treatment of the material. More of the general theory of weak convergence of probabilities on separable metric spaces would be useful. Metrizability of the convergence is not brought up until late in the Appendix. The close relation of the Prokhorov metric and a metric for convergence in probability is (hence) not mentioned (see V. Strassen, Ann. Math. Statist. 36 (1965), 423-439; the reviewer, ibid. 39 (1968), 1563-1572). This relation would illuminate and organize such results as Theorems 4.1, 4.2 and 4.4 which give isolated, ad hoc connections between weak convergence of measures and nearness in probability. In the middle of p. 16, it should be noted that C*(S) consists of signed measures which need only be finitely additive if 5 is not compact. On p. 239, where the author twice speaks of separable subsets having nonmeasurable cardinal, he means "discrete" rather than "separable." Theorem 1.4 is Ulam's theorem that a Borel probability on a complete separable metric space is tight. Theorem 1 of Appendix 3 weakens completeness to topological completeness. After mentioning that probabilities on the rationals are tight, the author says it is an

Convergence of probability measures

Recent advances in convolutional neural networks

The PASCAL Visual Object Classes Challenge

Face alignment is an essential preprocessing stage for most face-related visual tasks and has been widely studied. The performance of face alignment is boosted because of the rising and development of deep learning. While achieving a great success, existing face alignment methods overlooked a fact that different facial keypoints have different patterns and should be treated differently. For example, facial key-points that fall on facial contour are more likely to be misaligned than their peers that fall on five senses (eyes, nose and mouth). In this work, we propose a cascaded convolutional neural network (ConvNet) for robust face alignment. The network consists of multiple stages and refines predictions of the facial landmarks along the stages. Each stage of the network embeds Squeeze and Excitation (SE) units and residual attention unit into a deep ConvNet. The embedding of SE units and attention mechanism enables the network to have a global receptive field and locate different landmarks adaptively. We also improve the cascading way how stages are linked. Experiments reveal that, our method decreases the alignment error and achieves the state-of-the-art performance on 300 Faces In-the-Wild Challenging (300-W) dataset.

Cascaded Deep Convolutional Neural Network for Robust Face Alignment

3D facial extraction from volume data is very helpful in virtual plastic surgery. Although the traditional Marching Cubes algorithm (MC) can be used for this purpose, it could not separate the facial surface from other tissue surfaces. This weakness greatly limited the accuracy of the facial model and its application in plastic surgery. In this paper a volume graph model is proposed, in which the facial surface extraction is formulated as a min-cut problem and can be solved by existing graph cut algorithm. Based on this model, irrelevant tissue surfaces are effectively excluded and a more accurate 3D virtual face can be built for plastic surgery.

Volume Graph Model for 3D Facial Surface Extraction

In this paper, we aim to address the cell phase identification problem, and two important aspects, the feature extraction methods and the classifier design, are discussed. In our study, we first propose extracting high frequency information of different orientations using Steerable filters. Next, we employ a multi-layer neural network using the back-propagation algorithm to replace K-Nearest Neighbor (KNN) classifier which has been implemented in the Cellular Image Quantitator (CELLIQ) system [3]. Experimental results provide a comparison between the proposed steerable filter features and existing regular features which have been used in published papers [3, 5]. From the comparison, it can be concluded that Steerable filter features can effectively represent the cells in different phases and improve the classification accuracy. Neural network also has a better performance than KNN currently deployed in CELLIQ system [3].

Identification of cell-cycle phases using neural network and steerable filter features

In this paper, we present a new object tracking scheme. Different from conventional tracking process, the proposed method is combined with video encoding and can be easily embedded into video encoding system. The only information the tracker need is Summed Absolute Difference (SAD) generated by motion estimation during encoding. These SADs are used as soft votes in a fast Hough-Transform (HT) algorithm in parameter space of translation. This can be much faster than conventional tracking algorithm such as particle filter and more accurate than recent compress-domain approaches. Taking the advantage of HT, this approach is also robust to unstable camera, background moving and partial occlusion. The parameter space can be also extended to affine transform space with those soft votes to track scale change and partially rotation moving. We solve the latter multi-parameter problem by Linear Programming (LP) algorithm. The tracking result can also direct encoding behavior: detecting Region of Interest (ROI), adjusting QP, and etc.

Houqiang Li

Papers

Cascaded Deep Convolutional Neural Network for Robust Face Alignment

Volume Graph Model for 3D Facial Surface Extraction

Identification of cell-cycle phases using neural network and steerable filter features

A novel tracking-by-encoding scheme based on linear programming matching

CLIP-ViP: Adapting Pre-trained Image-Text Model to Video-Language Alignment