.png){kind=icon}
.png){kind=icon}
Return
Knowledge-guided and Collaborative Learning Network for Camouflaged Object Detection
.png){kind=icon}
PRE
AI
DOI：10.1016/j.engappai.2025.110771.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Camouflaged Object Detection (COD) task is more arduous than other target detection tasks because of the challenges of complex and variable contours, scale diversity, and high similarity to the background. Moreover, in pursuit of better detection performance, most existing COD methods usually require many parameters and computational complexity, which undoubtedly increases the difficulty and cost of implementation. In this paper, by revisiting this difficult task, we find that the collaborative effect of extracting explicit edge knowledge and global semantics highlights the camouflaged regions more and significantly affects detection efficiency. We propose a more comprehensible and efficient network for COD, namely the Knowledge-guided and Collaborative Learning Network (KCNet). It comes with more complex camouflaged targets by introducing rough features containing a large amount of edge knowledge and global semantics to interact with other components fully and collaborative learning. Specifically, we gradually introduce the rough features acquired by the preliminary perception unit to the layers by designing a knowledge-guided positioning module. Secondly, we design a detail enhancement module to enhance the extraction of the detailed parts of semantic information at deeper levels. Finally, we give a convolutional decoding unit to output the complete camouflaged target prediction information. Extensive experimental results show that our model reaches the state-of-the-art on four challenging datasets, outperforming 22 advanced models currently available. Meanwhile, KCNet exhibits a low number of parameters, a low computational complexity, and a very competitive inference speed, all of which are advantages over existing methods. The codes are released at https://github.com/wd61419/KCNet.
Keywords:
Camouflaged Object Detection
Edge knowledge
Global semantics
Multiple attention mechanism
Journal
IF:
8
Papers:
5.3K
Citations:
3.5W