4 papers · 1 filter
EfficientXpert: Efficient Domain Adaptation for Large Language Models via Propagation-Aware Pruning
Songlin Zhao, Michael Pitts, Zhuwei Qin
Deploying domain-specialized large language models on resource-constrained hardware motivates reducing both adaptation cost and the number of retained weights. LoRA lowers adaptati…
Is the medical image segmentation problem solved? A survey of current developments and future directions
Guoping Xu, Jayaram K. Udupa, Jax Luo +8
Medical image segmentation has advanced rapidly over the past two decades, largely driven by deep learning, which has enabled accurate and efficient delineation of cells, tissues,…
Segment Anything for Video: A Comprehensive Review of Video Object Segmentation and Tracking from Past to Future
Guoping Xu, Jayaram K. Udupa, Yajun Yu +4
Video Object Segmentation and Tracking (VOST) presents a complex yet critical challenge in computer vision, requiring robust integration of segmentation and tracking across tempora…
SegImgNet: Segmentation-Guided Dual-Branch Network for Retinal Disease Diagnoses
Xinwei Luo, Songlin Zhao, Yun Zong +3
Retinal image plays a crucial role in diagnosing various diseases, as retinal structures provide essential diagnostic information. However, effectively capturing structural feature…