EUVIMEDEUVIMED entdecken
Crossref

Retrieval-Augmented Primitive Representations for Compositional Zero-Shot Learning

Chenchen Jing, Yukun Li, Hao Chen, Chunhua Shen

Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (3) · 2652-2660

DOI: 10.1609/aaai.v38i3.28043 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Chenchen Jing und 3 weiteren Autor:innen. Die Arbeit wurde bisher 16-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Compositional zero-shot learning (CZSL) aims to recognize unseen attribute-object compositions by learning from seen compositions. Composing the learned knowledge of seen primitives, i.e., attributes or objects, into novel compositions is critical for CZSL. In this work, we propose to explicitly retrieve knowledge of seen primitives for compositional zero-shot learning. We present a retrieval-augmented method, which augments standard multi-path classification methods with two retrieval modules. Specifically, we construct two databases storing the attribute and object representations of training images, respectively. For an input training/testing image, we use two retrieval modules to retrieve representations of training images with the same attribute and object, respectively. The primitive representations of the input image are augmented by using the retrieved representations, for composition recognition. By referencing semantically similar images, the proposed method is capable of recalling knowledge of seen primitives for compositional generalization. Experiments on three widely-used datasets show the effectiveness of the proposed method.

Zitieren

APA

Jing, C., Li, Y., Chen, H., & Shen, C. (2024). Retrieval-Augmented Primitive Representations for Compositional Zero-Shot Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 38(3), 2652-2660. https://doi.org/10.1609/aaai.v38i3.28043

Vancouver

Jing C, Li Y, Chen H, Shen C. Retrieval-Augmented Primitive Representations for Compositional Zero-Shot Learning. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(3):2652-2660. doi:10.1609/aaai.v38i3.28043

BibTeX
@article{Jing2024,
  author = {Jing, Chenchen and Li, Yukun and Chen, Hao and Shen, Chunhua},
  title = {Retrieval-Augmented Primitive Representations for Compositional Zero-Shot Learning},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2024},
  volume = {38},
  number = {3},
  pages = {2652--2660},
  doi = {10.1609/aaai.v38i3.28043}
}
Kostenlos starten →