100 citations · 113 across the 7 of their papers we have counts for
7 papers
Composed Image Retrieval for Training-Free Domain Conversion
Nikos Efthymiadis, Bill Psomas, Zakaria Laskar +4
This work addresses composed image retrieval in the context of domain conversion, where the content of a query image is retrieved in the domain specified by the query text. We show…
Evaluation of Resource-Efficient Crater Detectors on Embedded Systems
Simon Vellas, Bill Psomas, Kalliopi Karadima +5
Real-time analysis of Martian craters is crucial for mission-critical operations, including safe landings and geological exploration. This work leverages the latest breakthroughs f…
Composed Image Retrieval for Remote Sensing
Bill Psomas, Ioannis Kakogeorgiou, Nikos Efthymiadis +4
This work introduces composed image retrieval to remote sensing. It allows to query a large image archive by image examples alternated by a textual description, enriching the descr…
Keep It SimPool: Who Said Supervised Transformers Suffer from Attention Deficit?
Bill Psomas, Ioannis Kakogeorgiou, Konstantinos Karantzalos +1
Convolutional networks and vision transformers have different forms of pairwise interactions, pooling across layers and pooling at the end of the network. Does the latter really ne…
OpenFilter: A Framework to Democratize Research Access to Social Media AR Filters
Piera Riccio, Bill Psomas, Francesco Galati +3
Augmented Reality or AR filters on selfies have become very popular on social media platforms for a variety of applications, including marketing, entertainment and aesthetics. Give…
What to Hide from Your Students: Attention-Guided Masked Image Modeling
Ioannis Kakogeorgiou, Spyros Gidaris, Bill Psomas +4
Transformers and masked language modeling are quickly being adopted and explored in computer vision as vision transformers and masked image modeling (MIM). In this work, we argue t…
It Takes Two to Tango: Mixup for Deep Metric Learning
Shashanka Venkataramanan, Bill Psomas, Ewa Kijak +3
Metric learning involves learning a discriminative representation such that embeddings of similar classes are encouraged to be close, while embeddings of dissimilar classes are pus…