3 papers
cs.CV2024
SLIM: Spuriousness Mitigation with Minimal Human Annotations
Xiwei Xuan, Ziquan Deng, Hsuan-Tien Lin +1
Recent studies highlight that deep learning models often learn spurious features mistakenly linked to labels, compromising their reliability in real-world scenarios where such corr…
cs.CV2024
USE: Universal Segment Embeddings for Open-Vocabulary Image Segmentation
Xiaoqi Wang, Wenbin He, Xiwei Xuan +8
The open-vocabulary image segmentation task involves partitioning images into semantically meaningful segments and classifying them with flexible text-defined categories. The recen…
cs.HC2023
LabelVizier: Interactive Validation and Relabeling for Technical Text Annotations
Xiaoyu Zhang, Xiwei Xuan, Alden Dima +2
With the rapid accumulation of text data produced by data-driven techniques, the task of extracting "data annotations"--concise, high-quality data summaries from unstructured raw t…