Salvato in:
Dettagli Bibliografici
Autori principali: Khan, Anas Anwarul Haq, Verma, Utkarsh, Ramakrishnan, Ganesh
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2504.21831
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911148637421568
author Khan, Anas Anwarul Haq
Verma, Utkarsh
Ramakrishnan, Ganesh
author_facet Khan, Anas Anwarul Haq
Verma, Utkarsh
Ramakrishnan, Ganesh
contents We introduce DEEVISum (Distilled Early Exit Vision language model for Summarization), a lightweight, efficient, and scalable vision language model designed for segment wise video summarization. Leveraging multi modal prompts that combine textual and audio derived signals, DEEVISum incorporates Multi Stage Knowledge Distillation (MSKD) and Early Exit (EE) to strike a balance between performance and efficiency. MSKD offers a 1.33% absolute F1 improvement over baseline distillation (0.5%), while EE reduces inference time by approximately 21% with a 1.3 point drop in F1. Evaluated on the TVSum dataset, our best model PaLI Gemma2 3B + MSKD achieves an F1 score of 61.1, competing the performance of significantly larger models, all while maintaining a lower computational footprint. We publicly release our code and processed dataset to support further research.
format Preprint
id arxiv_https___arxiv_org_abs_2504_21831
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Early Exit and Multi Stage Knowledge Distillation in VLMs for Video Summarization
Khan, Anas Anwarul Haq
Verma, Utkarsh
Ramakrishnan, Ganesh
Computer Vision and Pattern Recognition
Artificial Intelligence
We introduce DEEVISum (Distilled Early Exit Vision language model for Summarization), a lightweight, efficient, and scalable vision language model designed for segment wise video summarization. Leveraging multi modal prompts that combine textual and audio derived signals, DEEVISum incorporates Multi Stage Knowledge Distillation (MSKD) and Early Exit (EE) to strike a balance between performance and efficiency. MSKD offers a 1.33% absolute F1 improvement over baseline distillation (0.5%), while EE reduces inference time by approximately 21% with a 1.3 point drop in F1. Evaluated on the TVSum dataset, our best model PaLI Gemma2 3B + MSKD achieves an F1 score of 61.1, competing the performance of significantly larger models, all while maintaining a lower computational footprint. We publicly release our code and processed dataset to support further research.
title Early Exit and Multi Stage Knowledge Distillation in VLMs for Video Summarization
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2504.21831