CLIP-Lite: Information Efficient Visual Representation Learning with Language Supervision

We propose CLIP-Lite, an information efficient method for visual representation learning by feature alignment with textual annotations. Compared to the previously proposed CLIP model, CLIP-Lite requires only one negative image-text sample pair for every positive image-text sample during the optimiza...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2023-05
Hauptverfasser:	Shrivastava, Aman, Selvaraju, Ramprasaath R, Naik, Nikhil, Ordonez, Vicente
Format:	Artikel
Sprache:	eng
Schlagworte:	Alignment Annotations Datasets Image classification Learning Lower bounds Optimization Pascal (programming language) Performance evaluation Representations Semantics
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!