Szczegóły publikacji
Opis bibliograficzny
Advancing ConvNet architectures: a novel XGB-based pruning algorithm for transfer learning efficiency / Igor Ratajczyk, Adrian HORZYK // W: ECAI 2024 [Dokument elektroniczny] : 27th European Conference on Artificial Intelligence : 19-24 October 2024, Santiago de Compostella, Spain : including 13th conference on Prestigious Applications of Intelligent Systems (PAIS 2024) / ed. by U. Endriss, [et al.]. — Wersja do Windows. — Dane tekstowe. — [Amsterdam] : IOS Press, cop. 2024. — ( Frontiers in Artificial Intelligence and Applications ; ISSN 0922-6389 ; vol. 392 ). — e-ISBN: 978-1-64368-548-9. — S. 2114–2121. — Wymagania systemowe: Adobe Reader. — Bibliogr. s. 2121, Abstr.
Autorzy (2)
Dane bibliometryczne
| ID BaDAP | 156242 |
|---|---|
| Data dodania do BaDAP | 2024-11-18 |
| Tekst źródłowy | URL |
| DOI | 10.3233/FAIA240730 |
| Rok publikacji | 2024 |
| Typ publikacji | materiały konferencyjne (aut.) |
| Otwarty dostęp |  |
| Creative Commons | |
| Wydawca | IOS Press |
| Konferencja | European Conference on Artificial Intelligence 2024 |
| Czasopismo/seria | Frontiers in Artificial Intelligence and Applications |
Abstract
This paper introduces a novel pruning method designed for transfer-learning models in computer vision, leveraging XGBoost to enhance model efficiency through simultaneous depth and width pruning. Contemporary computer vision tasks often rely on transfer learning due to its efficiency after short training periods. However, these pre-trained architectures, while robust, are typically overparameterized, leading to inefficiencies when fine-tuning for simpler problems. Our approach utilizes Parallel Tree Boosting as a surrogate neural classifier to evaluate and prune unnecessary convolutional filters in these architectures effectively. This method addresses the challenge of interference that is often present in transfer-learning models and enables a significant reduction in the size of the model. We demonstrate that it is feasible to achieve both depth and width pruning concurrently, allowing for substantial reductions in model complexity without compromising performance. Experimental results show that our proposed XGB-based Pruner not only reduces the model size by nearly 50% but also improves the accuracy by up to 9% in test data compared to conventional models. Moreover, it can achieve a dramatic reduction in model size by over a hundred times with minimal accuracy loss, proving its effectiveness across various architectures and datasets. This approach marks a significant advancement in optimizing transfer-learning models, promising enhanced performance in real-world applications.
