Recent research about camouflaged object detection (COD) aims to segment highly concealed objects hidden in complex surroundings. The tiny, fuzzy camouflaged objects result in visually indistinguishable properties. However, current single-view COD detectors are sensitive to background distractors. Therefore, blurred boundaries and variable shapes of the camouflaged objects are challenging to be fully captured with a single-view detector. To overcome these obstacles, we propose a behavior-inspired framework, called Multi-view Feature Fusion Network (MFFN), which mimics the human behaviors of finding indistinct objects in images, i.e., observing from multiple angles, distances, perspectives. Specifically, the key idea behind it is to generate multiple ways of observation (multi-view) by data augmentation and apply them as inputs. MFFN captures critical boundary and semantic information by comparing and fusing extracted multi-view features. In addition, our MFFN exploits the dependence and interaction between views and channels. Specifically, our methods leverage the complementary information between different views through a two-stage attention module called Co-attention of Multi-view (CAMV). And we design a local-overall module called Channel Fusion Unit (CFU) to explore the channel-wise contextual clues of diverse feature maps in an iterative manner. The experiment results show that our method performs favorably against existing state-of-the-art methods via training with the same data. The code will be available at https://github.com/ dwardzheng/MFFN_COD.
翻译:最近关于隐蔽物体探测(COD)的研究旨在将隐藏在复杂环境中的高度隐蔽物体分割开来,这些微小、模糊的隐蔽物体导致视觉上无法区分的特性。然而,目前的单一视图的COD探测器对背景分散器十分敏感。 因此,隐蔽物体的模糊界限和变异形状很难用单一视图探测器完全捕捉。为了克服这些障碍,我们建议了一个行为启发框架,称为多视图特征分解网络(MFFFFF),它模仿人类在图像中查找不同对象的行为,即从多角度、距离、角度观察。具体地说,它背后的关键想法是通过数据增强产生多种观测方式(多视图),并将其用作投入。MFFN通过比较和用提取的多视图探测器探测器特征,掌握关键的边界和语义信息。此外,我们的MFFN利用不同观点和渠道之间的依赖和互动关系。具体地说,我们的方法通过一个名为多视角的双级关注模块,从多角度观察,从多角度观察,从多视角观察,从多角度,从多个角度,从角度,从角度,从角度,从角度,从角度,从角度,从角度,角度,角度,角度,角度,从中观察中观察,具体角度,从中,从中,从中,从中观察,从中,从中,从中,从中,从中,从中,从中,从中,从中,从中,从中,从中,从中,从中,从中,从中,从中,从中,从中,从中,从中,从中,从中,从中,从中,从中,从中,从中,从中,到角度,到角度,从中,到角度,从中,到角度,从中,从中,从中,从中,从中,观察,到角度,观察,观察,观察,观察,观察,观察,观察,到角度,观察,观察,观察,观察,观察,观察,观察,到角度,到角度,观察,观察,观察到角度,观察,到角度,观察,观察,到角度,从中,到角度,观察,到角度,观察,观察,从中,观察,到角度,观察,从中,到角度,从中,从中,观察,观察,从中,