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

TL;DR

This paper introduces a novel cross-modality encoder with separation-and-aggregation gating for RGB-D semantic segmentation, effectively handling noisy depth data and improving feature fusion between RGB and depth modalities.

Contribution

The work proposes a unified encoder with a separation-and-aggregation gating mechanism and bi-directional multi-step propagation to enhance RGB-D feature fusion and segmentation accuracy.

Findings

Outperforms state-of-the-art methods on challenging datasets

Effectively handles noisy and misaligned depth data

Improves feature calibration and fusion in RGB-D segmentation

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. In this paper, we propose a unified and efficient Cross-modality Guided Encoder to not only effectively recalibrate RGB feature responses, but also to distill accurate depth information via multiple stages and aggregate the two recalibrated representations alternatively. The key of the proposed architecture is a novel Separation-and-Aggregation Gating operation that jointly filters and recalibrates both representations before cross-modality aggregation. Meanwhile, a Bi-direction Multi-step Propagation strategy is introduced, on the one hand, to help to propagate and fuse information between the two modalities, and on the other hand, to preserve their specificity along the long-term propagation process. Besides, our proposed encoder can be easily injected into the previous encoder-decoder structures to boost their performance on RGB-D semantic segmentation. Our model outperforms state-of-the-arts consistently on both in-door and out-door challenging datasets. Code of this work is available at https://charlescxk.github.io/