This paper presents how we can achieve the state-of-the-art accuracy in
multi-category object detection task while minimizing the computational cost by
adapting and combining recent technical innovations. Following the common
pipeline of "CNN feature extraction + region proposal + RoI classification", we
mainly redesign the feature extraction part, since region proposal part is not
computationally expensive and classification part can be efficiently compressed
with common techniques like truncated SVD. Our design principle is "less
channels with more layers" and adoption of some building blocks including
concatenated ReLU, Inception, and HyperNet. The designed network is deep and
thin and trained with the help of batch normalization, residual connections,
and learning rate scheduling based on plateau detection. We obtained solid
results on well-known object detection benchmarks: 83.8% mAP (mean average
precision) on VOC2007 and 82.5% mAP on VOC2012 (2nd place), while taking only
750ms/image on Intel i7-6700K CPU with a single core and 46ms/image on NVIDIA
Titan X GPU. Theoretically, our network requires only 12.3% of the
computational cost compared to ResNet-101, the winner on VOC2012.

本文介绍了如何在最小化计算成本的同时，通过采用和组合最新技术创新来实现多类别物体检测任务的最先进准确度。设计原则是 “少通道多层”，采用了一些基本块，包括拼接 ReLU、Inception 和 HyperNet， 在 VOC2007 上达到 83.8％的 mAP，VOC2012 为 82.5％mAP（第 2 名），仅使用 Intel i7-6700K CPU 单核时，每张图像仅需 750ms，在 NVIDIA Titan X GPU 上为 46ms / 图像，其网络与 ResNet-101 相比，计算成本只需 12.3％。