From Categories to Classifiers: Name-Only Continual Learning by Exploring the Web

Ameya Prabhu, Hasan Abed Al Kader Hammoud, Ser-Nam Lim, Bernard Ghanem, Philip Torr, Adel Bibi
Proceedings of The 3rd Conference on Lifelong Learning Agents, PMLR 274:534-559, 2025.

Abstract

Continual Learning (CL) often relies on the availability of extensive annotated datasets, an assumption that is unrealistically time-consuming and costly in practice. We explore a novel paradigm termed *name-only continual learning* where time and cost constraints prohibit manual annotation. In this scenario, learners adapt to new category shifts using only category names without the luxury of annotated training data. Our proposed solution leverages the expansive and ever-evolving internet to query and download *uncurated* webly-supervised data for image classification. We investigate the reliability of our web data and find them comparable, and in some cases superior, to manually annotated datasets. Additionally, we show that by harnessing the web, we can create support sets that surpass state-of-the-art name-only classification that create support sets using generative models or image retrieval from LAION-5B, achieving up to 25Continual Learning (CL) often relies on the availability of extensive annotated datasets, an assumption that is unrealistically time-consuming and costly in practice. We explore a novel paradigm termed *name-only continual learning* where time and cost constraints prohibit manual annotation. In this scenario, learners adapt to new category shifts using only category names without the luxury of annotated training data. Our proposed solution leverages the expansive and ever-evolving internet to query and download *uncurated* webly-supervised data for image classification. We investigate the reliability of our web data and find them comparable, and in some cases superior, to manually annotated datasets. Additionally, we show that by harnessing the web, we can create support sets that surpass state-of-the-art name-only classification that create support sets using generative models or image retrieval from LAION-5B, achieving up to 25\% boost in accuracy. When applied across varied continual learning contexts, our method consistently exhibits a small performance gap in comparison to models trained on manually annotated datasets. We present *EvoTrends*, a class-incremental dataset made from the web to capture real-world trends, created in just minutes. Overall, this paper underscores the potential of using uncurated webly-supervised data to mitigate the challenges associated with manual data labeling in continual learning.

Cite this Paper


BibTeX
@InProceedings{pmlr-v274-prabhu25a, title = {From Categories to Classifiers: Name-Only Continual Learning by Exploring the Web}, author = {Prabhu, Ameya and Hammoud, Hasan Abed Al Kader and Lim, Ser-Nam and Ghanem, Bernard and Torr, Philip and Bibi, Adel}, booktitle = {Proceedings of The 3rd Conference on Lifelong Learning Agents}, pages = {534--559}, year = {2025}, editor = {Lomonaco, Vincenzo and Melacci, Stefano and Tuytelaars, Tinne and Chandar, Sarath and Pascanu, Razvan}, volume = {274}, series = {Proceedings of Machine Learning Research}, month = {29 Jul--01 Aug}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v274/main/assets/prabhu25a/prabhu25a.pdf}, url = {https://proceedings.mlr.press/v274/prabhu25a.html}, abstract = {Continual Learning (CL) often relies on the availability of extensive annotated datasets, an assumption that is unrealistically time-consuming and costly in practice. We explore a novel paradigm termed *name-only continual learning* where time and cost constraints prohibit manual annotation. In this scenario, learners adapt to new category shifts using only category names without the luxury of annotated training data. Our proposed solution leverages the expansive and ever-evolving internet to query and download *uncurated* webly-supervised data for image classification. We investigate the reliability of our web data and find them comparable, and in some cases superior, to manually annotated datasets. Additionally, we show that by harnessing the web, we can create support sets that surpass state-of-the-art name-only classification that create support sets using generative models or image retrieval from LAION-5B, achieving up to 25Continual Learning (CL) often relies on the availability of extensive annotated datasets, an assumption that is unrealistically time-consuming and costly in practice. We explore a novel paradigm termed *name-only continual learning* where time and cost constraints prohibit manual annotation. In this scenario, learners adapt to new category shifts using only category names without the luxury of annotated training data. Our proposed solution leverages the expansive and ever-evolving internet to query and download *uncurated* webly-supervised data for image classification. We investigate the reliability of our web data and find them comparable, and in some cases superior, to manually annotated datasets. Additionally, we show that by harnessing the web, we can create support sets that surpass state-of-the-art name-only classification that create support sets using generative models or image retrieval from LAION-5B, achieving up to 25\% boost in accuracy. When applied across varied continual learning contexts, our method consistently exhibits a small performance gap in comparison to models trained on manually annotated datasets. We present *EvoTrends*, a class-incremental dataset made from the web to capture real-world trends, created in just minutes. Overall, this paper underscores the potential of using uncurated webly-supervised data to mitigate the challenges associated with manual data labeling in continual learning.} }
Endnote
%0 Conference Paper %T From Categories to Classifiers: Name-Only Continual Learning by Exploring the Web %A Ameya Prabhu %A Hasan Abed Al Kader Hammoud %A Ser-Nam Lim %A Bernard Ghanem %A Philip Torr %A Adel Bibi %B Proceedings of The 3rd Conference on Lifelong Learning Agents %C Proceedings of Machine Learning Research %D 2025 %E Vincenzo Lomonaco %E Stefano Melacci %E Tinne Tuytelaars %E Sarath Chandar %E Razvan Pascanu %F pmlr-v274-prabhu25a %I PMLR %P 534--559 %U https://proceedings.mlr.press/v274/prabhu25a.html %V 274 %X Continual Learning (CL) often relies on the availability of extensive annotated datasets, an assumption that is unrealistically time-consuming and costly in practice. We explore a novel paradigm termed *name-only continual learning* where time and cost constraints prohibit manual annotation. In this scenario, learners adapt to new category shifts using only category names without the luxury of annotated training data. Our proposed solution leverages the expansive and ever-evolving internet to query and download *uncurated* webly-supervised data for image classification. We investigate the reliability of our web data and find them comparable, and in some cases superior, to manually annotated datasets. Additionally, we show that by harnessing the web, we can create support sets that surpass state-of-the-art name-only classification that create support sets using generative models or image retrieval from LAION-5B, achieving up to 25Continual Learning (CL) often relies on the availability of extensive annotated datasets, an assumption that is unrealistically time-consuming and costly in practice. We explore a novel paradigm termed *name-only continual learning* where time and cost constraints prohibit manual annotation. In this scenario, learners adapt to new category shifts using only category names without the luxury of annotated training data. Our proposed solution leverages the expansive and ever-evolving internet to query and download *uncurated* webly-supervised data for image classification. We investigate the reliability of our web data and find them comparable, and in some cases superior, to manually annotated datasets. Additionally, we show that by harnessing the web, we can create support sets that surpass state-of-the-art name-only classification that create support sets using generative models or image retrieval from LAION-5B, achieving up to 25\% boost in accuracy. When applied across varied continual learning contexts, our method consistently exhibits a small performance gap in comparison to models trained on manually annotated datasets. We present *EvoTrends*, a class-incremental dataset made from the web to capture real-world trends, created in just minutes. Overall, this paper underscores the potential of using uncurated webly-supervised data to mitigate the challenges associated with manual data labeling in continual learning.
APA
Prabhu, A., Hammoud, H.A.A.K., Lim, S., Ghanem, B., Torr, P. & Bibi, A.. (2025). From Categories to Classifiers: Name-Only Continual Learning by Exploring the Web. Proceedings of The 3rd Conference on Lifelong Learning Agents, in Proceedings of Machine Learning Research 274:534-559 Available from https://proceedings.mlr.press/v274/prabhu25a.html.

Related Material