Object detection methods usually represent objects through rectangular bounding boxes from which they extract features, regardless of their actual shapes. In this paper, we apply deformations to regions in order to learn representations better fitted to objects. We introduce DP-FCN, a deep model implementing this idea by learning to align parts to discriminative elements of objects in a latent way, i.e. without part annotation. This approach has two main assets: it builds invariance to local transformations, thus improving recognition, and brings geometric information to describe objects more finely, leading to a more accurate localization. We further develop both features in a new model named DP-FCN2.0 by explicitly learning interactions between parts. Alignment is done with an in-network joint optimization of all parts based on a CRF with custom potentials, and deformations are influencing localization through a bilinear product. We validate our models on PASCAL VOC and MS COCO datasets and show significant gains. DP-FCN2.0 achieves state-of-the-art results of 83.3 and 81.2% on VOC 2007 and 2012 with VOC data only.

中文翻译：

---

用于对象检测的基于潜在可变形部件的表示的端到端学习

对象检测方法通常通过矩形边界框来表示对象，无论它们的实际形状如何，它们从中提取特征。在本文中，我们将变形应用于区域以学习更适合对象的表示。我们介绍了 DP-FCN，这是一种深度模型，通过学习以潜在方式（即没有部分注释）将部件与对象的判别元素对齐来实现这一想法。这种方法有两个主要优点：它为局部变换建立了不变性，从而提高了识别率，并带来了几何信息来更精细地描述对象，从而实现更准确的定位。我们通过明确学习部件之间的交互，在名为 DP-FCN2.0 的新模型中进一步开发了这两个功能。对齐是通过基于具有自定义电位的 CRF 对所有部件进行网络内联合优化来完成的，并且变形通过双线性乘积影响定位。我们在 PASCAL VOC 和 MS COCO 数据集上验证了我们的模型，并显示出显着的收益。DP-FCN2.0 仅使用 VOC 数据在 VOC 2007 和 2012 上实现了 83.3% 和 81.2% 的最新结果。