4.3k citations · 19.2k across the 101 of their papers we have counts for
5 papers · 2 filters
Improving information retention in large scale online continual learning
Zhipeng Cai, Vladlen Koltun, Ozan Sener
Given a stream of data sampled from non-stationary distributions, online continual learning (OCL) aims to adapt efficiently to new data while retaining existing knowledge. The typi…
Global Tracking Transformers
Xingyi Zhou, Tianwei Yin, Vladlen Koltun +1
We present a novel transformer-based architecture for global multi-object tracking. Our network takes a short sequence of frames as input and produces global trajectories for all o…
Unsupervised Contrastive Domain Adaptation for Semantic Segmentation
Feihu Zhang, Vladlen Koltun, Philip Torr +2
Semantic segmentation models struggle to generalize in the presence of domain shift. In this paper, we introduce contrastive learning for feature alignment in cross-domain adaptati…
Dancing under the stars: video denoising in starlight
Kristina Monakhova, Stephan R. Richter, Laura Waller +1
Imaging in low light is extremely challenging due to low photon counts. Using sensitive CMOS cameras, it is currently possible to take videos at night under moonlight (0.05-0.3 lux…
Language-driven Semantic Segmentation
Boyi Li, Kilian Q. Weinberger, Serge Belongie +2
We present LSeg, a novel model for language-driven semantic image segmentation. LSeg uses a text encoder to compute embeddings of descriptive input labels (e.g., "grass" or "buildi…