AI RESEARCH

IBCapsNet: Information Bottleneck Capsule Network for Noise-Robust Representation Learning

arXiv CS.CV

ArXi:2603.20682v1 Announce Type: new Capsule networks (CapsNets) are superior at modeling hierarchical spatial relationships but suffer from two critical limitations: high computational cost due to iterative dynamic routing and poor robustness under input corruptions. To address these issues, we propose IBCapsNet, a novel capsule architecture grounded in the Information Bottleneck (IB) principle.