Yan Xinyu, Sun Meijun, Han Yahong, Wang Zheng
IEEE Trans Neural Netw Learn Syst. 2024 Nov;35(11):15993-16007. doi: 10.1109/TNNLS.2023.3291595. Epub 2024 Oct 29.
In the biosphere, camouflaged objects take the advantage of visional wholeness by keeping the color and texture of the objects highly consistent with the background, thereby confusing the visual mechanism of other creatures and achieving a concealed effect. This is also the main reason why the task of camouflaged object detection is challenging. In this article, we break the visual wholeness and see through the camouflage from the perspective of matching the appropriate field of view. We propose a matching-recognition-refinement network (MRR-Net), which consists of two key modules, i.e., the visual field matching and recognition module (VFMRM) and the stepwise refinement module (SWRM). In the VFMRM, various feature receptive fields are used to match candidate areas of camouflaged objects of different sizes and shapes and adaptively activate and recognize the approximate area of the real camouflaged object. The SWRM then uses the features extracted by the backbone to gradually refine the camouflaged region obtained by VFMRM, thus yielding the complete camouflaged object. In addition, a more efficient deep supervision method is exploited, making the features from the backbone input into the SWRM more critical and not redundant. Extensive experimental results demonstrate that our MRR-Net runs in real-time (82.6 frames/s) and significantly outperforms 30 state-of-the-art models on three challenging datasets under three standard metrics. Furthermore, MRR-Net is applied to four downstream tasks of camouflaged object segmentation (COS), and the results validate its practical application value. Our code is publicly available at: https://github.com/XinyuYanTJU/MRR-Net.
在生物圈中，伪装物体通过使物体的颜色和纹理与背景高度一致来利用视觉整体性，从而迷惑其他生物的视觉机制并实现隐蔽效果。这也是伪装物体检测任务具有挑战性的主要原因。在本文中，我们打破视觉整体性，从匹配适当视野的角度看穿伪装。我们提出了一种匹配-识别-细化网络（MRR-Net），它由两个关键模块组成，即视野匹配与识别模块（VFMRM）和逐步细化模块（SWRM）。在VFMRM中，使用各种特征感受野来匹配不同大小和形状的伪装物体的候选区域，并自适应地激活和识别真实伪装物体的近似区域。然后，SWRM使用主干网络提取的特征逐步细化VFMRM获得的伪装区域，从而得到完整的伪装物体。此外，我们采用了一种更有效的深度监督方法，使来自主干网络的特征输入到SWRM中更关键且无冗余。大量实验结果表明，我们的MRR-Net能够实时运行（82.6帧/秒），并且在三个具有挑战性的数据集上，在三个标准指标下显著优于30个先进模型。此外，MRR-Net被应用于伪装物体分割（COS）的四个下游任务，结果验证了其实际应用价值。我们的代码可在以下网址公开获取：https://github.com/XinyuYanTJU/MRR-Net 。
