English

Large-scale Pre-trained Models are Surprisingly Strong in Incremental Novel Class Discovery

Computer Vision and Pattern Recognition 2024-08-26 v5 Machine Learning

Abstract

Discovering novel concepts in unlabelled datasets and in a continuous manner is an important desideratum of lifelong learners. In the literature such problems have been partially addressed under very restricted settings, where novel classes are learned by jointly accessing a related labelled set (e.g., NCD) or by leveraging only a supervisedly pre-trained model (e.g., class-iNCD). In this work we challenge the status quo in class-iNCD and propose a learning paradigm where class discovery occurs continuously and truly unsupervisedly, without needing any related labelled set. In detail, we propose to exploit the richer priors from strong self-supervised pre-trained models (PTM). To this end, we propose simple baselines, composed of a frozen PTM backbone and a learnable linear classifier, that are not only simple to implement but also resilient under longer learning scenarios. We conduct extensive empirical evaluation on a multitude of benchmarks and show the effectiveness of our proposed baselines when compared with sophisticated state-of-the-art methods. The code is open source.

Keywords

Cite

@article{arxiv.2303.15975,
  title  = {Large-scale Pre-trained Models are Surprisingly Strong in Incremental Novel Class Discovery},
  author = {Mingxuan Liu and Subhankar Roy and Zhun Zhong and Nicu Sebe and Elisa Ricci},
  journal= {arXiv preprint arXiv:2303.15975},
  year   = {2024}
}

Comments

Accepted as a conference paper to ICPR 2024; The code is opensource

R2 v1 2026-06-28T09:37:55.112Z