FSD: Fully-Specialized Detector via Neural Architecture Search

Abstract

Most generic object detectors are mainly built for standard object detection tasks such as COCO and PASCAL VOC. They might not work well and/or efficiently on tasks of other domains consisting of images that are visually different from standard datasets. To this end, many advances have been focused on adapting a general-purposed object detector with limited domain-specific designs. However, designing a successful task-specific detector requires extraneous manual experiments and parameter tuning through trial and error. In this paper, we first propose and examine a fully-automatic pipeline to design a fully-specialized detector (FSD) which mainly incorporates a neural-architectural-searched model by exploring ideal network structures over the backbone and task-specific head. On the DeepLesion dataset, extensive results show that FSD can achieve 3.1 mAP gain while using approximately 40% fewer parameters on binary lesion detection task and improved the mAP by around 10% on multi-type lesion detection task via our region-aware graph modeling compared with existing general-purposed medical lesion detection networks.

References in corpus (5)

• Adam: A Method for Stochastic Optimization
• Neural Architecture Search with Reinforcement Learning
• Res2Net: A New Multi-scale Backbone Architecture
• Searching for Efficient Multi-Scale Architectures for Dense Image Prediction
• Retina U-Net: Embarrassingly Simple Exploitation of Segmentation Supervision for Medical Object Detection