Hugging Face Trending Papers

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

Read the original on Hugging Face Trending Papers →

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.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

arXiv AI
Jun 16

ActiveSAM: Image-Conditional Class Pruning for Fast and Accurate Open-Vocabulary Segmentation

arXiv:2606. 16996v1 Announce Type: cross Abstract: Segment Anything Model 3 (SAM 3) provides a strong frozen backbone for concept-prompted segmentation, but applying it directly to open-vocabulary semantic segmentation (OVSS) is inefficient: full-resolution decoding is typically run over the entire dataset vocabulary, whereas each image contains only a small active subset of classes.

By Tran Dinh Tien, Zhiqiang Shen