Losing the name before the box: measuring and repairing what narrow fine-tuning costs a detector outside its deployment vocabulary
在盒子之前失去名字:测量并修复窄域微调对检测器在其部署词汇之外造成的代价
机构 * Korea Electronics Technology Institute(韩国电子技术研究院)
AI总结 本研究提出纵向协议测量窄域微调对检测器覆盖预训练词汇外对象的影响,发现覆盖度下降而域内精度上升,并提出无需训练的修复方法,混合预训练状态可恢复覆盖且域内精度损失极小。
Comments 25 pages, 3 figures. Supplementary material (69 pages) is included as an ancillary file. Submitted to the International Journal of Computer Vision