NAS-FCOS: Fast Neural Architecture Search for Object Detection

Abstract

The success of deep neural networks relies on significant architecture engineering. Recently neural architecture search (NAS) has emerged as a promise to greatly reduce manual effort in network design by automatically searching for optimal architectures, although typically such algorithms need an excessive amount of computational resources, e.g., a few thousand GPU-days. To date, on challenging vision tasks such as object detection, NAS, especially fast versions of NAS, is less studied. Here we propose to search for the decoder structure of object detectors with search efficiency being taken into consideration. To be more specific, we aim to efficiently search for the feature pyramid network (FPN) as well as the prediction head of a simple anchor-free object detector, namely FCOS, using a tailored reinforcement learning paradigm. With carefully designed search space, search algorithms and strategies for evaluating network quality, we are able to efficiently search a top-performing detection architecture within 4 days using 8 V100 GPUs. The discovered architecture surpasses state-of-the-art object detection models (such as Faster R-CNN, RetinaNet and FCOS) by 1.5 to 3.5 points in AP on the COCO dataset, with comparable computation complexity and memory footprint, demonstrating the efficacy of the proposed NAS for object detection.

arXiv comment9 pages, 9 figures, accepted by CVPR-2020

References in corpus (10)

• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• YOLOv3: An Incremental Improvement
• Neural Architecture Search with Reinforcement Learning
• Neural Architecture Search: A Survey
• FCOS: Fully Convolutional One-Stage Object Detection
• Efficient Neural Architecture Search via Parameter Sharing
• Aggregated Residual Transformations for Deep Neural Networks
• Single Path One-Shot Neural Architecture Search with Uniform Sampling
• Deformable ConvNets v2: More Deformable, Better Results
• DetNAS: Backbone Search for Object Detection

Cited by in corpus (12)

• MobileDets: Searching for Object Detection Architectures for Mobile Accelerators
• Computation Reallocation for Object Detection
• Side-Aware Boundary Localization for More Precise Object Detection
• Auto-Panoptic: Cooperative Multi-Component Architecture Search for Panoptic Segmentation
• ASFD: Automatic and Scalable Face Detector
• SM-NAS: Structural-to-Modular Neural Architecture Search for Object Detection
• EcoNAS: Finding Proxies for Economical Neural Architecture Search
• MnasFPN: Learning Latency-aware Pyramid Architecture for Object Detection on Mobile Devices
• On the Privacy Risks of Cell-Based NAS Architectures
• Seesaw Loss for Long-Tailed Instance Segmentation
• Representation Sharing for Fast Object Detector Search and Beyond
• Mutually-aware Sub-Graphs Differentiable Architecture Search