Mamba Capsule Routing Towards Part-Whole Relational Camouflaged Object Detection

TL;DR

This paper introduces a novel mamba capsule routing method at the type level to improve camouflaged object detection, reducing computation and parameters compared to traditional pixel-level routing, and achieves superior results on benchmark datasets.

Contribution

The paper proposes a type-level mamba capsule routing approach that enhances efficiency and effectiveness in camouflaged object detection over existing pixel-level capsule routing methods.

Findings

Significantly outperforms state-of-the-art methods on three COD benchmarks.

Reduces computation and parameters compared to EM capsule routing.

Effectively retrieves pixel-level features guided by type-level capsules.

Abstract

The part-whole relational property endowed by Capsule Networks (CapsNets) has been known successful for camouflaged object detection due to its segmentation integrity. However, the previous Expectation Maximization (EM) capsule routing algorithm with heavy computation and large parameters obstructs this trend. The primary attribution behind lies in the pixel-level capsule routing. Alternatively, in this paper, we propose a novel mamba capsule routing at the type level. Specifically, we first extract the implicit latent state in mamba as capsule vectors, which abstract type-level capsules from pixel-level versions. These type-level mamba capsules are fed into the EM routing algorithm to get the high-layer mamba capsules, which greatly reduce the computation and parameters caused by the pixel-level capsule routing for part-whole relationships exploration. On top of that, to retrieve the pixel-level capsule features for further camouflaged prediction, we achieve this on the basis of the low-layer pixel-level capsules with the guidance of the correlations from adjacent-layer type-level mamba capsules. Extensive experiments on three widely used COD benchmark datasets demonstrate that our method significantly outperforms state-of-the-arts. Code has been available on https://github.com/Liangbo-Cheng/mamba\_capsule.