EUVIMEDEUVIMED entdecken
Crossref

Data Roaming and Quality Assessment for Composed Image Retrieval

Matan Levy, Rami Ben-Ari, Nir Darshan, Dani Lischinski

Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (4) · 2991-2999

DOI: 10.1609/aaai.v38i4.28081 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Matan Levy und 3 weiteren Autor:innen. Die Arbeit wurde bisher 44-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The task of Composed Image Retrieval (CoIR) involves queries that combine image and text modalities, allowing users to express their intent more effectively. However, current CoIR datasets are orders of magnitude smaller compared to other vision and language (V&L) datasets. Additionally, some of these datasets have noticeable issues, such as queries containing redundant modalities. To address these shortcomings, we introduce the Large Scale Composed Image Retrieval (LaSCo) dataset, a new CoIR dataset which is ten times larger than existing ones. Pre-training on our LaSCo, shows a noteworthy improvement in performance, even in zero-shot. Furthermore, we propose a new approach for analyzing CoIR datasets and methods, which detects modality redundancy or necessity, in queries. We also introduce a new CoIR baseline, the Cross-Attention driven Shift Encoder (CASE). This baseline allows for early fusion of modalities using a cross-attention module and employs an additional auxiliary task during training. Our experiments demonstrate that this new baseline outperforms the current state-of-the-art methods on established benchmarks like FashionIQ and CIRR.

Zitieren

APA

Levy, M., Ben-Ari, R., Darshan, N., & Lischinski, D. (2024). Data Roaming and Quality Assessment for Composed Image Retrieval. Proceedings of the AAAI Conference on Artificial Intelligence, 38(4), 2991-2999. https://doi.org/10.1609/aaai.v38i4.28081

Vancouver

Levy M, Ben-Ari R, Darshan N, Lischinski D. Data Roaming and Quality Assessment for Composed Image Retrieval. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(4):2991-2999. doi:10.1609/aaai.v38i4.28081

BibTeX
@article{Levy2024,
  author = {Levy, Matan and Ben-Ari, Rami and Darshan, Nir and Lischinski, Dani},
  title = {Data Roaming and Quality Assessment for Composed Image Retrieval},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2024},
  volume = {38},
  number = {4},
  pages = {2991--2999},
  doi = {10.1609/aaai.v38i4.28081}
}
Kostenlos starten →