Semi-supervised object detection (SSOD) in aerial imagery is significantly hampered by extreme object scale variations, primarily due to diverse spatial resolutions inherent in aerial data, measurable through Ground Sample Distance (GSD). Existing SSOD methods often overlook this crucial GSD information, leading to unr...
Yuqiu Li, Jian Xue, Fan Li et al.· IEEE Transactions on Image P...· 0 citations
Visual grounding combines image--language understanding with geometric prediction, yet autoregressive multimodal models often express a box as a coordinate sequence. Sequential decoding adds computation to the multimodal processing needed for localization. Adapting these representations to box geometry offers a route t...
This work proposes a conditional Flow Matching (CFM) based framework for efficient 3D medical image segmentation that maintains competitive segmentation accuracy while achieving an inference time of only 1.14 seconds per volume, offering a clear efficiency advantage over existing generative segmentation methods.
Y. Yilihamu, Jian Xue, Chuang Jia et al.· International Conference on...· 0 citations
Experiments on standard referring-expression grounding benchmarks show consistent region-level improvements over strong coordinate-generating baselines, demonstrating that ground-truth boxes can provide useful privileged guidance beyond serving as coordinate labels.
Xiuyuan Zhu, Ke Lu, Hao Wu et al.· arXiv.org· 0 citations
The results show that structured coordinate generation provides an effective approach to generative visual grounding and Hi-Token encodes each coordinate with axis-specific tokens for the hundreds, tens, and ones digits, which adds coarse-to-fine structure and increases token reuse while retaining the existing VLM arch...
Xiuyuan Zhu, Ke Lu, Kun Dong et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
