# GenOL: Generating Diverse Examples for Name-only Online Learning

arXiv: https://arxiv.org/abs/2403.10853 · HTML: https://mlsanity.com/paper/2403.10853/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Mar 2024.

## Built on by (most cited first, 9 of 9)

- [Recent Advances of Foundation Language Models-based Continual Learning: A Survey](https://mlsanity.com/paper/2405.18653/) (2024)
- [CLAP4CLIP: Continual Learning with Probabilistic Finetuning for Vision-Language Models](https://mlsanity.com/paper/2403.19137/) (2024)
- [Slight Corruption in Pre-training Data Makes Better Diffusion Models](https://mlsanity.com/paper/2405.20494/) (2024)
- [OASIS: Online Sample Selection for Continual Visual Instruction Tuning](https://mlsanity.com/paper/2506.02011/) (2025)
- [Beyond Cosine Decay: On the effectiveness of Infinite Learning Rate Schedule for Continual Pre-training](https://mlsanity.com/paper/2503.02844/) (2025)
- [Adapting Vision-Language Models Without Labels: A Comprehensive Survey](https://mlsanity.com/paper/2508.05547/) (2025)
- [When Pretty Isn't Useful: Investigating Why Modern Text-to-Image Models Fail as Reliable Training Data Generators](https://mlsanity.com/paper/2602.19946/) (2026)
- [Reinforced Interactive Continual Learning via Real-time Noisy Human Feedback](https://mlsanity.com/paper/2505.09925/) (2025)
- [Diffusion-Classifier Synergy: Reward-Aligned Learning via Mutual Boosting Loop for FSCIL](https://mlsanity.com/paper/2510.03608/) (2025)

## Abstract (arXiv)

Online learning methods often rely on supervised data. However, under data distribution shifts, such as in continual learning (CL), where continuously arriving online data streams incorporate new concepts (e.g., classes), real-time manual annotation is impractical due to its costs and latency, which hinder real-time adaptation. To alleviate this, 'name-only' setup has been proposed, requiring only the name of concepts, not the supervised samples. A recent approach tackles this setup by supplementing data with web-scraped images, but such data often suffers from issues of data imbalance, noise, and copyright. To overcome the limitations of both human supervision and webly supervision, we propose GenOL using generative models for name-only training. But naive application of generative models results in limited diversity of generated data. Here, we enhance (i) intra-diversity, the diversity of images generated by a single model, by proposing a diverse prompt generation method that generates diverse text prompts for text-to-image models, and (ii) inter-diversity, the diversity of images generated by multiple generative models, by introducing an ensemble strategy that selects minimally overlapping samples. We empirically validate that the proposed frameworkname outperforms prior arts, even a model trained with fully supervised data by large margins, in various tasks, including image recognition and multi-modal visual reasoning.