Fig. 2. Qualitative results for an abdomen image.
GT is for ‘Ground Truth’. This is the caption that was provided by the sonographer directly. DC is for ‘Dual Curriculum’. This is the caption that was generated by a model that was trained with a dual curriculum. I1-CF-DC is for ‘Image-First Course-Focused Dual Curriculum’. This is the caption that was generated by a model that was trained with an I1-CF-DC. T1-CF-DC is for ‘Text-First Course-Focused Dual Curriculum’. This is the caption that was generated by a model that was trained with a T1-CF-DC.
