SP-NAS: Serial-to-Parallel Backbone Search for Object Detection

By Chenhan Jiang, Hang Xu, Wei Zhang, Xiaodan Liang, Zhenguo Li. 2020

73 citations recorded by the source corpus.

Advanced object detectors usually adopt a backbone network designed and pretrained by ImageNet classification. Recently neural architecture search (NAS) has emerged to automatically design a task-specific backbone to bridge the gap between the tasks of classification and detection. In this paper, we propose a two-phase serial-to-parallel architecture search framework named SP-NAS towards a flexible task-oriented detection backbone. Specifically, the serial-searching round aims at finding a sequence of serial blocks with optimal scale and output channels in the feature hierarchy by a Swap-Expand-Reignite search algorithm; the parallel-searching phase then assembles several sub-architectures along with the previous searched backbone into a more powerful parallel-structured backbone. We efficiently search a detection backbone by exploring a network morphism strategy on multiple detection benchmarks. The resulting architectures achieve SOTA results, i.e. top performance (LAMR: 0.055) on the automotive detection leaderboard of EuroCityPersons benchmark, improving 2.3% mAP with less FLOPS than NAS-FPN on COCO, and reaching 84.1% AP50 on VOC better than DetNAS and Auto-FPN in terms of both accuracy and speed.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

VEGA: Towards an End-to-End Configurable AutoML Pipeline (2020, methodology): “Table 7 shows our results on VEGA comparing to the original reported results in (Jiang et al., 2020).”
CurveLane-NAS: Unifying Lane-Sensitive Architecture Search and Adaptive Point Blending (2020, methodology): “Arch encoding: BB_64_13_[5, 9]_[7, 12]”
SODA10M: Towards Large-Scale Object Detection Benchmark for Autonomous Driving (2021, methodology): “Pre-annotation: In order to ensure efficiency, a multi-task detection model, which is based on Faster RCNN [45] and searched backbone [29, 62], is trained on millions of Human-Vehicle images with bounding-box annotation and generate coarse labels for each image first.”
DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution (2020, methodology): “anoptic segmentation. 2. Related Works Object Detection. There are two main categories of object detection methods: one-stage methods, e.g., [40,49,54,60, 64,73,86,87], and multi-stage methods, e.g., [5,7,8,10,26,27, 29,34,62,75]. Multi-stage detectors are usually more ﬂexible and accurate but more ”
Object Detection in 20 Years: A Survey (2019, unknown): “When designing a detection model, NAS can reduce the need for human intervention in the design of the network backbone and anchor boxes [149], [150], [151], [152], [153], [154], [155].”