Marc T. Law

Research scientist @NVIDIA.

[Marc T. Law @MarcTLaw]

@nmwsharp @nvidia @FidlerSanja Welcome to our team. :)

[Rafid Mahmood @RafidRMahmood]

(1/7) Our #CVPR2022 paper “How Much More Data Do I Need? Estimating Requirements For Downstream Tasks” explores data collection practices!

w/ @james_r_lucas @davidjesusacu @lidaiqing @PhilionJonah @ALVAREZ_JOSEM @ZhidingYu @FidlerSanja @MarcTLaw

Webpage: https://t.co/dtjnS9zHB3

[AK @_akhaliq]

How Much More Data Do I Need? Estimating Requirements for Downstream Tasks
abs: https://t.co/RNXT4IRIaL

[Marc T. Law @MarcTLaw]

@james_r_lucas @nvidia @FidlerSanja Congrats and welcome! It will be our fifth year together in the same teams. 🥳

[David Acuna @davidjesusacu]

We just release the f-DAL source code into an easy-to-use library that allows integrating f-DAL with existing pipelines by only changing a few lines of code. Check it out https://t.co/i94iQMnIEU.

[David Acuna @davidjesusacu]

Excited to share fDAL #ICML2021
We connect theory and algorithms for domain adaptation using a novel f-divergence based bound. fDAL explains existing algorithms, shows their bottlenecks and how to fix them!

https://t.co/WAGzclGhu3
w/ @gjzhang1 @MarcTLaw @FidlerSanja @NVIDIAAI