Large-scale Pre-trained Models are Surprisingly Strong in Incremental Novel Class Discovery
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914921055256576 |
|---|---|
| author | Liu, Mingxuan Roy, Subhankar Zhong, Zhun Sebe, Nicu Ricci, Elisa |
| author_facet | Liu, Mingxuan Roy, Subhankar Zhong, Zhun Sebe, Nicu Ricci, Elisa |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2303_15975 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Large-scale Pre-trained Models are Surprisingly Strong in Incremental Novel Class Discovery Liu, Mingxuan Roy, Subhankar Zhong, Zhun Sebe, Nicu Ricci, Elisa Computer Vision and Pattern Recognition Machine Learning 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. |
| title | Large-scale Pre-trained Models are Surprisingly Strong in Incremental Novel Class Discovery |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2303.15975 |