Auto-FPN: Automatic Network Architecture Adaptation for Object Detection Beyond Classification
2019 IEEE/CVF International Conference on Computer Vision (ICCV)(2019)
摘要
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 GPUs). 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.
更多查看译文
关键词
NAS,CNN architecture,image classification,object detection,computer vision task,classification task,data-oriented network search,Auto-FPN,classification backbone,auto search modules,automatic network architecture,gradient-based architecture search,auto-fusion,auto-head,abstract neural architecture search
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络