Neural Architecture Adaptation for Object Detection by Searching Channel Dimensions and Mapping Pre-trained Parameters. (arXiv:2206.08509v1 [cs.CV])

Web: http://arxiv.org/abs/2206.08509

Most object detection frameworks use backbone architectures originally
designed for image classification, conventionally with pre-trained parameters
on ImageNet. However, image classification and object detection are essentially
different tasks and there is no guarantee that the optimal backbone for
classification is also optimal for object detection. Recent neural architecture
search (NAS) research has demonstrated that automatically designing a backbone
specifically for object detection helps improve the overall accuracy. In this
paper, we introduce a neural architecture adaptation method that can optimize …

architecture arxiv cv detection mapping neural