“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

Approximate Nearest Neighbour (ANN) search is an important research topic in multimedia and computer vision fields. In this paper, we propose a new deep supervised quantization method by Self-Organizing Map (SOM) to address this problem. Our method integrates the Convolutional Neural Networks (CNN) and Self-Organizing Map into a unified deep architecture. The overall training objective includes supervised quantization loss and classification loss. With the supervised quantization loss, we minimize the differences on the maps between similar image pairs, and maximize the differences on the maps between dissimilar image pairs. By optimization, the deep architecture can simultaneously extract deep features and quantize the features into the suitable nodes in the Self-Organizing Map. The experiments on several public standard datasets prove the superiority of our approach over the existing ANN search methods. Besides, as a byproduct, our deep architecture can be directly applied to classification task and visualization with little modification, and promising performances are demonstrated on these tasks in the experiments.

Deep Supervised Quantization by Self-Organizing Map

Unsupervised domain adaptation (UDA) is an important topic in the computer vision community. The key difficulty lies in defining a common property between the source and target domains so that the source-domain features can align with the target-domain semantics. In this paper, we present a simple and effective mechanism that regularizes cross-domain representation learning with a domain-agnostic prior (DAP) that constrains the features extracted from source and target domains to align with a domain-agnostic space. In practice, this is easily implemented as an extra loss term that requires a little extra costs. In the standard evaluation protocol of transferring synthesized data to real data, we validate the effectiveness of different types of DAP, especially that borrowed from a text embedding model that shows favorable performance beyond the state-of-the-art UDA approaches in terms of segmentation accuracy. Our research reveals that UDA benefits much from better proxies, possibly from other data modalities.

Domain-Agnostic Prior for Transfer Semantic Segmentation

In this paper, we focus on the composed query image retrieval task, namely retrieving the target images that are similar to a composed query, in which a modification text is combined with a query image to describe a user's accurate search intention. Previous methods usually focus on learning the joint image-text representations, but rarely consider the intrinsic relationship among the query image, the target image and the modification text. To address this problem, we propose a new cross-modal joint prediction and alignment framework for composed query image retrieval. In our framework, the modification text is regarded as an implicit transformation between the query image and the target image. Motivated by that, not only the combination of the query image and modification text should be similar to the target image, but also the modification text should be predicted according to the query image and the target image. We devote to aligning this relationship by a novel Joint Prediction Module (JPM). Our proposed framework can seamlessly incorporate the JPM into the existing methods to effectively improve the discrimination and robustness of visual and textual representations. The experiments on three public datasets demonstrate the effectiveness of our proposed framework, proving that our proposed JPM can be simply incorporated with the existing methods while effectively improving the performance.

Cross-modal Joint Prediction and Alignment for Composed Query Image Retrieval

Interactive selection of the desired viewpoint is one important feature in multiview video streaming. When receivers differ in the number of simultaneously displayed views, it is challenging to optimize the multiview coding structure particularly when it comes to the use of inter-view prediction and anchor picture frequency. This paper presents a coding and transmission scheme for streaming to clients of different display capabilities. The scheme saves transmission bandwidth by sending only those views that are displayed in a receiver. Furthermore, the scheme enables viewpoint switching through inter-view-predicted redundant pictures representing different sets of views being switched from and switched to. When switching happens at a switch point, an appropriate redundant picture is adaptively chosen based on which views were transmitted before and will be transmitted after the switch point. Experimental results show that the proposed scheme improves the rate-distortion (RD) performance compared to simple anchor picture insertion.

Inter-view-predicted redundant pictures for viewpoint switching in multiview video streaming

In theory, a Wyner-Ziv video codec should achieve the same efficiency as a joint encoding and decoding one. However, existing approaches still exhibit significant gaps. One main reason is the lack of the complete correlation exploitation between source and side information. In this paper, we propose a transform domain classification based Wyner-Ziv video codec, aiming at exploiting additional video statistics. In this proposed new scheme, the encoder exploits additional statistics by performing block classification to differentiate low motion blocks from high motion ones. In general, low motion blocks represent highly correlated regions. Such information is useful when the decoder performs motion-compensated interpolation to obtain better side information, thus improving the performance of Wyner-Ziv coding. Experimental results show that we are indeed able to achieve better rate-distortion performance compared to the existing Wyner-Ziv video codecs at the expense of some additional complexity in frame store and comparisons at the encoder.

Houqiang Li

Papers

Deep Supervised Quantization by Self-Organizing Map

Domain-Agnostic Prior for Transfer Semantic Segmentation

Cross-modal Joint Prediction and Alignment for Composed Query Image Retrieval

Inter-view-predicted redundant pictures for viewpoint switching in multiview video streaming

A Transform Domain Classification Based Wyner-Ziv Video Codec