论文标题
PPGN：用于参考表达理解的短语指导提案生成网络
PPGN: Phrase-Guided Proposal Generation Network For Referring Expression Comprehension
论文作者
论文摘要
参考表达理解（REC）旨在查找给定图像中短语所指的位置。在许多两阶段REC方法中，提案生成和提案表示是两种有效的技术。但是，大多数现有作品仅着眼于提案代表，而忽略了提案生成的重要性。结果，这些方法产生的低质量提案成为REC任务中的性能瓶颈。在本文中，我们重新考虑了提案生成的问题，并提出了一个新的短语指导的提议生成网络（PPGN）。 PPGN的主要实现原理是通过文本提炼视觉特征，并通过回归生成建议。实验表明，我们的方法有效，并在基准数据集中实现SOTA性能。
Reference expression comprehension (REC) aims to find the location that the phrase refer to in a given image. Proposal generation and proposal representation are two effective techniques in many two-stage REC methods. However, most of the existing works only focus on proposal representation and neglect the importance of proposal generation. As a result, the low-quality proposals generated by these methods become the performance bottleneck in REC tasks. In this paper, we reconsider the problem of proposal generation, and propose a novel phrase-guided proposal generation network (PPGN). The main implementation principle of PPGN is refining visual features with text and generate proposals through regression. Experiments show that our method is effective and achieve SOTA performance in benchmark datasets.
