Parallel Vertex Diffusion for Unified Visual Grounding
Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (2) · 1326-1334
DOI: 10.1609/aaai.v38i2.27896 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Zesen Cheng und 7 weiteren Autor:innen. Die Arbeit wurde bisher 33-mal zitiert (Crossref).
Abstract (Originalsprache)
Unified visual grounding (UVG) capitalizes on a wealth of task-related knowledge across various grounding tasks via one-shot training, which curtails retraining costs and task-specific architecture design efforts. Vertex generation-based UVG methods achieve this versatility by unified modeling object box and contour prediction and provide a text-powered interface to vast related multi-modal tasks, e.g., visual question answering and captioning. However, these methods typically generate vertexes sequentially through autoregression, which is prone to be trapped in error accumulation and heavy computation, especially for high-dimension sequence generation in complex scenarios. In this paper, we develop Parallel Vertex Diffusion (PVD) based on the parallelizability of diffusion models to accurately and efficiently generate vertexes in a parallel and scalable manner. Since the coordinates fluctuate greatly, it typically encounters slow convergence when training diffusion models without geometry constraints. Therefore, we consummate our PVD by two critical components, i.e., center anchor mechanism and angle summation loss, which serve to normalize coordinates and adopt a differentiable geometry descriptor from the point-in-polygon problem of computational geometry to constrain the overall difference of prediction and label vertexes. These innovative designs empower our PVD to demonstrate its superiority with state-of-the-art performance across various grounding tasks.
Zitieren
APA
Cheng, Z., Li, K., Jin, P., Li, S., Ji, X., Yuan, L., Liu, C., & Chen, J. (2024). Parallel Vertex Diffusion for Unified Visual Grounding. Proceedings of the AAAI Conference on Artificial Intelligence, 38(2), 1326-1334. https://doi.org/10.1609/aaai.v38i2.27896
Vancouver
Cheng Z, Li K, Jin P, Li S, Ji X, Yuan L, et al. Parallel Vertex Diffusion for Unified Visual Grounding. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(2):1326-1334. doi:10.1609/aaai.v38i2.27896
BibTeX
@article{Cheng2024,
author = {Cheng, Zesen and Li, Kehan and Jin, Peng and Li, Siheng and Ji, Xiangyang and Yuan, Li and Liu, Chang and Chen, Jie},
title = {Parallel Vertex Diffusion for Unified Visual Grounding},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2024},
volume = {38},
number = {2},
pages = {1326--1334},
doi = {10.1609/aaai.v38i2.27896}
}
EUVIMED