Improving Camouflaged Object Detection with the Uncertainty of Pseudo-edge Labels
Improving Camouflaged Object Detection with the Uncertainty of Pseudo-edge Labels
复制标题
DOI：
10.1145/3469877.3490587
复制
发表时间：
2021-10
期刊：
影响因子：
--
通讯作者：
Nobukatsu Kajiura;Hong Liu;S. Satoh
中科院分区：
文献类型：
--
作者：
Nobukatsu Kajiura;Hong Liu;S. Satoh
本文重点关注伪装对象检测（COD），这是检测隐藏在背景中的对象的任务。当前大多数 COD 模型的目标是直接突出目标对象，同时输出模糊的伪装边界。另一方面，考虑边缘信息的模型的性能尚不令人满意。为此，我们提出了一个新的框架，充分利用多种视觉线索，即显着性和边缘，来细化预测的伪装图。该框架由三个关键组件组成，即伪边缘生成器、伪地图生成器和不确定性感知细化模块。具体地，伪边缘生成器估计输出伪边缘标签的边界，并且传统的COD方法充当输出伪地图标签的伪地图生成器。然后，我们提出了一种基于不确定性的模块来减少这两个伪标签的不确定性和噪声，该模块将两个伪标签作为输入并输出边缘精确的伪装图。对各种 COD 数据集的实验证明了我们方法的有效性，其性能优于现有的最先进方法。
This paper focuses on camouflaged object detection (COD), which is a task to detect objects hidden in the background. Most of the current COD models aim to highlight the target object directly while outputting ambiguous camouflaged boundaries. On the other hand, the performance of the models considering edge information is not yet satisfactory. To this end, we propose a new framework that makes full use of multiple visual cues, i.e., saliency as well as edges, to refine the predicted camouflaged map. This framework consists of three key components, i.e., a pseudo-edge generator, a pseudo-map generator, and an uncertainty-aware refinement module. In particular, the pseudo-edge generator estimates the boundary that outputs the pseudo-edge label, and the conventional COD method serves as the pseudo-map generator that outputs the pseudo-map label. Then, we propose an uncertainty-based module to reduce the uncertainty and noise of such two pseudo labels, which takes both pseudo labels as input and outputs an edge-accurate camouflaged map. Experiments on various COD datasets demonstrate the effectiveness of our method with superior performance to the existing state-of-the-art methods.