Object

Title: DCF-VQA: Counterfactual structure based on multi-feature enhancement

Współtwórca:

Korbicz, Józef (1951- ) - red. ; Uciński, Dariusz - red.

Tytuł publikacji grupowej:

AMCS, volume 34 (2024)

Abstract:

Visual question answering (VQA) is a pivotal topic at the intersection of computer vision and natural language processing. This paper addresses the challenges of linguistic bias and bias fusion within invalid regions encountered in existing VQA models due to insufficient representation of multi-modal features. To overcome those issues, we propose a multi-feature enhancement scheme. This scheme involves the fusion of one or more features with the original ones, incorporating discrete cosine transform (DCT) features into the counterfactual reasoning framework. ; This approach harnesses finegrained information and spatial relationships within images and questions, enabling a more refined understanding of the indirect relationship between images and questions. Consequently, it effectively mitigates linguistic bias and bias fusion within invalid regions in the model. Extensive experiments are conducted on multiple datasets, including VQA2 and VQACP2, employing various baseline models and fusion techniques, resulting in promising and robust performance.

Wydawca:

Zielona Góra: Uniwersytet Zielonogórski

Identyfikator zasobu:

oai:zbc.uz.zgora.pl:87143

DOI:

10.61822/amcs-2024-0032

Strony:

453-466

Źródło:

AMCS, volume 34, number 3 (2024) ; click here to follow the link

Jezyk:

eng

Licencja CC BY 4.0:

click here to follow the link

Prawa do dysponowania publikacją:

Biblioteka Uniwersytetu Zielonogórskiego

Objects Similar

×

Citation

Citation style:

This page uses 'cookies'. More information