Guardado en:
Detalles Bibliográficos
Autores principales: Jennings, Roy H., Paikin, Genady, Shaul, Roy, Soloveichik, Evgeny
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2507.14997
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866918235156250624
author Jennings, Roy H.
Paikin, Genady
Shaul, Roy
Soloveichik, Evgeny
author_facet Jennings, Roy H.
Paikin, Genady
Shaul, Roy
Soloveichik, Evgeny
contents Multimodal Large Language Models (MLLMs) show promise for image-based regression tasks, but current approaches face key limitations. Recent methods fine-tune MLLMs using preset output vocabularies and generic task-level prompts (e.g., "How would you rate this image?"), assuming this mimics human rating behavior. Our analysis reveals that these approaches provide no benefit over image-only training. Models using preset vocabularies and generic prompts perform equivalently to image-only models, failing to leverage semantic understanding from textual input. We propose Regression via Transformer-Based Classification (RvTC), which replaces vocabulary-constrained classification with a flexible bin-based approach. Unlike approaches that address discretization errors through complex distributional modeling, RvTC eliminates manual vocabulary crafting through straightforward bin increase, achieving state-of-the-art performance on four image assessment datasets using only images. More importantly, we demonstrate that data-specific prompts dramatically improve performance. Unlike generic task descriptions, prompts containing semantic information about specific images enable MLLMs to leverage cross-modal understanding. On the AVA dataset, adding challenge titles to prompts substantially improves our already state-of-the-art image-only baseline. We demonstrate through empirical evidence from the AVA and AGIQA-3k datasets that MLLMs benefit from semantic prompt information, surpassing mere statistical biases. We validate RvTC across two different MLLM architectures, demonstrating consistent improvements and method generalizability.
format Preprint
id arxiv_https___arxiv_org_abs_2507_14997
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Language Integration in Fine-Tuning Multimodal Large Language Models for Image-Based Regression
Jennings, Roy H.
Paikin, Genady
Shaul, Roy
Soloveichik, Evgeny
Computer Vision and Pattern Recognition
Machine Learning
Multimodal Large Language Models (MLLMs) show promise for image-based regression tasks, but current approaches face key limitations. Recent methods fine-tune MLLMs using preset output vocabularies and generic task-level prompts (e.g., "How would you rate this image?"), assuming this mimics human rating behavior. Our analysis reveals that these approaches provide no benefit over image-only training. Models using preset vocabularies and generic prompts perform equivalently to image-only models, failing to leverage semantic understanding from textual input. We propose Regression via Transformer-Based Classification (RvTC), which replaces vocabulary-constrained classification with a flexible bin-based approach. Unlike approaches that address discretization errors through complex distributional modeling, RvTC eliminates manual vocabulary crafting through straightforward bin increase, achieving state-of-the-art performance on four image assessment datasets using only images. More importantly, we demonstrate that data-specific prompts dramatically improve performance. Unlike generic task descriptions, prompts containing semantic information about specific images enable MLLMs to leverage cross-modal understanding. On the AVA dataset, adding challenge titles to prompts substantially improves our already state-of-the-art image-only baseline. We demonstrate through empirical evidence from the AVA and AGIQA-3k datasets that MLLMs benefit from semantic prompt information, surpassing mere statistical biases. We validate RvTC across two different MLLM architectures, demonstrating consistent improvements and method generalizability.
title Language Integration in Fine-Tuning Multimodal Large Language Models for Image-Based Regression
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2507.14997