“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

We propose the Orientation Estimation Network (OEN) to predict the dominant orientation of the outdoor images and rotate the images to a canonical orientation which is visually comfortable. The OEN outputs the sine and cosine of the angle which are continuous in contrast to the angle. We collect a new dataset called the Outdoor Images dataset for this task. This dataset contains various kinds of outdoor images, such as buildings, landscape, persons and boats, and the orientation information has been manually annotated. We choose AlexNet, MobileNet and VGGNet to extract image features and regress to the angle of images. In our task, MobileNet achieves high performance while needing less resource, and can be applied to mobile and embedded vision applications. We compare our method with the hand-crafted methods on our dataset. In the evaluation, our learning based method significantly outperforms the hand-crafted methods in the task of outdoor images orientation estimation.

Orientation Estimation Network

In cooperative multi-agent tasks, a team of agents jointly interact with an environment by taking actions, receiving a team reward and observing the next state. During the interactions, the uncertainty of environment and reward will inevitably induce stochasticity in the long-term returns and the randomness can be exacerbated with the increasing number of agents. However, such randomness is ignored by most of the existing value-based multi-agent reinforcement learning (MARL) methods, which only model the expectation of Q-value for both individual agents and the team. Compared to using the expectations of the long-term returns, it is preferable to directly model the stochasticity by estimating the returns through distributions. With this motivation, this work proposes a novel value-based MARL framework from a distributional perspective, i.e. , parameterizing value function via Mixture of Categorical distributions for MARL. Speciﬁcally, we model both individual Q-values and global Q-value with categorical distribution. To integrate categorical distributions, we deﬁne ﬁve basic operations on the distribution, which allow the generalization of expected value function factorization methods ( e.g. , VDN and QMIX) to their MCMARL variants. We further prove that our MCMARL framework satisﬁes Distributional-Individual-Global-Max (DIGM) principle with respect to the expectation of distribution, which guarantees the consistency between joint and individual greedy action selections in the global Q-value and individual Q-values. Empirically, we evaluate MCMARL on both a stochastic matrix game and a challenging set of StarCraft II micromanagement tasks, showing the efﬁcacy of our framework.

MCMARL: Parameterizing Value Function via Mixture of Categorical Distributions for Multi-Agent Reinforcement Learning

The state-of-the-art compression method for Light Detection And Ranging (LiDAR) point clouds is the geometry-based point cloud compression (G-PCC) standard developed by Moving Pictures Experts Group immersive media working group (MPEG-I). However, there are currently no rate control algorithms designed specifically for Geometry-based LiDAR point cloud compression (G-LPCC). In this paper, we propose the first frame-level rate control algorithm for G-LPCC. We mainly have the following contributions in our proposed rate control algorithm. First, we model the rate-distortion (R-D) relationship for both the geometry and attribute. As the geometry bitrate is mainly determined by the frame-level geometry quantizer <formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex>$Q_G$</tex></formula> , we propose a relationship between the geometry bitrate and <formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex>$Q_G$</tex></formula> . In addition, as the attribute bitrate can be influenced by both the attribute quantizer <formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex>$Q_A$</tex></formula> and <formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex>$Q_G$</tex></formula> , we build a relationship among the attribute bitrate, <formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex>$Q_G$</tex></formula> , and <formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex>$Q_A$</tex></formula> . Second, we propose a bit allocation algorithm between the geometry and attribute based on the R-D modeling. The <formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex>$Q_G$</tex></formula> and <formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex>$Q_A$</tex></formula> are modeled into a proper relationship to obtain geometry and attribute bits to achieve good R-D performance. Third, we propose using the point density of LiDAR point clouds to estimate the geometry model parameters. The point density is calculated using the average distance between each point and its nearest neighbor after excluding some noisy points. The proposed rate control algorithm is implemented in the G-PCC reference software. The experimental results show that the proposed rate control algorithm can control the bitrate accurately with satisfactory R-D performance. 

Frame-level Rate Control for Geometry-based LiDAR Point Cloud Compression

Discrete Cosine Transform (DCT) has been the commonly used transform for a few decades in image/video coding. However, DCT does not work well on the blocks having anisotropic correlations. In this paper, based on the adaptive dictionary, we propose a new online transform scheme using Orthogonal Matching Pursuit (OMP) for High Efficiency Video Coding (HEVC). For a coding block, we construct its dictionary by exploiting non-local correlations from the reconstructed regions. The OMP algorithm is implemented to obtain the sparse transform coefficients. Experimental results show that the BD-rate savings of the proposed scheme for the sequences with strong edges can be up to 19.9%.

OMP-based transform for inter coding in HEVC

Multiuser video transmission, where the server transmits videos to multiple users that request different contents at the same time, becomes more and more popular with the development of wireless communication technology. One key problem in multiuser video transmission is how to optimally allocate the system resources such as transmission power and channels to multiple users to achieve the best system performance. To resolve the problem, in this paper, we propose an uncoded multiuser video streaming system, which exploits diversities of video contents and channel conditions of multiple users. We first solve the channel assignment problem with known power allocation by taking into account the intra-block energy diffusion and inter-block energy aliasing. Then, with the obtained channel assignment, we derive a closed-form solution to the multiuser power allocation optimization problem. Finally, we conduct simulations to evaluate the proposed uncoded multiuser video streaming system by comparing with three other approaches, and simulation results show that the proposed method can achieve the best system performance.

Houqiang Li

Papers

Orientation Estimation Network

MCMARL: Parameterizing Value Function via Mixture of Categorical Distributions for Multi-Agent Reinforcement Learning

Frame-level Rate Control for Geometry-based LiDAR Point Cloud Compression

OMP-based transform for inter coding in HEVC

Exploiting Channel Assignment and Power Allocation for Linear Uncoded Multiuser Video Streaming