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

In this work, we revisit atrous convolution, a powerful tool to explicitly adjust filter's field-of-view as well as control the resolution of feature responses computed by Deep Convolutional Neural Networks, in the application of semantic image segmentation. To handle the problem of segmenting objects at multiple scales, we design modules which employ atrous convolution in cascade or in parallel to capture multi-scale context by adopting multiple atrous rates. Furthermore, we propose to augment our previously proposed Atrous Spatial Pyramid Pooling module, which probes convolutional features at multiple scales, with image-level features encoding global context and further boost performance. We also elaborate on implementation details and share our experience on training our system. The proposed `DeepLabv3' system significantly improves over our previous DeepLab versions without DenseCRF post-processing and attains comparable performance with other state-of-art models on the PASCAL VOC 2012 semantic image segmentation benchmark.

Rethinking Atrous Convolution for Semantic Image Segmentation

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

The PASCAL Visual Object Classes Challenge

Semantic segmentation requires both rich spatial information and sizeable receptive field. However, modern approaches usually compromise spatial resolution to achieve real-time inference speed, which leads to poor performance. In this paper, we address this dilemma with a novel Bilateral Segmentation Network (BiSeNet). We first design a Spatial Path with a small stride to preserve the spatial information and generate high-resolution features. Meanwhile, a Context Path with a fast downsampling strategy is employed to obtain sufficient receptive field. On top of the two paths, we introduce a new Feature Fusion Module to combine features efficiently. The proposed architecture makes a right balance between the speed and segmentation performance on Cityscapes, CamVid, and COCO-Stuff datasets. Specifically, for a 2048 \(\times \) 1024 input, we achieve 68.4% Mean IOU on the Cityscapes test dataset with speed of 105 FPS on one NVIDIA Titan XP card, which is significantly faster than the existing methods with comparable performance.

/pdf/bisenet-bilateral-segmentation-network-for-real-time-2pc7rh0tw1.pdf

BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation

Pseudo Relevance Feedback (PRF) has shown effective performance in information retrieval, but it has seldom been applied in the area of high level feature detection (HLF). In this paper, we explicitly propose to introduce PRF into HLF. Our contributions mainly lie in two-fold: (1) proposing three novel PRF approaches to extract pseudo positive samples, i.e., Nearest-Neighbor (NN) based PRF, Score-Evaluation (SE) based PRF and Multi-Classifier Decision (MCD) based PRF; (2) utilizing incremental learning to reduce the re-training time. We evaluate our approaches on the benchmark of TRECVID2008. Reported results have shown that MCD based approach outperforms the other two and obtain an excellent gain in average precision with respect to the baseline without PRF.

Pseudo relevance feedback with incremental learning for high level feature detection

Recently, most of pioneering works based on supervised learning have been proposed for image captioning task. These approaches are heavily dependent on labeled training data. Through careful observation, we note that these approaches suffer from the problem of class imbalance (CIB) which can lead to performance degradation and limit the diversity of generated sentences. In this paper, to address this problem, we propose a pipeline based on an adaptive balancing loss (ABL) for image captioning which re-weighs loss of each category dynamically over the training process. Our proposed method can improve the accuracy and increase the diversity of generated descriptions through adaptively reducing losses of well-classified and frequent categories and increasing losses of under-classified and infrequent categories. We conduct experiments on the well-known MS CO-CO caption dataset to evaluate the performance of the proposed method. The results show that our approach achieves competitive performance compared to the state-of-the-art methods and can generate more accurate and diverse captions.

Image Captioning Based on Adaptive Balancing Loss

Usually learning dynamical systems by data-driven methods requires large amount of training data, which may be time consuming and expensive. Active learning, which aims at choosing the most informative samples to make learning more efficient is a promising way to solve this issue. However, actively learning dynamical systems is difficult since it is not possible to arbitrarily sample the state-action space under the constraint of system dynamics. The state-of-the-art methods for actively learning dynamical systems iteratively search for an informative state-action pair by maximizing the differential entropy of the predictive distribution, or iteratively search for a long informative trajectory by maximizing the sum of predictive variances along the trajectory. These methods suffer from low efficiency or high computational complexity and memory demand. To solve these problems, this paper proposes novel and more sample-efficient methods which combine global and local explorations. As the global exploration, the agent searches for a relatively short informative trajectory in the whole state-action space of the dynamical system. Then, as the local exploration, an action sequence is optimized to drive the system’s state towards the initial state of the local informative trajectory found by the global exploration and the agent explores this local informative trajectory. Compared to the state-of-the-art methods, the proposed methods are capable of exploring the state-action space more efficiently, and have much lower computational complexity and memory demand. With the state-of-the-art methods as baselines, the advantages of the proposed methods are verified via various numerical examples.

Actively Learning Gaussian Process Dynamical Systems Through Global and Local Explorations

Electric Vehicles (EVs) have become a popular alternative to Internal Combustion Engine Vehicles (ICEVs) due to its ability to be replenished by renewable sources of energy. Despite its advantages, EVs still possess some major disadvantages, which have reduced the take up rate of EVs by consumers. This project is therefore proposed to provide a user-centric solution to evaluate and to encourage the use of EVs In particular, the project aims to establish a remote telemetry and diagnostics System for EVs. In this project, a database system has been developed, which is used with a compatible data acquisition system. The developed database system is able to store the relevant and useful information for the EV users, and they may be used by engineers and researches to conduct data mining for research and development purposes. In addition, smart phone application has been developed for the iPhone to provide EV users with real-time critical information that will alleviate the anxieties mentioned above. Furthermore, a tablet application has also been developed to give technicians access to vital information regarding their clients' EVs, and also to past information, which is useful when diagnosing a problem.

Development of a remote telemetry and diagnostic system for electric vehicles and electric vehicle supply equipment

We propose a novel method for extracting text feature from the automatic speech recognition (ASR) results in semantic video retrieval We combine HowNet-rule-based knowledge with statistic information to build special concept lexicons, which can rapidly narrow the vocabulary and improve the retrieval precision Furthermore, we use the term precision (TP) weighting method to analyze ASR texts This weighting method is sensitive to the sparse but important terms in the relevant documents Experiments show that the proposed method is effective for semantic video retrieval

Sheng Tang

Papers

Pseudo relevance feedback with incremental learning for high level feature detection

Image Captioning Based on Adaptive Balancing Loss

Actively Learning Gaussian Process Dynamical Systems Through Global and Local Explorations

Development of a remote telemetry and diagnostic system for electric vehicles and electric vehicle supply equipment

A novel method for spoken text feature extraction in semantic video retrieval