RefineDetLite: A Lightweight One-stage Object Detection Framework for CPU-only Devices
This work addresses the need for high-efficiency object detectors in resource-restricted industrial scenarios, representing an incremental improvement over existing methods.
The authors tackled the problem of efficient object detection on CPU-only devices by proposing RefineDetLite, a lightweight one-stage framework that achieves 26.8 mAP on MSCOCO at 130 ms per image on a single-thread CPU, with accuracy improving to 29.6 mAP using enhanced training strategies.
Previous state-of-the-art real-time object detectors have been reported on GPUs which are extremely expensive for processing massive data and in resource-restricted scenarios. Therefore, high efficiency object detectors on CPU-only devices are urgently-needed in industry. The floating-point operations (FLOPs) of networks are not strictly proportional to the running speed on CPU devices, which inspires the design of an exactly "fast" and "accurate" object detector. After investigating the concern gaps between classification networks and detection backbones, and following the design principles of efficient networks, we propose a lightweight residual-like backbone with large receptive fields and wide dimensions for low-level features, which are crucial for detection tasks. Correspondingly, we also design a light-head detection part to match the backbone capability. Furthermore, by analyzing the drawbacks of current one-stage detector training strategies, we also propose three orthogonal training strategies---IOU-guided loss, classes-aware weighting method and balanced multi-task training approach. Without bells and whistles, our proposed RefineDetLite achieves 26.8 mAP on the MSCOCO benchmark at a speed of 130 ms/pic on a single-thread CPU. The detection accuracy can be further increased to 29.6 mAP by integrating all the proposed training strategies, without apparent speed drop.