论文标题
用格式多尺度功能融合的快速对象检测
Fast Object Detection with Latticed Multi-Scale Feature Fusion
论文作者
论文摘要
比例差异是多尺度对象检测中至关重要的挑战之一。早期方法通过利用图像和特征金字塔来解决此问题，该图像通过计算负担增加了次优的结果，并根据固有的网络结构约束。开拓性的作品还提出了多尺度（即多分支和多分支）的功能融合，以纠正问题并取得了令人鼓舞的进步。但是，现有的融合仍然存在一定的局限性，例如特征量表不一致，对水平的语义转换的无知和粗粒度。在这项工作中，我们提出了一个新型的模块，即绒毛块，以减轻当前多尺度融合方法的缺点，并促进多尺度对象检测。具体而言，绒毛利用多级和多分支方案，具有扩张的卷积，以具有快速，有效和细粒度的特征融合。此外，我们将Fluff集成到SSD作为FluffNet，这是一种功能强大的实时单级检测器，用于多尺度对象检测。对Coco和Pascal VOC的经验结果表明，Fluffnet具有出色的效率，具有最先进的精度。此外，我们通过显示如何将其嵌入到其他广泛使用的检测器中来指示绒毛块的巨大通用性。
Scale variance is one of the crucial challenges in multi-scale object detection. Early approaches address this problem by exploiting the image and feature pyramid, which raises suboptimal results with computation burden and constrains from inherent network structures. Pioneering works also propose multi-scale (i.e., multi-level and multi-branch) feature fusions to remedy the issue and have achieved encouraging progress. However, existing fusions still have certain limitations such as feature scale inconsistency, ignorance of level-wise semantic transformation, and coarse granularity. In this work, we present a novel module, the Fluff block, to alleviate drawbacks of current multi-scale fusion methods and facilitate multi-scale object detection. Specifically, Fluff leverages both multi-level and multi-branch schemes with dilated convolutions to have rapid, effective and finer-grained feature fusions. Furthermore, we integrate Fluff to SSD as FluffNet, a powerful real-time single-stage detector for multi-scale object detection. Empirical results on MS COCO and PASCAL VOC have demonstrated that FluffNet obtains remarkable efficiency with state-of-the-art accuracy. Additionally, we indicate the great generality of the Fluff block by showing how to embed it to other widely-used detectors as well.
