Auto-FPN: Automatic Network Architecture Adaptation for Object Detection Beyond Classification
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 computer vision task that classifies and localizes object instances in an image. Existing works focus on transferring the searched architecture from classification task (ImageNet) to the detector backbone, while the rest of the architecture of the detector remains unchanged. However, this pipeline is not task-specific or data-oriented network search which cannot guarantee optimal adaptation to any dataset. Therefore, we propose an architecture search framework named Auto-FPN specifically designed for detection beyond simply searching a classification backbone. Specifically, we propose two auto search modules for detection: Auto-fusion to search a better fusion of the multi-level features; Auto-head to search a better structure for classification and bounding-box(bbox) regression. Instead of searching for one repeatable cell structure, we relax the constraint and allow different cells. The search space of both modules covers many popular designs of detectors and allows efficient gradient-based architecture search with resource constraint (2 days for COCO on 8 GPU cards). Extensive experiments on Pascal VOC, COCO, BDD, VisualGenome and ADE demonstrate the effectiveness of the proposed method, e.g. achieving around 5% improvement than FPN in terms of mAP while requiring around 50% fewer parameters on the searched modules.
Code (0)
등록된 구현이 없습니다.
Tasks
ClassificationGeneral ClassificationGPUimage-classificationImage ClassificationNeural Architecture Searchobject-detectionObject DetectionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Neural Architecture Adaptation for Object Detection by Searching Channel Dimensions and Mapping Pre-trained Parameters
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 ess…
Classificationimage-classificationImage ClassificationNeural Architecture Search+3TaylorMade VDD: Domain-adaptive Visual Defect Detector for High-mix Low-volume Production of Non-convex Cylindrical Metal Objects
Visual defect detection (VDD) for high-mix low-volume production of non-convex metal objects, such as high-pressure cylindrical piping joint parts (VDD-HPPPs), is challenging because subtle difference in domain (e.g., me…
Defect Detectionobject-detectionObject DetectionAutomatic adaptation of object detectors to new domains using self-training
This work addresses the unsupervised adaptation of an existing object detector to a new target domain. We assume that a large number of unlabeled videos from this domain are readily available. We automatically obtain lab…
Domain AdaptationKnowledge DistillationPedestrian DetectionUnsupervised Domain AdaptationLarge-Scale Object Discovery and Detector Adaptation from Unlabeled Video
We explore object discovery and detector adaptation based on unlabeled video sequences captured from a mobile platform. We propose a fully automatic approach for object mining from video which builds upon a generic objec…
Autonomous DrivingClusteringObjectObject Discovery+1Towards Railway Domain Adaptation for LiDAR-based 3D Detection: Road-to-Rail and Sim-to-Real via SynDRA-BBox
In recent years, interest in automatic train operations has significantly increased. To enable advanced functionalities, robust vision-based algorithms are essential for perceiving and understanding the surrounding envir…
3D Object DetectionDomain Adaptation