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

Обнаружение транспортных средств на изображениях загородных шоссе на основе метода Single shot multibox Detector

Survey on semantic segmentation using deep learning techniques

With the rapid development of smart manufacturing, data-driven fault diagnosis has attracted increasing attentions. As one of the most popular methods applied in fault diagnosis, deep learning (DL) has achieved remarkable results. However, due to the fact that the volume of labeled samples is small in fault diagnosis, the depths of DL models for fault diagnosis are shallow compared with convolutional neural network in other areas (including ImageNet), which limits their final prediction accuracies. In this research, a new TCNN(ResNet-50) with the depth of 51 convolutional layers is proposed for fault diagnosis. By combining with transfer learning, TCNN(ResNet-50) applies ResNet-50 trained on ImageNet as feature extractor for fault diagnosis. Firstly, a signal-to-image method is developed to convert time-domain fault signals to RGB images format as the input datatype of ResNet-50. Then, a new structure of TCNN(ResNet-50) is proposed. Finally, the proposed TCNN(ResNet-50) has been tested on three datasets, including bearing damage dataset provided by KAT datacenter, motor bearing dataset provided by Case Western Reserve University (CWRU) and self-priming centrifugal pump dataset. It achieved state-of-the-art results. The prediction accuracies of TCNN(ResNet-50) are as high as 98.95% ± 0.0074, 99.99% ± 0 and 99.20% ± 0, which demonstrates that TCNN(ResNet-50) outperforms other DL models and traditional methods.

A transfer convolutional neural network for fault diagnosis based on ResNet-50

LSTM with sentence representations for document-level sentiment classification

CNN-based encoder-decoder networks for salient object detection: A comprehensive review and recent advances

This paper presents a character-level seque-nce-to-sequence learning method, RNNembed. This method allows the system to read raw characters, instead of words generated by preprocessing steps, into a pure single neural network model under an end-to-end framework. Specifically, we embed a recurrent neural network into an encoder–decoder framework and generate character-level sequence representation as input. The dimension of input feature space can be significantly reduced as well as avoiding the need to handle unknown or rare words in sequences. In the language model, we improve the basic structure of a gated recurrent unit by adding an output gate, which is used for filtering out unimportant information involved in the attention scheme of the alignment model. Our proposed method was examined in a large-scale dataset on an English-to-Chinese translation task. Experimental results demonstrate that the proposed approach achieves a translation performance comparable, or close, to conventional word-based and phrase-based systems.

Understanding Subtitles by Character-Level Sequence-to-Sequence Learning

This paper presents a novel learning-based framework for video content-based advertising, DeepLink, which aims at linking Sitcom-stars and online shops with clothing retrieval by using state-of-the-art deep convolutional neural networks (CNNs). Specifically, several deep CNN models are adopted for composing multiple sub-modules in DeepLink, including human-body detection, human pose selection, face verification, clothing detection and retrieval from advertisements (ads) pool that is constructed by clothing images crawled from real-world online shops. For clothing detection and retrieval from ad-images, we firstly transfer the state-of-the-art deep CNN models to our data domain, and then train corresponding models based on our constructed large-scale clothes datasets. Extensive experimental results demonstrate the feasibility and efficacy of our proposed clothing-based video advertising system.

Yuzhu Ji

Papers

CNN-based encoder-decoder networks for salient object detection: A comprehensive review and recent advances

Understanding Subtitles by Character-Level Sequence-to-Sequence Learning

Sitcom-star-based clothing retrieval for video advertising: a deep learning framework

Salient object detection via multi-scale attention CNN

Toward AI fashion design: An Attribute-GAN model for clothing match