← Search

Juanping Zhao

2 accepted papers

2024

Efficient Architecture Search for Real-Time Instance Segmentation

ICASSP 2024accepted

Traditional CNN-based training for instance segmentation is time-consuming owing to large datasets and complex network modules, making direct searching of architecture challenging. In this paper, we introduce an efficient framework, named EASInst. It can discover practical backbone and encoder archi…

Cited by 0SourceScholar
2022

EAutoDet: Efficient Architecture Search for Object Detection

ECCV 2022poster

"Training CNN for detection is time-consuming due to the large dataset and complex network modules, making it hard to search architectures on detection datasets directly, which usually requires vast search costs (usually tens and even hundreds of GPU-days). In contrast, this paper introduces an effi…