I am a PhD student at Boston University, advised by Prof. Venkatesh Saligrama.
I also work with Prof. Eshed Ohn-Bar.
My research is mainly about efficient training
for deep leanring algorithm and its application on computer vision and autonomous driving.
Prior to BU, I got my Master degree at Brown University working with Prof. Benjamin Kimia on vision navigation.
I have just spent a wonderful summer in Computer Vision team at AWS with Yuting Zhang, Qi Dong and Zhuowen Tu working on vision foundation model.
I am also fortunate to intern at Dataminr and Bosch Research before.
DOP can automatically parse a object into semantically salient parts. Fine-Grained Few-shot learning get SOTA performance utilizing such representations.