DetNAS: Backbone Search for Object Detection

Object detectors are usually equipped with backbone networks designed for image classification. It might be sub-optimal because of the gap between the tasks of image classification and object detection. In this work, we present DetNAS to use Neural Architecture Search (NAS) for the design of better backbones for object detection.

Data and Resources

Cite this as

Yukang Chen, Tong Yang, Xiangyu Zhang, Gaofeng Meng, Xinyu Xiao, Jian Sun (2024). Dataset: DetNAS: Backbone Search for Object Detection. https://doi.org/10.57702/88glklds

DOI retrieved: December 2, 2024

Additional Info

Field Value
Created December 2, 2024
Last update December 2, 2024
Author Yukang Chen
More Authors
Tong Yang
Xiangyu Zhang
Gaofeng Meng
Xinyu Xiao
Jian Sun
Homepage https://github.com/megvii-model/DetNAS