Yin Bowen, Zhang Xuying, Fan Deng-Ping, Jiao Shaohui, Cheng Ming-Ming, Van Gool Luc, Hou Qibin
IEEE Trans Pattern Anal Mach Intell. 2024 Dec;46(12):10362-10374. doi: 10.1109/TPAMI.2024.3438565. Epub 2024 Nov 6.
How to identify and segment camouflaged objects from the background is challenging. Inspired by the multi-head self-attention in Transformers, we present a simple masked separable attention (MSA) for camouflaged object detection. We first separate the multi-head self-attention into three parts, which are responsible for distinguishing the camouflaged objects from the background using different mask strategies. Furthermore, we propose to capture high-resolution semantic representations progressively based on a simple top-down decoder with the proposed MSA to attain precise segmentation results. These structures plus a backbone encoder form a new model, dubbed CamoFormer. Extensive experiments show that CamoFormer achieves new state-of-the-art performance on three widely-used camouflaged object detection benchmarks. To better evaluate the performance of the proposed CamoFormer around the border regions, we propose to use two new metrics, i.e., BR-M and BR-F. There are on average ∼ 5% relative improvements over previous methods in terms of S-measure and weighted F-measure.
如何从背景中识别和分割伪装物体具有挑战性。受Transformer中多头自注意力机制的启发，我们提出了一种用于伪装物体检测的简单掩码可分离注意力（MSA）。我们首先将多头自注意力分为三个部分，它们使用不同的掩码策略负责将伪装物体与背景区分开来。此外，我们建议基于一个简单的自上而下解码器和所提出的MSA逐步捕捉高分辨率语义表示，以获得精确的分割结果。这些结构加上一个骨干编码器形成了一个新模型，称为CamoFormer。大量实验表明，CamoFormer在三个广泛使用的伪装物体检测基准上取得了新的最优性能。为了更好地评估所提出的CamoFormer在边界区域周围的性能，我们提出使用两个新的指标，即BR-M和BR-F。在S度量和加权F度量方面，相对于先前方法平均有大约5%的相对改进。
