CORTEXA
← Browse
arxivcs.CVcs.AI2026-07-22

Toward Reliable RGB-D Semantic Segmentation: Handling Missing Modalities via Condition Dropout

Xuchen Zhu, Yajuan Wei, Shuang Hao, Jiwei Jiang, Guanxiang Mao, Fang Ren

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.

View free PDFSource page

Related papers

arxivcs.CVcs.AI2026-07-20Cited by 3

DA-Fusion: Deformable Attention-Based RGB-D Fusion Transformer for Unseen Object Instance Segmentation

Yesol Park, Hye-Jung Yoon, Juno Kim, Byoung-Tak Zhang

In logistics automation, precise segmentation of unseen objects is crucial for efficient robotic manipulation in cluttered environments. Tasks such as bin-picking and shelf-picking require robust perception to handle occlusions, varying object shapes, and complex spatial arrangem…

View free PDFSource page
arxivcs.CVcs.AI2026-06-29

Efficient RGB-T Object Detection via Sparse Cross-Modality Fusion

Chao Tian, Zikun Zhou, Chao Yang, Guoqing Zhu, Zhenyu He

RGB-T detectors leverage the complementary strengths of visible and thermal infrared modalities, achieving robust performance under challenging conditions. Many of them resort to heavy dual backbones and exhaustive cross-modality fusion across the entire image, leading to impract…

View free PDFSource page
arxivcs.CVcs.AI2026-06-30

Learning Structurally Consistent Representations for Multi-View Radar Semantic Segmentation

Ali Zia, Muhammad Umer Ramzan, Abdelwahed Khamis, Usman Ali, Abdul Rehman

Radar sensors provide reliable perception under adverse weather and lighting conditions, but their sparse, noisy, and weakly semantic measurements make dense semantic segmentation challenging. Most existing radar segmentation methods rely on grid-based encodings and pairwise inte…

View free PDFSource page
arxivcs.CVcs.AI2026-07-23

DINOde: Continuous Vision-Text Alignment for Open-Vocabulary Semantic Segmentation

Sung-Hoon Yoon, Hoyong Kwon, Changgyoon Oh, Kuk-Jin Yoon

Open-vocabulary semantic segmentation (OVSS) leverages textual semantics to segment objects beyond predefined categories. While the self-supervised model DINOv3 provides strong structured visual representations, its lack of native textual alignment hinders its direct application…

View free PDFSource page
arxivcs.CVcs.AI2026-07-07

ProMoE-FL: Prototype-conditioned Mixture of Experts for Multimodal Federated Learning with Missing Modalities

Aavash Chhetri, Bibek Niroula, Eduard Vazquez, Yash Raj Shrestha, Prashnna Gyawali, Loris Bazzani, et al.

In this paper, we address the problem of multimodal federated learning with missing modality. Existing methods utilize an additional public dataset or perform naive feature synthesis that is based solely on the available modality. To address these limitations, we propose ProMoE-F…

View free PDFSource page