Refinement Matters: Textual Description Needs to be Refined for Zero-shot Learning

Chandan Gautam, Sethupathy Parameswaran, Vinay Verma, Suresh Sundaram, Savitha Ramasamy


Abstract
Zero-Shot Learning (ZSL) has shown great promise at the intersection of vision and language, and generative methods for ZSL are predominant owing to their efficiency. Moreover, textual description or attribute plays a critical role in transferring knowledge from the seen to unseen classes in ZSL. Such generative approaches for ZSL are very costly to train and require the class description of the unseen classes during training. In this work, we propose a non-generative gating-based attribute refinement network for ZSL, which achieves similar accuracies to generative methods of ZSL, at a much lower computational cost. The refined attributes are mapped into the visual domain through an attribute embedder, and the whole network is guided by the circle loss and the well-known softmax cross-entropy loss to obtain a robust class embedding. We refer to our approach as Circle loss guided gating-based Attribute-Refinement Network (CARNet). We perform extensive experiments on the five benchmark datasets over the various challenging scenarios viz., Generalized ZSL (GZSL), Continual GZSL (CGZSL), and conventional ZSL. We observe that the CARNet significantly outperforms recent non-generative ZSL methods and most generative ZSL methods in all three settings by a significant margin. Our extensive ablation study disentangles the performance of various components and justifies their importance. The source code is available at https://github.com/Sethup123/CARNet.
Anthology ID:
2022.findings-emnlp.455
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2022
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6127–6140
Language:
URL:
https://aclanthology.org/2022.findings-emnlp.455
DOI:
10.18653/v1/2022.findings-emnlp.455
Bibkey:
Cite (ACL):
Chandan Gautam, Sethupathy Parameswaran, Vinay Verma, Suresh Sundaram, and Savitha Ramasamy. 2022. Refinement Matters: Textual Description Needs to be Refined for Zero-shot Learning. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 6127–6140, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Refinement Matters: Textual Description Needs to be Refined for Zero-shot Learning (Gautam et al., Findings 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.findings-emnlp.455.pdf
Video:
 https://aclanthology.org/2022.findings-emnlp.455.mp4