Object detection has made substantial progress in the last decade, due to the capability of convolution in extracting local context of objects. However, the scales of objects are diverse and current convolution can only process single-scale input. The capability of traditional convolution with a fixed receptive field in dealing with such a scale variance problem, is thus limited. Multi-scale feature representation has been proven to be an effective way to mitigate the scale variance problem. Recent researches mainly adopt partial connection with certain scales, or aggregate features from all scales and focus on the global information across the scales. However, the information across spatial and depth dimensions is ignored. Inspired by this, we propose the multi-scale convolution (MSConv) to handle this problem. Taking into consideration scale, spatial and depth information at the same time, MSConv is able to process multi-scale input more comprehensively. MSConv is effective and computationally efficient, with only a small increase of computational cost. For most of the single-stage object detectors, replacing the traditional convolutions with MSConvs in the detection head can bring more than 2.5\% improvement in AP (on COCO 2017 dataset), with only 3\% increase of FLOPs. MSConv is also flexible and effective for two-stage object detectors. When extended to the mainstream two-stage object detectors, MSConv can bring up to 3.0\% improvement in AP. Our best model under single-scale testing achieves 48.9\% AP on COCO 2017 \textit{test-dev} split, which surpasses many state-of-the-art methods.
翻译:过去十年来,由于在采集本地天体方面的能力发生变迁,物体的探测取得了显著进展。然而,物体的规模各不相同,当前的变迁只能处理单一规模的投入。因此,传统变迁与固定的可接受场处理规模差异问题的能力有限。多规模特征代表已证明是缓解规模差异问题的有效方法。最近的研究主要采用某些规模或所有规模的综合特征的部分连接,并侧重于全球范围的信息。然而,空间和深度层面的信息被忽略。受此启发,我们提议多规模变迁(MSConv)只能处理单一规模的投入。考虑到规模、空间和深度信息处理这种规模差异问题,MSConv能够更全面地处理多规模的投入。MSConv是有效的和计算效率,只有少量增加计算成本。对于大多数单级物体探测器而言,检测头部的MSConvors传统变异模式可以使AP(CO 201717年分级目标)的改进超过2.5 ⁇ 以上。在此过程中,只有3个空间和深度的多规模的MSLQ-CO-CRM-M-S-S-S-S-S-S-S-S-S-Servilental-S-S-S-S-S-S-S-S-S-S-Servil-S-Serviol-S-S-S-Servil-S-S-S-S-S-S-S-S-S-S-S-Serval-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-