“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

An increasing number of deployed surveillance cameras raise a huge demand for higher efficiency video coding scheme, and the emerging background reference based video coding methods with High Efficiency Video Coding (HEVC) have achieved a large increase of coding efficiency on surveillance videos. However, the high encoding complexity of HEVC causes troubles for these methods to be adopted in practice, especially in real-time coding scenarios. Among all the factors resulting in the increase of encoding complexity, mode decision and motion estimation are both critical reasons. Therefore, a fast algorithm based on a block-level background generation method is proposed to address this problem for surveillance video. With the help of fast detection of background coding units, the Merge mode is early decided, some prediction modes at specific depths that have the least probabilities are skipped using early termination during rate-distortion optimization, and unnecessary motion estimation is also avoided. Thanks to the full utilization of the static camera premise, the proposed fast algorithm achieves 77.0% reduction of encoding time, while only incurs 1.0% performance loss that is negligible. More experimental results also verify that the proposed algorithm outperforms the state-of-the-art schemes.

Fast encoding of surveillance videos based on HEVC

Affinity, which represents whether two pixels belong to a same instance, is an equivalent representation to the instance segmentation labels. Conventional works do not make an explicit exploration on the affinity. In this article, we present two instance segmentation schemes based on pixel affinity information and show the effectiveness of affinity in both aspects. For proposal-free method, we predict pixel affinity for each image and then propose a simple yet effective graph merge algorithm to cluster pixels into instances. It shows that the affinity is powerful as an instance-relevant information to guide the clustering procedure in proposal-free instance segmentation. For proposal-based methods, we extend conventional framework with affinity head and introduce affinity as attached supervision in training phase. Without any additional inference cost, we can improve the performance of existing proposal-based instance segmentation methods, which shows that the affinity can also be applied as an auxiliary loss and training with such extra loss is beneficial to the training progress. Experimental results show that our schemes achieve comparable performance to other state-of-the-art instance segmentation methods. With Cityscapes training data, the proposed proposal-free method achieves 28.8 AP and the proposal-based method gets 27.2 AP both on test sets.

Affinity Derivation for Accurate Instance Segmentation

This paper investigates joint source-channel secrecy for Gaussian broadcast communication in Shannon cipher system. We use a recently proposed secrecy measure, list secrecy, to measure secrecy, in which an eavesdropper is allowed to produce a list of reconstruction sequences and the secrecy is measured by the minimum distortion over the entire list. For achievability part, we propose a novel joint source-channel secrecy scheme, which cascades the traditional linear joint source-channel coding (analog coding) with a random orthogonal transform. For this scheme, we characterize the set of achievable tuples (secret key rate, list rate, eavesdropper distortion, distortions of all legitimate users). Besides, one of existing schemes, sign-change based scheme, is analyzed, and by comparison the proposed scheme outperforms this sign-change based scheme. For the converse part, we provide a necessary condition on the achievability of any tuple, and comparing this converse with the achievability result of the proposed scheme shows that the proposed scheme is optimal under some certain conditions. Besides, we also extend the proposed scheme and the corresponding achievability result to vector Gaussian communication scenario. No matter for scalar or vector Gaussian communication case, the codebook in the proposed scheme consists of a sequence of random matrices. This is very different from the traditional construction of codebook in information theory that usually consists of a sequence of random samples.

Joint Source-Channel Secrecy Using Analog Coding: Towards Secure Source Broadcast.

Depth maps, an essential part in the new generation of 3D video coding, allow rendering of arbitrary viewpoints of a video scene. Depth maps are characterized by sharp object boundaries, which significantly affect the rendering quality and account for the most bitrate for depth map coding. This paper proposes a novel intra coding method for depth maps based on a two-step adaptive boundary location process. By extracting a series of sub-blocks along a depth boundary and refining the boundary within sub-blocks, accurate predictions for blocks with arbitrary edge shapes can be realized. Experimental results show that the proposed scheme achieves bitrate reductions of up to 28% and 13% on average for seven test sequences of MPEG 3DV compared to original intra coding of H.264/AVC considering the same quality of synthesized views. Besides, subjective quality of virtual views is improved owning to well preserved boundary information.

Intra coding for depth maps using adaptive boundary location

Low-light video enhancement (LLVE) is an important yet challenging task with many applications such as photographing and autonomous driving. Unlike single image low-light enhancement, most LLVE methods utilize temporal information from adjacent frames to restore the color and remove the noise of the target frame. However, these algorithms, based on the framework of multi-frame alignment and enhancement, may produce multi-frame fusion artifacts when encountering extreme low light or fast motion. In this paper, inspired by the low latency and high dynamic range of events, we use synthetic events from multiple frames to guide the enhancement and restoration of low-light videos. Our method contains three stages: 1) event synthesis and enhancement, 2) event and image fusion, and 3) low-light enhancement. In this framework, we design two novel modules (event-image fusion transform and event-guided dual branch) for the second and third stages, respectively. Extensive experiments show that our method outperforms existing low-light video or single image enhancement approaches on both synthetic and real LLVE datasets. Our code will be available at https://gitee.com/mindspore/models/tree/master/research/cv/LLVE-SEG.

Houqiang Li

Papers

Fast encoding of surveillance videos based on HEVC

Affinity Derivation for Accurate Instance Segmentation

Joint Source-Channel Secrecy Using Analog Coding: Towards Secure Source Broadcast.

Intra coding for depth maps using adaptive boundary location

Low-Light Video Enhancement with Synthetic Event Guidance