paper-with-me

홈 › Papers

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

2022-06-17 · Harim Jung, Myeong-Seok Oh, Cheoljong Yang, Seong-Whan Lee

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.

📄 PDF Abstract BibTeX arXiv:2206.08509

Code (0)

등록된 구현이 없습니다.

Tasks

Classificationimage-classificationImage ClassificationNeural Architecture SearchObjectobject-detectionObject Detection

Similar Papers 제목 키워드 기반

Efficient Neural Architecture Transformation Searchin Channel-Level for Object Detection

2019-09-05 · Junran Peng, Ming Sun, Zhao-Xiang Zhang, Tieniu Tan 외

Recently, Neural Architecture Search has achieved great success in large-scale image classification. In contrast, there have been limited works focusing on architecture search for object detection, mainly because the cos…

image-classificationImage ClassificationNeural Architecture SearchObject+2

Efficient Neural Architecture Transformation Search in Channel-Level for Object Detection

2019-12-01 · NeurIPS 2019 12 · Junran Peng, Ming Sun, Zhao-Xiang Zhang, Tieniu Tan 외

Recently, Neural Architecture Search has achieved great success in large-scale image classification. In contrast, there have been limited works focusing on architecture search for object detection, mainly because the cos…

image-classificationImage ClassificationNeural Architecture SearchObject+2

Auto-FPN: Automatic Network Architecture Adaptation for Object Detection Beyond Classification

2019-10-01 · ICCV 2019 10 · Hang Xu, Lewei Yao, Wei Zhang, Xiaodan Liang 외

Abstract Neural architecture search (NAS) has shown great potential in automating the manual process of designing a good CNN architecture for image classification. In this paper, we study NAS for object detection, a core…

ClassificationGeneral ClassificationGPUimage-classification+4

SP-NAS: Serial-to-Parallel Backbone Search for Object Detection

2020-06-01 · CVPR 2020 6 · Chenhan Jiang, Hang Xu, Wei Zhang, Xiaodan Liang 외

Advanced object detectors usually adopt a backbone network designed and pretrained by ImageNet classification. Recently neural architecture search (NAS) has emerged to automatically design a task-specific backbone to bri…

General ClassificationNeural Architecture Searchobject-detectionObject Detection

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

2019-11-22 · Lewei Yao, Hang Xu, Wei zhang, Xiaodan Liang 외

The state-of-the-art object detection method is complicated with various modules such as backbone, feature fusion neck, RPN and RCNN head, where each module may have different designs and structures. How to leverage the …

GPUNeural Architecture SearchObjectobject-detection+1