Stationary representations: Optimally approximating compatibility and implications for improved model replacements
Learning compatible representations enables the interchangeable use of semantic features
as models are updated over time. This is particularly relevant in search and retrieval systems …
as models are updated over time. This is particularly relevant in search and retrieval systems …
Towards cross-modal backward-compatible representation learning for vision-language models
Modern retrieval systems often struggle with upgrading to new and more powerful models
due to the incompatibility of embeddings between the old and new models. This …
due to the incompatibility of embeddings between the old and new models. This …
Asymmetric image retrieval with cross model compatible ensembles
The asymmetrical retrieval setting is a well suited solution for resource constrained
applications such as face recognition and image retrieval. In this setting, a large model is …
applications such as face recognition and image retrieval. In this setting, a large model is …
Backward-Compatible Aligned Representations via an Orthogonal Transformation Layer
Visual retrieval systems face significant challenges when updating models with improved
representations due to misalignment between the old and new representations. The costly …
representations due to misalignment between the old and new representations. The costly …
Asymmetric Image Retrieval with Cross Model Compatible Ensembles
The asymmetrical retrieval setting is a well suited solution for resource constrained
applications such as face recognition and image retrieval. In this setting, a large model is …
applications such as face recognition and image retrieval. In this setting, a large model is …