-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Chiaroni_2023_ICCV, author = {Chiaroni, Florent and Dolz, Jose and Masud, Ziko Imtiaz and Mitiche, Amar and Ben Ayed, Ismail}, title = {Parametric Information Maximization for Generalized Category Discovery}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1729-1739} }
Parametric Information Maximization for Generalized Category Discovery
Abstract
We introduce a Parametric Information Maximization (PIM) model for the Generalized Category Discovery (GCD) problem. Specifically, we propose a bi-level optimization formulation, which explores a parameterized family of objective functions, each evaluating a weighted mutual information between the features and the latent labels, subject to supervision constraints from the labeled samples. Our formulation mitigates the class-balance bias encoded in standard information maximization approaches, thereby handling effectively both short-tailed and long-tailed data sets. We report extensive experiments and comparisons demonstrating that our PIM model consistently sets new state-of-the-art performances in GCD across six different datasets, more so when dealing with challenging fine-grained problems. Our code: https://github.com/ThalesGroup/pim-generalized-category-discovery.
Related Material