arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2203.04838cs.CVcs.ROeess.IV
收藏

CMX:基于Transformer的RGB-X语义分割跨模态融合

CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers

Karlsruhe Institute of Technology(卡尔斯鲁厄理工学院);Hunan University(湖南大学);NIO(蔚来);ByteDance Inc.(字节跳动)

Jiaming Zhang, Huayao Liu, Kailun Yang, Xinxin Hu, Ruiping Liu, Rainer Stiefelhagen

AI总结:

提出统一融合框架CMX,通过跨模态特征校正模块和特征融合模块实现RGB与多种补充模态的有效融合,在多个多模态语义分割基准上达到最先进性能。

摘要:

基于图像分割的场景理解是自动驾驶车辆的关键组件。通过利用来自补充模态(X模态)的互补特征,可以推进RGB图像的像素级语义分割。然而,由于不同模态之间传感器特性的差异,用模态无关的模型覆盖各种传感器仍然是一个未解决的问题。与以往特定于模态的方法不同,在这项工作中,我们提出了一个用于RGB-X语义分割的统一融合框架CMX。为了在不同模态间良好泛化(通常包括补充信息和不确定性),统一的跨模态交互对于模态融合至关重要。具体来说,我们设计了一个跨模态特征校正模块(CM-FRM),通过利用一个模态的特征来校正另一个模态的特征,从而校准双模态特征。对于校正后的特征对,我们部署了一个特征融合模块(FFM),在混合之前执行长程上下文的充分交换。为了验证CMX,我们首次统一了五种与RGB互补的模态,即深度、热成像、偏振、事件和LiDAR。大量实验表明,CMX对各种多模态融合具有良好的泛化能力,在五个RGB-Depth基准测试,以及RGB-Thermal、RGB-Polarization和RGB-LiDAR数据集上取得了最先进的性能。此外,为了研究对密集-稀疏数据融合的泛化能力,我们基于EventScape数据集建立了一个RGB-Event语义分割基准,CMX在该基准上创造了新的最先进水平。CMX的源代码已在 https://github.com/huaaaliu/RGBX_Semantic_Segmentation 公开。

英文摘要:

Scene understanding based on image segmentation is a crucial component of autonomous vehicles. Pixel-wise semantic segmentation of RGB images can be advanced by exploiting complementary features from the supplementary modality (X-modality). However, covering a wide variety of sensors with a modality-agnostic model remains an unresolved problem due to variations in sensor characteristics among different modalities. Unlike previous modality-specific methods, in this work, we propose a unified fusion framework, CMX, for RGB-X semantic segmentation. To generalize well across different modalities, that often include supplements as well as uncertainties, a unified cross-modal interaction is crucial for modality fusion. Specifically, we design a Cross-Modal Feature Rectification Module (CM-FRM) to calibrate bi-modal features by leveraging the features from one modality to rectify the features of the other modality. With rectified feature pairs, we deploy a Feature Fusion Module (FFM) to perform sufficient exchange of long-range contexts before mixing. To verify CMX, for the first time, we unify five modalities complementary to RGB, i.e., depth, thermal, polarization, event, and LiDAR. Extensive experiments show that CMX generalizes well to diverse multi-modal fusion, achieving state-of-the-art performances on five RGB-Depth benchmarks, as well as RGB-Thermal, RGB-Polarization, and RGB-LiDAR datasets. Besides, to investigate the generalizability to dense-sparse data fusion, we establish an RGB-Event semantic segmentation benchmark based on the EventScape dataset, on which CMX sets the new state-of-the-art. The source code of CMX is publicly available at https://github.com/huaaaliu/RGBX_Semantic_Segmentation.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