AsymFormer: Asymmetrical Cross-Modal Representation Learning for Mobile Platform Real-Time RGB-D Semantic Segmentation

arXiv:2309.14065v5 Announce Type: replace
Abstract: In the realm of robotic intelligence, achieving efficient and precise RGB-D semantic segmentation is a key cornerstone. State-of-the-art multimodal semantic segmentation methods, primarily rooted in symmetrical skeleton networks, find it challenging to harmonize computational efficiency and precision. In this work, we propose AsymFormer, a novel network for real-time RGB-D semantic segmentation, which targets the minimization of superfluous parameters by optimizing the distribution of computational resources and introduces an asymmetrical backbone to allow for the effective …

abstract art arxiv computational cs.cv efficiency intelligence key mobile modal multimodal networks platform precision real-time representation representation learning rgb-d robotic robotic intelligence segmentation semantic state type work