Home /
Research
Showing 697 - 702 / 904
An improved helmet detection method for YOLOv3 on an unbalanced dataset
RuiGeng, YixuanMa, WanhongHuang....
Published date-11/09/2020
DataAugmentation
The YOLOv3 target detection algorithm is widely used in industry due to its high speed and high accuracy, but it has some limitations, such as the accuracy degradation of unbalanced …
Geometric Deep Reinforcement Learning for Dynamic DAG Scheduling
NathanGrinsztajn, OlivierBeaumont, EmmanuelJeannot....
Published date-11/09/2020
CombinatorialOptimization
In practice, it is quite common to face combinatorial optimization problems which contain uncertainty along with non-determinism and dynamicity. These three properties call for appropriate algorithms; reinforcement learning (RL) is …
Parameterized Explainer for Graph Neural Network
DongshengLuo, WeiCheng, DongkuanXu....
Published date-11/09/2020
GraphClassification
Despite recent progress in Graph Neural Networks (GNNs), explaining predictions made by GNNs remains a challenging open problem. The leading method independently addresses the local explanations (i.e., important subgraph structure …
What time is it? Temporal Analysis of Novels
AllenKim, CharutaPethe, StevenSkiena....
Published date-11/09/2020
Recognizing the flow of time in a story is a crucial aspect of understanding it. Prior work related to time has primarily focused on identifying temporal expressions or relative sequencing …
SplitEasy: A Practical Approach for Training ML models on Mobile Devices in a split second
KamaleshPalanisamy, VivekKhimani, MoinHussainMoti....
Published date-11/09/2020
Modern mobile devices, although resourceful, cannot train state-of-the-art machine learning models without the assistance of servers, which require access to privacy-sensitive user data. Split learning has recently emerged as a …
Long Range Arena: A Benchmark for Efficient Transformers
YiTay, MostafaDehghani, SamiraAbnar....
Published date-11/08/2020
Transformers do not scale very well to long sequence lengths largely because of quadratic self-attention complexity. In the recent months, a wide spectrum of efficient, fast Transformers have been proposed …