Paint Outside the Box: Synthesizing and Selecting Training Data for Visual Grounding

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Du, Zilin, Li, Haoxin, Yu, Jianfei, Li, Boyang
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866913800629780480
author Du, Zilin
Li, Haoxin
Yu, Jianfei
Li, Boyang
author_facet Du, Zilin
Li, Haoxin
Yu, Jianfei
Li, Boyang
contents Visual grounding aims to localize the image regions based on a textual query. Given the difficulty of large-scale data curation, we investigate how to effectively learn visual grounding under data-scarce settings in this paper. To address the data scarcity, we propose a novel framework, POBF (Paint Outside the Box and Filter). POBF synthesizes images by inpainting outside the box, tackling a label misalignment issue encountered in previous works. Furthermore, POBF leverages an innovative filtering scheme to select the most effective training data. This scheme combines a hardness score and an overfitting score, balanced by a penalty term. Extensive experiments across four benchmark datasets demonstrate that POBF consistently improves performance, achieving an average gain of 5.83\% over the real-data-only method and outperforming leading baselines by 2.29\%-3.85\% in accuracy. Additionally, we validate the robustness and generalizability of POBF across various generative models, training data sizes, and model architectures.
format Preprint
id arxiv_https___arxiv_org_abs_2412_00684
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Paint Outside the Box: Synthesizing and Selecting Training Data for Visual Grounding
Du, Zilin
Li, Haoxin
Yu, Jianfei
Li, Boyang
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Visual grounding aims to localize the image regions based on a textual query. Given the difficulty of large-scale data curation, we investigate how to effectively learn visual grounding under data-scarce settings in this paper. To address the data scarcity, we propose a novel framework, POBF (Paint Outside the Box and Filter). POBF synthesizes images by inpainting outside the box, tackling a label misalignment issue encountered in previous works. Furthermore, POBF leverages an innovative filtering scheme to select the most effective training data. This scheme combines a hardness score and an overfitting score, balanced by a penalty term. Extensive experiments across four benchmark datasets demonstrate that POBF consistently improves performance, achieving an average gain of 5.83\% over the real-data-only method and outperforming leading baselines by 2.29\%-3.85\% in accuracy. Additionally, we validate the robustness and generalizability of POBF across various generative models, training data sizes, and model architectures.
title Paint Outside the Box: Synthesizing and Selecting Training Data for Visual Grounding
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2412.00684