33 citations · 53 across the 4 of their papers we have counts for
3 papers · 1 filter
Mask-Adapter: The Devil is in the Masks for Open-Vocabulary Segmentation
Yongkang Li, Tianheng Cheng, Bin Feng +2
Recent open-vocabulary segmentation methods adopt mask generators to predict segmentation masks and leverage pre-trained vision-language models, e.g., CLIP, to classify these masks…
Symphonize 3D Semantic Scene Completion with Contextual Instance Queries
Haoyi Jiang, Tianheng Cheng, Naiyu Gao +4
`3D Semantic Scene Completion (SSC) has emerged as a nascent and pivotal undertaking in autonomous driving, aiming to predict voxel occupancy within volumetric scenes. However, pre…
IoU-balanced Loss Functions for Single-stage Object Detection
Shengkai Wu, Jinrong Yang, Xinggang Wang +1
Single-stage object detectors have been widely applied in computer vision applications due to their high efficiency. However, we find that the loss functions adopted by single-stag…