Speeding Up Image Classifiers with Little Companions

Speeding Up Image Classifiers with Little Companions

Scaling up neural networks has been a key recipe to the success of large language and vision models. However, in practice, up-scaled models can be disproportionately costly in terms of computations, providing only marginal improvements in performance; for example, EfficientViT-L3-384 achieves

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Liu, Yang, Thopalli, Kowshik, Thiagarajan, Jayaraman
Format: Artikel
Sprache:eng
Schlagworte:
Computer Science - Computer Vision and Pattern Recognition
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Scaling up neural networks has been a key recipe to the success of large language and vision models. However, in practice, up-scaled models can be disproportionately costly in terms of computations, providing only marginal improvements in performance; for example, EfficientViT-L3-384 achieves
DOI:10.48550/arxiv.2406.17117