论文标题
多尺度交互式网络，用于显着对象检测
Multi-scale Interactive Network for Salient Object Detection
论文作者
论文摘要
基于深度学习的显着对象检测方法取得了长足的进步。但是，显着对象的可变规模和未知类别一直是巨大的挑战。这些与多级和多尺度功能的利用密切相关。在本文中，我们提出了骨料交互模块，以整合相邻级别的特征，其中引入了较少的噪声，因为仅使用了小的上/下抽采样率。为了从集成功能获得更有效的多尺度功能，将嵌入每个解码器单元中的自相互作用模块。此外，由量表变化引起的类不平衡问题削弱了二进制横熵损失的影响，并导致预测的空间不一致。因此，我们利用一致性增强的损失来突出前/背面的差异并保留类内的一致性。五个基准数据集的实验结果表明，提出的没有任何后处理的方法对23种最先进的方法有利。源代码将在https://github.com/lartpang/minet上公开获取。
Deep-learning based salient object detection methods achieve great progress. However, the variable scale and unknown category of salient objects are great challenges all the time. These are closely related to the utilization of multi-level and multi-scale features. In this paper, we propose the aggregate interaction modules to integrate the features from adjacent levels, in which less noise is introduced because of only using small up-/down-sampling rates. To obtain more efficient multi-scale features from the integrated features, the self-interaction modules are embedded in each decoder unit. Besides, the class imbalance issue caused by the scale variation weakens the effect of the binary cross entropy loss and results in the spatial inconsistency of the predictions. Therefore, we exploit the consistency-enhanced loss to highlight the fore-/back-ground difference and preserve the intra-class consistency. Experimental results on five benchmark datasets demonstrate that the proposed method without any post-processing performs favorably against 23 state-of-the-art approaches. The source code will be publicly available at https://github.com/lartpang/MINet.
