다중혈관 관상동맥 환자에서 y-문합을 이용하여 양쪽 내흉동맥만을 사용한 우회술의 조기 성적

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

Recently, Neural Architecture Search (NAS) has successfully identified neural network architectures that exceed human designed ones on large-scale image classification. In this paper, we study NAS for semantic image segmentation. Existing works often focus on searching the repeatable cell structure, while hand-designing the outer network structure that controls the spatial resolution changes. This choice simplifies the search space, but becomes increasingly problematic for dense image prediction which exhibits a lot more network level architectural variations. Therefore, we propose to search the network level structure in addition to the cell level structure, which forms a hierarchical architecture search space. We present a network level search space that includes many popular designs, and develop a formulation that allows efficient gradient-based architecture search (3 P100 GPU days on Cityscapes images). We demonstrate the effectiveness of the proposed method on the challenging Cityscapes, PASCAL VOC 2012, and ADE20K datasets. Auto-DeepLab, our architecture searched specifically for semantic image segmentation, attains state-of-the-art performance without any ImageNet pretraining.

/pdf/auto-deeplab-hierarchical-neural-architecture-search-for-rsvt67m5s2.pdf

Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation

Person re-identification (Re-ID) aims at retrieving a person of interest across multiple non-overlapping cameras. With the advancement of deep neural networks and increasing demand of intelligent video surveillance, it has gained significantly increased interest in the computer vision community. By dissecting the involved components in developing a person Re-ID system, we categorize it into the closed-world and open-world settings. The widely studied closed-world setting is usually applied under various research-oriented assumptions, and has achieved inspiring success using deep learning techniques on a number of datasets. We first conduct a comprehensive overview with in-depth analysis for closed-world person Re-ID from three different perspectives, including deep feature representation learning, deep metric learning and ranking optimization. With the performance saturation under closed-world setting, the research focus for person Re-ID has recently shifted to the open-world setting, facing more challenging issues. This setting is closer to practical applications under specific scenarios. We summarize the open-world Re-ID in terms of five different aspects. By analyzing the advantages of existing methods, we design a powerful AGW baseline, achieving state-of-the-art or at least comparable performance on twelve datasets for FOUR different Re-ID tasks. Meanwhile, we introduce a new evaluation metric (mINP) for person Re-ID, indicating the cost for finding all the correct matches, which provides an additional criteria to evaluate the Re-ID system for real applications. Finally, some important yet under-investigated open issues are discussed.

Deep Learning for Person Re-identification: A Survey and Outlook

Recent advancements in perception for autonomous driving are driven by deep learning. In order to achieve robust and accurate scene understanding, autonomous vehicles are usually equipped with different sensors (e.g. cameras, LiDARs, Radars), and multiple sensing modalities can be fused to exploit their complementary properties. In this context, many methods have been proposed for deep multi-modal perception problems. However, there is no general guideline for network architecture design, and questions of “what to fuse”, “when to fuse”, and “how to fuse” remain open. This review paper attempts to systematically summarize methodologies and discuss challenges for deep multi-modal object detection and semantic segmentation in autonomous driving. To this end, we first provide an overview of on-board sensors on test vehicles, open datasets, and background information for object detection and semantic segmentation in autonomous driving research. We then summarize the fusion methodologies and discuss challenges and open questions. In the appendix, we provide tables that summarize topics and methods. We also provide an interactive online platform to navigate each reference: https://boschresearch.github.io/multimodalperception/ .

Deep Multi-Modal Object Detection and Semantic Segmentation for Autonomous Driving: Datasets, Methods, and Challenges

Person re-identification (ReID) is a challenging task due to arbitrary human pose variations, background clutters, etc. It has been studied extensively in recent years, but the multifarious local and global features are still not fully exploited by either ignoring the interplay between whole-body images and body-part images or missing in-depth examination of specific body-part images. In this paper, we propose a novel attention-driven multi-branch network that learns robust and discriminative human representation from global whole-body images and local body-part images simultaneously. Within each branch, an intra-attention network is designed to search for informative and discriminative regions within the whole-body or body-part images, where attention is elegantly decomposed into spatial-wise attention and channel-wise attention for effective and efficient learning. In addition, a novel inter-attention module is designed which fuses the output of intra-attention networks adaptively for optimal person ReID. The proposed technique has been evaluated over three widely used datasets CUHK03, Market-1501 and DukeMTMC-ReID, and experiments demonstrate its superior robustness and effectiveness as compared with the state of the arts.

