DeepAI AI Chat
Log In Sign Up

Neural Architecture Adaptation for Object Detection by Searching Channel Dimensions and Mapping Pre-trained Parameters

by   Harim Jung, et al.
Korea University

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 the given backbone for detection purposes, while still allowing the use of pre-trained parameters. We propose to adapt both the micro- and macro-architecture by searching for specific operations and the number of layers, in addition to the output channel dimensions of each block. It is important to find the optimal channel depth, as it greatly affects the feature representation capability and computation cost. We conduct experiments with our searched backbone for object detection and demonstrate that our backbone outperforms both manually designed and searched state-of-the-art backbones on the COCO dataset.


page 1

page 3


Fast Neural Network Adaptation via Parameter Remapping and Architecture Search

Deep neural networks achieve remarkable performance in many computer vis...

SM-NAS: Structural-to-Modular Neural Architecture Search for Object Detection

The state-of-the-art object detection method is complicated with various...

DetNet: A Backbone network for Object Detection

Recent CNN based object detectors, no matter one-stage methods like YOLO...

An Empirical Study of Adder Neural Networks for Object Detection

Adder neural networks (AdderNets) have shown impressive performance on i...

Efficient Neural Architecture Transformation Searchin Channel-Level for Object Detection

Recently, Neural Architecture Search has achieved great success in large...

Hit-Detector: Hierarchical Trinity Architecture Search for Object Detection

Neural Architecture Search (NAS) has achieved great success in image cla...

RSBNet: One-Shot Neural Architecture Search for A Backbone Network in Remote Sensing Image Recognition

Recently, a massive number of deep learning based approaches have been s...