5 papers
Prefer-DAS: Learning from Local Preferences and Sparse Prompts for Domain Adaptive Segmentation of Electron Microscopy
Jiabao Chen, Shan Xiong, Jialin Peng
Domain adaptive segmentation (DAS) is a promising paradigm for delineating intracellular structures from various large-scale electron microscopy (EM) without incurring extensive an…
Instance-Aware Pseudo-Labeling and Class-Focused Contrastive Learning for Weakly Supervised Domain Adaptive Segmentation of Electron Microscopy
Shan Xiong, Jiabao Chen, Ye Wang +1
Annotation-efficient segmentation of the numerous mitochondria instances from various electron microscopy (EM) images is highly valuable for biological and neuroscience research. A…
Kant: An Efficient Unified Scheduling System for Large-Scale AI Clusters
Lingling Zeng, Gen Zhang, Jialin Peng +3
As AI cluster sizes continue to expand and the demand for large-language-model (LLM) training and inference workloads grows rapidly, traditional scheduling systems face significant…
Prompt-DAS: Annotation-Efficient Prompt Learning for Domain Adaptive Semantic Segmentation of Electron Microscopy Images
Jiabao Chen, Shan Xiong, Jialin Peng
Domain adaptive segmentation (DAS) of numerous organelle instances from large-scale electron microscopy (EM) is a promising way to enable annotation-efficient learning. Inspired by…
BiPrompt-SAM: Enhancing Image Segmentation via Explicit Selection between Point and Text Prompts
Suzhe Xu, Jialin Peng, Chengyuan Zhang
Segmentation is a fundamental task in computer vision, with prompt-driven methods gaining prominence due to their flexibility. The Segment Anything Model (SAM) excels at point-prom…