CVAIROMar 30, 2023

Complementary Random Masking for RGB-Thermal Semantic Segmentation

arXiv:2303.17386v253 citationsh-index: 28Has Code
Originality Incremental advance
AI Analysis

This addresses the need for reliable semantic scene understanding in adverse conditions, offering an incremental improvement in multi-modal fusion methods.

The paper tackles the problem of over-reliance on single modalities in RGB-thermal semantic segmentation by proposing a complementary random masking strategy and self-distillation loss, achieving state-of-the-art performance on three benchmarks.

RGB-thermal semantic segmentation is one potential solution to achieve reliable semantic scene understanding in adverse weather and lighting conditions. However, the previous studies mostly focus on designing a multi-modal fusion module without consideration of the nature of multi-modality inputs. Therefore, the networks easily become over-reliant on a single modality, making it difficult to learn complementary and meaningful representations for each modality. This paper proposes 1) a complementary random masking strategy of RGB-T images and 2) self-distillation loss between clean and masked input modalities. The proposed masking strategy prevents over-reliance on a single modality. It also improves the accuracy and robustness of the neural network by forcing the network to segment and classify objects even when one modality is partially available. Also, the proposed self-distillation loss encourages the network to extract complementary and meaningful representations from a single modality or complementary masked modalities. Based on the proposed method, we achieve state-of-the-art performance over three RGB-T semantic segmentation benchmarks. Our source code is available at https://github.com/UkcheolShin/CRM_RGBTSeg.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes