Densely Connected Parameter-Efficient Tuning for Referring Image Segmentation
Proceedings of the AAAI Conference on Artificial Intelligence · 11.04.2025 · 39 (4) · 3653-3661
DOI: 10.1609/aaai.v39i4.32380 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 11.04.2025. Verfasst von Jiaqi Huang und 6 weiteren Autor:innen. Die Arbeit wurde bisher 28-mal zitiert (Crossref).
Abstract (Originalsprache)
In the domain of computer vision, Parameter-Efficient Tuning (PET) is increasingly replacing the traditional paradigm of pre-training followed by full fine-tuning. PET is particularly favored for its effectiveness in large foundation models, as it streamlines transfer learning costs and optimizes hardware utilization. However, the current PET methods are mainly designed for single-modal optimization. While some pioneering studies have undertaken preliminary explorations, they still remain at the level of aligned encoders (e.g., CLIP) and lack exploration of misaligned encoders. These methods show sub-optimal performance with misaligned encoders, as they fail to effectively align the multimodal features during fine-tuning. In this paper, we introduce DETRIS, a parameter-efficient tuning framework designed to enhance low-rank visual feature propagation by establishing dense interconnections between each layer and all preceding layers, which enables effective cross-modal feature interaction and adaptation to misaligned encoders. We also suggest using text adapters to improve textual features. Our simple yet efficient approach greatly surpasses state-of-the-art methods with 0.9% to 1.8% backbone parameter updates, evaluated on challenging benchmarks.
Zitieren
APA
Huang, J., Xu, Z., Liu, T., Liu, Y., Han, H., Yuan, K., & Li, X. (2025). Densely Connected Parameter-Efficient Tuning for Referring Image Segmentation. Proceedings of the AAAI Conference on Artificial Intelligence, 39(4), 3653-3661. https://doi.org/10.1609/aaai.v39i4.32380
Vancouver
Huang J, Xu Z, Liu T, Liu Y, Han H, Yuan K, et al. Densely Connected Parameter-Efficient Tuning for Referring Image Segmentation. Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39(4):3653-3661. doi:10.1609/aaai.v39i4.32380
BibTeX
@article{Huang2025,
author = {Huang, Jiaqi and Xu, Zunnan and Liu, Ting and Liu, Yong and Han, Haonan and Yuan, Kehong and Li, Xiu},
title = {Densely Connected Parameter-Efficient Tuning for Referring Image Segmentation},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2025},
volume = {39},
number = {4},
pages = {3653--3661},
doi = {10.1609/aaai.v39i4.32380}
}
EUVIMED