To bridge the performance gap, we propose a novel object-level self-supervised learning method, called Contrastive learning with Downstream background invariance (CoDo).
With this method, Yuan 1. 0, the current largest singleton language model with 245B parameters, achieves excellent performance on thousands GPUs during training, and the state-of-the-art results on NLP tasks.
This paper proposes a set of testing strategies for testing machine learning applications in the framework of the datamorphism testing methodology.
It is still an open question to leverage various types of information under the BERT framework.
We conduct our experiments on the proposed real-world interior layout dataset that contains $191208$ designs from the professional designers.
In this paper, we propose a multiple-domain model for producing a custom-size furniture layout in the interior scene.
In this paper, we propose an assistive model that supports professional interior designers to produce industrial interior decoration solutions and to meet the personalized preferences of the property owners.
In this paper, we propose an adversarial model for producing furniture layout for interior scene synthesis when the interior room is rotated.
This study next reviews major services and toolkits for HPO, comparing their support for state-of-the-art searching algorithms, feasibility with major deep learning frameworks, and extensibility for new modules designed by users.
With the rapid growth of the applications of machine learning (ML) and other artificial intelligence (AI) techniques, adequate testing has become a necessity to ensure their quality.
In the time of Big Data, training complex models on large-scale data sets is challenging, making it appealing to reduce data volume for saving computation resources by subsampling.
In this work, the face-centered cubic (fcc) anion frameworks were creatively constructed to study the effects of anion charge and lattice volume on the stability of lithium ion occupation and lithium ion migration.
In this paper, we propose a three-stream convolutional neural network (3SCNN) for action recognition from skeleton sequences, which aims to thoroughly and fully exploit the skeleton data by extracting, learning, fusing and inferring multiple motion-related features, including 3D joint positions and joint displacements across adjacent frames as well as oriented bone segments.
Ranked #35 on Skeleton Based Action Recognition on NTU RGB+D
In this paper, we presented systematic solutions to build robust and practical AEs against real world object detectors.