Online Backfilling with No Regret for Large-Scale Image Retrieval

no code implementations • 10 Jan 2023 • Seonguk Seo, Mustafa Gokhan Uzunbas, Bohyung Han, Sara Cao, Joena Zhang, Taipeng Tian, Ser-Nam Lim

Backfilling is the process of re-extracting all gallery embeddings from upgraded models in image retrieval systems.

Contrastive Learning Image Retrieval +1

A Reinforcement Learning Approach to the View Planning Problem

no code implementations • CVPR 2017 • Mustafa Devrim Kaba, Mustafa Gokhan Uzunbas, Ser Nam Lim

We present a Reinforcement Learning (RL) solution to the view planning problem (VPP), which generates a sequence of view points that are capable of sensing all accessible area of a given object represented as a 3D model.

reinforcement-learning Reinforcement Learning (RL)