Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhu, Jilong, Feng, Yang
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2604.12508
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911592073920512
author Zhu, Jilong
Feng, Yang
author_facet Zhu, Jilong
Feng, Yang
contents While Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities in general visual understanding, they frequently falter in fine-grained perception tasks that require identifying tiny objects or discerning subtle visual relationships. We attribute this limitation to Visual Attenuation: a phenomenon where sparse fine-grained visual signals are prematurely suppressed or diluted by dominant textual tokens during network propagation, resulting in a "loss of focus" during the deep-level decision-making process. Existing input-centric solutions fail to fundamentally reverse this intrinsic mechanism of information loss. To address this challenge, we propose the Variational Information Flow (VIF) framework. Adopting a probabilistic perspective, VIF leverages a Conditional Variational Autoencoder (CVAE) to model the visual saliency relevant to the question-answer pair as a latent distribution. As a plug-and-play module, VIF can be integrated into existing architectures. Extensive evaluations across diverse benchmarks, covering General VQA, fine-grained perception, and visual grounding, demonstrate that VIF yields competitive improvements over previous methods, validating its effectiveness in enhancing the fine-grained perception of MLLMs.
format Preprint
id arxiv_https___arxiv_org_abs_2604_12508
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle From Attenuation to Attention: Variational Information Flow Manipulation for Fine-Grained Visual Perception
Zhu, Jilong
Feng, Yang
Computer Vision and Pattern Recognition
While Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities in general visual understanding, they frequently falter in fine-grained perception tasks that require identifying tiny objects or discerning subtle visual relationships. We attribute this limitation to Visual Attenuation: a phenomenon where sparse fine-grained visual signals are prematurely suppressed or diluted by dominant textual tokens during network propagation, resulting in a "loss of focus" during the deep-level decision-making process. Existing input-centric solutions fail to fundamentally reverse this intrinsic mechanism of information loss. To address this challenge, we propose the Variational Information Flow (VIF) framework. Adopting a probabilistic perspective, VIF leverages a Conditional Variational Autoencoder (CVAE) to model the visual saliency relevant to the question-answer pair as a latent distribution. As a plug-and-play module, VIF can be integrated into existing architectures. Extensive evaluations across diverse benchmarks, covering General VQA, fine-grained perception, and visual grounding, demonstrate that VIF yields competitive improvements over previous methods, validating its effectiveness in enhancing the fine-grained perception of MLLMs.
title From Attenuation to Attention: Variational Information Flow Manipulation for Fine-Grained Visual Perception
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.12508