English

CoReS: Compatible Representations via Stationarity

Computer Vision and Pattern Recognition 2023-03-29 v3 Machine Learning

Abstract

Compatible features enable the direct comparison of old and new learned features allowing to use them interchangeably over time. In visual search systems, this eliminates the need to extract new features from the gallery-set when the representation model is upgraded with novel data. This has a big value in real applications as re-indexing the gallery-set can be computationally expensive when the gallery-set is large, or even infeasible due to privacy or other concerns of the application. In this paper, we propose CoReS, a new training procedure to learn representations that are \textit{compatible} with those previously learned, grounding on the stationarity of the features as provided by fixed classifiers based on polytopes. With this solution, classes are maximally separated in the representation space and maintain their spatial configuration stationary as new classes are added, so that there is no need to learn any mappings between representations nor to impose pairwise training with the previously learned model. We demonstrate that our training procedure largely outperforms the current state of the art and is particularly effective in the case of multiple upgrades of the training-set, which is the typical case in real applications.

Keywords

Cite

@article{arxiv.2111.07632,
  title  = {CoReS: Compatible Representations via Stationarity},
  author = {Niccolo Biondi and Federico Pernici and Matteo Bruni and Alberto Del Bimbo},
  journal= {arXiv preprint arXiv:2111.07632},
  year   = {2023}
}

Comments

in IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023. Code: https://github.com/NiccoBiondi/cores-compatibility

R2 v1 2026-06-24T07:38:30.660Z