Attention Driven Person Re-identification

In this paper, we propose a fast and effective mode decision (MD) algorithm based on rate distortion optimization (RDO) for AVS high definition video encoder. The fast algorithm is composed of two parts. Firstly, mode preselection based on sum of absolute difference (SAD) is employed to reduce modes for candidate so as to alleviate the dramatic throughout burden. Secondly, we adopt 4-way parallel scanning technique to reduce the cycles of each mode decision based on RDO. Theoretical analysis and experimental results show that the proposed fast algorithm can meet the needs of 720P and 1080P real-time high definition AVS video encoding. Besides, the mode pre-selection algorithm provides a similar performance to the all modes enabled algorithm. And the 4-way parallel technique using negligible extra resources increases the speed of coding bits estimation by 3.4 times than traditional techniques.

http://www.jdl.ac.cn/doc/2010/PCM2010-%20Fast%20Mode%20Decision%20Based%20on%20RDO%20for%20AVS%20High%20Definition%20Video%20Encoder.pdf

Fast mode decision based on RDO for AVS high definition video encoder

In this paper, we propose a hardware architecture of an adaptive multi-resolution motion estimation algorithm (AMMEA) for high definition video encoder to reduce hardware cost. The texture-based search strategies are based on temporal stationarity and spatial homogeneity with Sobel edge operator. The proposed algorithm makes motion estimation more concise. We also propose Sobel edge operator hardware architecture. The four-pixel SAD unit which is the basic processing element (PE) in our proposed architecture is used for SAD calculation and Sobel edge operator computation. The hardware architecture achieves very high data utilization and data throughout. Using our proposed AMMEA with regular data flow, simulation results show that the proposed architecture can significantly reduce the hardware cost with a negligible PSNR loss of 0.03dB compared with the full-search. The design is implemented with SMIC 0.18μm CMOS technology and costs 950K gates count, and it supports the real-time encoding of 1080P@30fps with two reference frames under a clock frequency of 150MHz.

Hardware-oriented adaptive multi-resolution motion estimation algorithm and its VLSI architecture

Image scaling is a fundamental algorithm used in a large range of digital image applications. In this paper, we propose an efficient VLSI architecture for a novel edge-directed linear interpolation algorithm. Our VLSI design is implemented using high level synthesis (HLS) tool, which generates RTL modules from C/C++ functions. HLS provides significantly improved design productivity compared to the traditional RTL-based design flow. So we explored a large design space including several fine-grained and coarse-grained optimizations in the pipeline architecture design. Our architecture is verified in a working system based on Xilinx Kintex-7 FPGA. Experiments show that our design can process UHD (3840*2160) videos at 30fps with moderate resource utilization.

High efficiency VLSI implementation of an edge-directed video up-scaler using high level synthesis

Blind watermarking provides powerful evidence for copyright protection, image authentication, and tampering identification.However, it remains a challenge to design a watermarking model with high imperceptibility and robustness against strong noise attacks. To resolve this issue, we present a framework Combining the Invertible and Non-invertible (CIN) mechanisms. The CIN is composed of the invertible part to achieve high imperceptibility and the non-invertible part to strengthen the robustness against strong noise attacks. For the invertible part, we develop a diffusion and extraction module (DEM) and a fusion and split module (FSM) to embed and extract watermarks symmetrically in an invertible way. For the non-invertible part, we introduce a non-invertible attention-based module (NIAM) and the noise-specific selection module (NSM) to solve the asymmetric extraction under a strong noise attack. Extensive experiments demonstrate that our framework outperforms the current state-of-the-art methods of imperceptibility and robustness significantly. Our framework can achieve an average of 99.99% accuracy and 67.66 dB PSNR under noise-free conditions, while 96.64% and 39.28 dB combined strong noise attacks. The code will be available in https://github.com/RM1110/CIN.

/pdf/towards-blind-watermarking-combining-invertible-and-non-2yxuik7y.pdf

Huizhu Jia

Papers

Attention Driven Person Re-identification

Fast mode decision based on RDO for AVS high definition video encoder

Hardware-oriented adaptive multi-resolution motion estimation algorithm and its VLSI architecture

High efficiency VLSI implementation of an edge-directed video up-scaler using high level synthesis

Towards Blind Watermarking: Combining Invertible and Non-invertible Mechanisms