MnasFPN: Learning Latency-aware Pyramid Architecture for Object Detection on Mobile Devices

CVPR 2020 Bo ChenGolnaz GhiasiHanxiao LiuTsung-Yi LinDmitry KalenichenkoHartwig AdamsQuoc V. Le

Despite the blooming success of architecture search for vision tasks in resource-constrained environments, the design of on-device object detection architectures have mostly been manual. The few automated search efforts are either centered around non-mobile-friendly search spaces or not guided by on-device latency... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Object Detection COCO test-dev MnasFPN (MNASNet-B1) box AP 24.6 # 81
Object Detection COCO test-dev MnasFPN (MobileNetV2) box AP 26.1 # 78
Object Detection COCO test-dev MnasFPN x0.7 (MobileNetV2) box AP 23.8 # 82
Object Detection COCO test-dev MnasFPN (MobileNetV3) box AP 25.5 # 80

Methods used in the Paper