CubeNet: X-shape connection for camouflaged object detection

作者：

Highlights：

• We propose a novel CubeNet architecture for camouflaged object detection, which accompanies with feature Fusion Blocks and X-connection to sufficiently integrate multiple layer features.

• The proposed model can be trained quickly. Meanwhile, it achieves real-time inference efficiency.

• Extensive results on three challenging datasets verify the effectiveness of the proposed method.

摘要

•We propose a novel CubeNet architecture for camouflaged object detection, which accompanies with feature Fusion Blocks and X-connection to sufficiently integrate multiple layer features.•The proposed model can be trained quickly. Meanwhile, it achieves real-time inference efficiency.•Extensive results on three challenging datasets verify the effectiveness of the proposed method.

论文关键词：Camouflaged object detection,Neural network,Edge guidance,Novel feature aggregation

论文评审过程：Received 21 September 2020, Revised 13 December 2021, Accepted 8 March 2022, Available online 10 March 2022, Version of Record 16 March 2022.

论文官网地址：https://doi.org/10.1016/j.patcog.2022.108644