Learning to decompose for object detection and instance segmentation
Eunbyung Park、Alexander C. Berg Department of Computer Science University of North Carolina at Chapel Hill
Abstract
Although deep convolutional neural networks(CNNs) have achieved remarkable results on object detection and segmentation, pre- and post-processing steps such as region proposals and non-maximum suppression(NMS), have been required. These steps result in high computational complexity and sensitivity to hyperparameters, e.g. thresholds for NMS. In this work, we propose a novel end-to-end trainable deep neural network architecture, which consists of convolutional and recurrent layers, that generates the correct number of object instances and their bounding boxes (or segmentation masks) given an image, using only a single network evaluation without any pre- or post-processing steps. We have tested on detecting digits in multi-digit images synthesized using MNIST, automatically segmenting digits in these images, and detecting cars in the KITTI benchmark dataset. The proposed approach outperforms a strong CNN baseline on the synthesized digits datasets and shows promising results on KITTI car detection.
中文速览
目标检测领域长期依赖区域候选框生成和非极大值抑制等繁琐的前后处理步骤，这不仅带来巨大的计算开销，还引入了对超参数的敏感依赖。为此，研究者提出了一种名为 DecompNet 的端到端可训练深度神经网络，将卷积层与循环层结合：先由卷积部分生成各类别的响应图，再通过循环网络逐步将其"分解"为单个目标实例的掩码图，从而在一次前向推断中直接输出数量可变的目标边界框或分割掩码，完全省去区域候选和 NMS。在基于 MNIST 合成的多目标数字检测与分割任务上，该方法优于强力 CNN 基线，在真实场景的 KITTI 车辆检测基准上也展现了有竞争力的结果。这项工作的意义在于，它从根本上简化了多类别、多实例目标检测的训练流程，为构建更轻量、更易推广的端到端检测系统提供了新思路。
原文 arXiv:1511.06449;中英对照 + 大白话阅读 https://aha.fim.ai/paper/1511.06449v3