lightbulbPractical problem主动学习与机器教学中的不确定性复杂的多标签数据标注既耗时又容易出错,影响模型性能。IUI '21Increasing the Speed and Accuracy of Data Labeling Through an AI Assisted Interface
lightbulbPractical problem主动学习与机器教学中的不确定性非专业人士很难高质量地为特定领域的数据集标注。IUI '25Empowering Medical Data Labeling for Non-Experts with DANNY: Enhancing Accuracy and Mitigating Over-Reliance on AI
lightbulbPractical problem主动学习与机器教学中的不确定性分析师可能过度信任或低估主动学习系统,导致决策错误。IUI '24Assessing Trust in Active Learning Systems: Insights from Query Policies and Uncertainty Visualization
lightbulbPractical problem主动学习与机器教学中的不确定性用户在冷启动阶段难以高效收集标注文本数据。IUI '22Trade-offs in Sampling and Search for Early-stage Interactive Machine Learning
lightbulbPractical problem主动学习与机器教学中的不确定性非技术用户在使用AI教分类器时,难以理解模型行为和预测不确定性。IUI '22Deep Learning Uncertainty in Machine Teaching
lightbulbPractical problem主动学习与机器教学中的不确定性医疗领域专家难以在自动化标注中既提高效率又避免接受错误推荐。CHI '21Assessing the Impact of Automated Suggestions on Decision Making: Domain Experts Mediate Model Errors but Take Less Initiative