paper-with-me

Papers

Mamba Capsule Routing Towards Part-Whole Relational Camouflaged Object Detection

2024-10-05 · Dingwen Zhang, Liangbo Cheng, Yi Liu, Xinggang Wang, Junwei Han

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.

📄 PDF Abstract BibTeX arXiv:2410.03987

Code (1)

Liangbo-Cheng/mamba_capsule 공식 구현 pytorch

Tasks

Mambaobject-detectionObject Detection

Methods 이 논문이 사용한 방법론

Mamba Foundation models, now powering most of the exciting applications in deep learning, are almost universally based on the Transformer architecture and its core attention module.…

Similar Papers 제목 키워드 기반

Part-Whole Relational Fusion Towards Multi-Modal Scene Understanding

2024-10-19 · Yi Liu, Chengxin Li, Shoukun Xu, Jungong Han

Multi-modal fusion has played a vital role in multi-modal scene understanding. Most existing methods focus on cross-modal fusion involving two modalities, often overlooking more complex multi-modal fusion, which is essen…

Autonomous Drivingobject-detectionObject DetectionSalient Object Detection+1

Fast Inference in Capsule Networks Using Accumulated Routing Coefficients

2019-04-15 · Zhen Zhao, Ashley Kleinhans, Gursharan Sandhu, Ishan Patel 외

We present a method for fast inference in Capsule Networks (CapsNets) by taking advantage of a key insight regarding the routing coefficients that link capsules between adjacent network layers. Since the routing coeffici…

ObjectRotated MNIST

Linguistically Routing Capsule Network for Out-of-Distribution Visual Question Answering

2021-01-01 · ICCV 2021 10 · Qingxing Cao, Wentao Wan, Keze Wang, Xiaodan Liang 외

Generalization on out-of-distribution (OOD) test data is an essential but underexplored topic in visual question answering. Current state-of-the-art VQA models often exploit the biased correlation between data and la…

Novel ConceptsQuestion AnsweringVisual Question AnsweringVisual Question Answering (VQA)

Hierarchical Object-Centric Learning with Capsule Networks

2024-05-30 · Riccardo Renzulli

Capsule networks (CapsNets) were introduced to address convolutional neural networks limitations, learning object-centric representations that are more robust, pose-aware, and interpretable. They organize neurons into gr…

Computational EfficiencyLung Nodule SegmentationObject

Capsule Graph Neural Networks with EM Routing

2021-10-18 · Yu Lei, Jing Zhang

To effectively classify graph instances, graph neural networks need to have the capability to capture the part-whole relationship existing in a graph. A capsule is a group of neurons representing complicated properties o…

Graph Classification