Marc T. Law retweeted
(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: nv-tlabs.github.io/estimatin…
Marc T. Law retweeted
How Much More Data Do I Need? Estimating Requirements for Downstream Tasks
abs: arxiv.org/abs/2207.01725
Marc T. Law retweeted
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 nv-tlabs.github.io/fDAL/.
Marc T. Law retweeted
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!
arxiv.org/abs/2106.11344
w/ @gjzhang1 @MarcTLaw @FidlerSanja @NVIDIAAI




