Retrieve and Segment: Are a Few Examples Enough to Bridge the Supervision Gap in Open-Vocabulary Segmentation?
Bridging the supervision gap in open-vocabulary segmentation using a few pixel-level annotated examples along with class names.
PhD Student at CTU Prague (VRG).
I will be attending the ELLIS Winter School in Amsterdam.
Event detailsOur work "Only-Style" won a Best Paper Award in the Personalization in Generative AI Workshop (ICCV Workshops).
Read the paperI am a first year PhD candidate in the Visual Recognition Group in Prague, under the supervision of Giorgos Tolias, focusing on instance-level recognition. In a few words, I am trying to create models that recognize (retrieve-classify-detect-segment) particular objects in an open-world environment.
Bridging the supervision gap in open-vocabulary segmentation using a few pixel-level annotated examples along with class names.
A re-examination of attentive probing methods focusing on efficiency-oriented insights.
A method that achieves style-consistent image generation without content leakage.