Based on the proposed quality measurement, we propose a deep Tiny Face Quality network (tinyFQnet) to learn a quality prediction function from data.
Most teacher-student frameworks based on knowledge distillation (KD) depend on a strong congruent constraint on instance level.
In this paper, we investigate the effectiveness of two-stage detectors in real-time generic detection and propose a lightweight two-stage detector named ThunderNet.
Ranked #13 on Object Detection on PASCAL VOC 2007
LRM is a general method for real-time detectors, as it utilizes the final feature map which exists in all real-time detectors to mine hard examples.
Depthwise convolutions provide significant performance benefits owing to the reduction in both parameters and mult-adds.
Compact neural networks are inclined to exploit "sparsely-connected" convolutions such as depthwise convolution and group convolution for employment in mobile applications.
Experiments on ILSVRC 2012 and PASCAL VOC 2007 datasets demonstrate that FD-MobileNet consistently outperforms MobileNet and achieves comparable results with ShuffleNet under different computational budgets, for instance, surpassing MobileNet by 5. 5% on the ILSVRC 2012 top-1 accuracy and 3. 6% on the VOC 2007 mAP under a complexity of 12 MFLOPs.
S-OHEM exploits OHEM with stratified sampling, a widely-adopted sampling technique, to choose the training examples according to this influence during hard example mining, and thus enhance the performance of object detectors.