Representation Sharing for Fast Object Detector Search and Beyond
arXiv:2007.12075
Abstract
Region Proposal Network (RPN) provides strong support for handling the scale variation of objects in two-stage object detection. For one-stage detectors which do not have RPN, it is more demanding to have powerful sub-networks capable of directly capturing objects of unknown sizes. To enhance such capability, we propose an extremely efficient neural architecture search method, named Fast And Diverse (FAD), to better explore the optimal configuration of receptive fields and convolution types in the sub-networks for one-stage detectors. FAD consists of a designed search space and an efficient architecture search algorithm. The search space contains a rich set of diverse transformations designed specifically for object detection. To cope with the designed search space, a novel search algorithm termed Representation Sharing (RepShare) is proposed to effectively identify the best combinations of the defined transformations. In our experiments, FAD obtains prominent improvements on two types of one-stage detectors with various backbones. In particular, our FAD detector achieves 46.4 AP on MS-COCO (under single-scale testing), outperforming the state-of-the-art detectors, including the most recent NAS-based detectors, Auto-FPN (searched for 16 GPU-days) and NAS-FCOS (28 GPU-days), while significantly reduces the search cost to 0.6 GPU-days. Beyond object detection, we further demonstrate the generality of FAD on the more challenging instance segmentation, and expect it to benefit more tasks.
arXiv commentECCV 2020 accepted
References in corpus (19)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
- YOLOv3: An Incremental Improvement
- Neural Architecture Search with Reinforcement Learning
- R-FCN: Object Detection via Region-based Fully Convolutional Networks
- FCOS: Fully Convolutional One-Stage Object Detection
- Efficient Neural Architecture Search via Parameter Sharing
- Large-Scale Evolution of Image Classifiers
- DropBlock: A regularization method for convolutional networks
- Neural Architecture Optimization
- FreeAnchor: Learning to Match Anchors for Visual Object Detection
- DetNAS: Backbone Search for Object Detection
- Scale-Aware Trident Networks for Object Detection
- Efficient Neural Architecture Transformation Searchin Channel-Level for Object Detection
- Computation Reallocation for Object Detection
- NAS-FCOS: Fast Neural Architecture Search for Object Detection
- SM-NAS: Structural-to-Modular Neural Architecture Search for Object Detection
- Soft Anchor-Point Object Detection