做语义分割的可以看看 ConD，训练完一个模型就能同时应付缺 RGB 或缺深度的情况，还能保持全模态精度。简单有效，代码也快开源了。
针对 RGB-D 语义分割模型在缺失 RGB 或深度模态时性能骤降的问题，研究者提出 Condition Dropout (ConD) 方法。ConD 在预训练模型基础上增加第二阶段训练，随机模拟完整、缺 RGB 或缺深度输入，冻结原编码器并训练带有零初始化特征注入的副本。在 NYU-Depth V2 和 SUN RGB-D 数据集上，ConD 在缺失模态下显著提升鲁棒性，且完整模态下略有增益。代码将在论文接收后公开。
Toward Reliable RGB-D Semantic Segmentation: Handling Missing Modalities via Condition Dropout
RGB-D semantic segmentation has achieved remarkable progress, yet most models assume that RGB and depth are always available. In practice, failures or occlusions of surveillance sensors often remove one modality. Although RGB or depth alone can contain sufficient cues, models trained only on full-modality inputs fail to exploit the remaining modality once one is missing, causing severe degradation. We tackle this issue with a simple continued-training paradigm, \emph{Condition Dropout (ConD)}, which mitigates degradation while preserving full-modality accuracy. Starting from a pretrained RGB-D model, ConD adds a second stage that randomly simulates complete, RGB-missing, and depth-missing inputs, freezes the original encoders, and trains copied encoders with zero-initialized feature injection. Experiments on NYU-Depth V2 and SUN RGB-D show that ConD improves robustness under missing modalities and even yields slight gains when modalities are complete. Our code will be made publicly available upon acceptance.