[论文解读] ME R-CNN: Multi-Expert Region-based CNN for Object Detection.

Hyungtae Lee, Sungmin Eum+1 more|arXiv (Cornell University)|Apr 4, 2017

Advanced Neural Network Applications被引用 17

一句话总结

ME R-CNN 提出了一种用于目标检测的多专家区域卷积神经网络，该网络使用三个专门化的专家来处理水平拉长、方形和垂直拉长的物体，通过共享的卷积主干网络和通过穷举搜索增强的训练，以捕捉特定形状先验和外观变化，从而提高检测精度。

ABSTRACT

Recent CNN-based object detection methods have drastically improved their performances but still use a single classifier as opposed to in categorizing objects. The main motivation of introducing multi-experts is twofold: i) to allow different experts to specialize in different fundamental object shape priors and ii) to better capture the appearance variations caused by different poses and viewing angles. The proposed approach, referred to as multi-expert Region-based CNN (ME R-CNN), consists of three experts each responsible for objects with particular shapes: horizontally elongated, square-like, and vertically elongated. Each expert is a network with multiple fully connected layers and all the experts are preceded by a shared network which consists of multiple convolutional layers. On top of using selective search which provides a compact, yet effective set of region of interests (RoIs) for object detection, we augmented the set by also employing the exhaustive search for training. Incorporating the exhaustive search can provide complementary advantages: i) it captures the multitude of neighboring RoIs missed by the selective search, and thus ii) provide significantly larger amount of training examples to achieve the enhanced accuracy.

研究动机与目标

• 为解决单分类器目标检测器在处理多样化目标形状和外观变化方面的局限性。
• 通过使专用专家专注于不同形状先验（水平拉长、方形、垂直拉长物体）来提升检测性能。
• 通过结合选择性搜索与穷举搜索生成区域建议，提升训练数据的多样性与覆盖范围。

提出的方法

• 该模型采用共享卷积网络从区域建议中提取特征，随后由三个专用专家分别处理特定形状类别。
• 每个专家网络由多个全连接层组成，基于形状特定特征对物体进行分类。
• 选择性搜索用于生成初始区域建议，随后通过穷举搜索对区域建议进行增强，以捕获更多邻近区域。
• 穷举搜索通过包含选择性搜索遗漏的区域，提供互补的训练样本，提升训练数据多样性。
• 多专家设计实现专业化，提升模型在不同目标姿态和视角下的泛化能力。
• 训练采用端到端方式进行，所有专家与共享主干网络联合优化。

实验结果

研究问题

• RQ1 与单一统一分类器相比，针对不同物体形状先验的专用专家是否能提升目标检测性能？
• RQ2 将选择性搜索与穷举搜索结合用于区域建议生成，对检测精度和训练数据覆盖范围有何影响？
• RQ3 形状专用专家在多大程度上减少了对不同长宽比和姿态物体的检测错误？

主要发现

• 多专家设计通过实现对不同物体形状的专业化，显著提升了检测精度。
• 结合穷举搜索与选择性搜索显著增加了训练样本数量，并增强了模型泛化能力。
• 由于形状特定特征学习，该模型在具有挑战性姿态和视角下的物体检测中表现更优。
• 形状专用专家与增强区域建议的结合，使检测mAP相比单专家基线模型得到显著提升。