Home /
Research
Showing 811 - 816 / 904
Pixel-wise Dense Detector for Image Inpainting
RuisongZhang, WeizeQuan, BaoyuanWu....
Published date-11/04/2020
ImageInpainting
Recent GAN-based image inpainting approaches adopt an average strategy to discriminate the generated image and output a scalar, which inevitably lose the position information of visual artifacts. Moreover, the adversarial …
DeepReg: a deep learning toolkit for medical image registration
YunguanFu, NinaMontañaBrown, ShaheerU.Saeed....
Published date-11/04/2020
ImageRegistration, MedicalImageRegistration
DeepReg (https://github.com/DeepRegNet/DeepReg) is a community-supported open-source toolkit for research and education in medical image registration using deep learning.
A spatial hue similarity measure for assessment of colourisation
SeánMullery, PaulF.Whelan....
Published date-11/03/2020
SSIM
Automatic colourisation of grey-scale images is an ill-posed multi-modal problem. Where full-reference images exist, objective performance measures rely on pixel-difference techniques such as MSE and PSNR. These measures penalise any …
CMT in TREC-COVID Round 2: Mitigating the Generalization Gaps from Web to Special Domain Search
ChenyanXiong, ZhenghaoLiu, SiSun....
Published date-11/03/2020
DomainAdaptation, Few-ShotLearning, InformationRetrieval
Neural rankers based on deep pretrained language models (LMs) have been shown to improve many information retrieval benchmarks. However, these methods are affected by their the correlation between pretraining domain …
Semi-Supervised Cleansing of Web Argument Corpora
JonasDorsch, HenningWachsmuth....
Published date-11/03/2020
Debate portals and similar web platforms constitute one of the main text sources in computational argumentation research and its applications. While the corpora built upon these sources are rich of …
VEGA: Towards an End-to-End Configurable AutoML Pipeline
BochaoWang, HangXu, JiajinZhang....
Published date-11/03/2020
AutoML, DataAugmentation, HyperparameterOptimization, ModelCompression, NeuralArchitectureSearch
Automated Machine Learning (AutoML) is an important industrial solution for automatic discovery and deployment of the machine learning models. However, designing an integrated AutoML system faces four great challenges of …