Sign in
Reward Finetuning for Faster and More Accurate Unsupervised Object Discovery.
Katie Z. Luo
Zhenzhen Liu
Xiangyu Chen
Yurong You
Sagie Benaim
Cheng Perng Phoo
Mark E. Campbell
Wen Sun
Bharath Hariharan
Kilian Q. Weinberger
Published in:
CoRR (2023)
Keyphrases
</>
unsupervised learning
reinforcement learning
semi supervised
data driven
database
data sets
real world
information systems
optimal solution
high accuracy
high precision
highly accurate
memory efficient
unsupervised manner
average reward