Bi-directional Cross-Modality Feature Propagation with Separation-and-Aggregation Gate for RGB-D Semantic Segmentation

Xiaokang Chen; Kwan-Yee Lin; Jingbo Wang; Wayne Wu; Chen Qian; Hongsheng Li; Gang Zeng

ECCV 2020poster431 citations

Bi-directional Cross-Modality Feature Propagation with Separation-and-Aggregation Gate for RGB-D Semantic Segmentation

Xiaokang Chen, Kwan-Yee Lin, Jingbo Wang, Wayne Wu, Chen Qian, Hongsheng Li, Gang Zeng

Abstract

Depth information has proven to be a useful cue in the semantic segmentation of RGB-D images for providing a geometric counterpart to the RGB representation. Most existing works simply assume that depth measurements are accurate and well-aligned with the RGB pixels and models the problem as a cross-modal feature fusion to obtain better feature representations to achieve more accurate segmentation. This, however, may not lead to satisfactory results as actual depth data are generally noisy, which might worsen the accuracy as the networks go deeper.

BibTeX

@inproceedings{eccv2020_bidirectionalcro,
  title = {Bi-directional Cross-Modality Feature Propagation with Separation-and-Aggregation Gate for RGB-D Semantic Segmentation},
  author = {Xiaokang Chen and Kwan-Yee Lin and Jingbo Wang and Wayne Wu and Chen Qian and Hongsheng Li and Gang Zeng},
  booktitle = {ECCV 2020},
  year = {2020}
}