Unveiling PEFT Robustness to Noisy Labels in VLMs: A Gradient-Loss Decoupling Perspective.
| Anthology ID: | DBLP:conf/mir/MaPW26 |
|---|---|
| Volume: | Proceedings of the 2026 International Conference on Multimedia Retrieval, ICMR 2026, Amsterdam, The Netherlands, June 16-19, 2026 |
| Year: | 2026 |
| Venue: | International Conference on Multimedia Retrieval (ICMR) |
| Publisher: | ACM |
| Pages: | 967-976 |
| URL: | https://doi.org/10.1145/3805622.3810828 |
| DOI: | https://doi.org/10.1145/3805622.3810828 |
| DBLP: | conf/mir/MaPW26 |
| BibTeX: |
@inproceedings{ma-2026-unveiling,
author = {Tengfei Ma and
Weiran Pan and
Wei Wei},
editor = {Stevan Rudinac and
Zi Huang and
Marcel Worring and
Lucia Vadicamo and
Xirong Li and
Pascal Mettes and
Lizi Liao},
title = {{Unveiling PEFT Robustness to Noisy Labels in VLMs: A Gradient-Loss Decoupling Perspective}},
booktitle = {{Proceedings of the 2026 International Conference on Multimedia Retrieval, ICMR 2026, Amsterdam, The Netherlands, June 16-19, 2026}},
pages = {967--976},
publisher = {ACM},
year = {2026},
url = {https://doi.org/10.1145/3805622.3810828},
doi = {https://doi.org/10.1145/3805622.3810828}
}