Most high quality object detection approaches use the same scheme: salience-based object proposal methods followed by post-classification using deep convolutional features. In this work, we demonstrate that fully learnt, data-driven proposal generation methods can effectively match the accuracy of their hand engineered counterparts, while allowing for very efficient runtime-quality trade-offs. This is achieved by making several key improvements to the MultiBox method [3], among which are an improved neural network architecture, use of contextual features and a new loss function that is robust to missing groundtruth labels. We show that our proposal generation method can closely match the performance of Selective Search [20] at a fraction of the cost. We report new state-of-the-art on the ILSVRC 2014 detection challenge data set, with $55.7%$ mean average precision when combining both Selective Search and MultiBox proposals with our post-classification model. Finally, our approach allows the training of single class detectors that can process 50 images per second on a Xeon workstation, using CPU only, rivaling the quality of the current best performing methods.

本研究使用深度学习的 MSC-MultiBox 方法，在 ILSVRC 2014 数据集上取得了 $0.5$ 的 mAP 表现，明显优于其前任 MultiBox 方法，同时还能在减小提议数量的情况下提高边界框召回率。

可扩展的高质量目标检测