Generalized logit adjustment: Calibrating fine-tuned models by removing label bias in foundation models

• المؤلفون الرئيسيون: ZHU, Beier, TANG, Kaihua, SUN, Qianru, ZHANG, Hanwang
• التنسيق: text
• اللغة: English
• منشور في: Institutional Knowledge at Singapore Management University 2023
• الموضوعات: Databases and Information Systems
• الوصول للمادة أونلاين: https://ink.library.smu.edu.sg/sis_research/8473; https://ink.library.smu.edu.sg/context/sis_research/article/9476/viewcontent/Generalized_Logit_Adjustment__Calibrating_Fine_tuned_Models_by_Removing_Label_Bias_in_Foundation_Models__1_.pdf

Foundation models like CLIP allow zero-shot transfer on various tasks without additional training data. Yet, the zero-shot performance is less competitive than a fully supervised one. Thus, to enhance the performance, fine-tuning and ensembling are also commonly adopted to better fit the downstream...