Improving Cross-Modal Retrieval with Set of Diverse Embeddings
- Title
- Improving Cross-Modal Retrieval with Set of Diverse Embeddings
- Authors
- 김동원; 김남엽; 곽수하
- Date Issued
- 2023-06
- Publisher
- IEEE Computer Society
- Abstract
- Cross-modal retrieval across image and text modalities is a challenging task due to its inherent ambiguity: An image often exhibits various situations, and a caption can be coupled with diverse images. Set-based embedding has been studied as a solution to this problem. It seeks to encode a sample into a set of different embedding vectors that capture different semantics of the sample. In this paper, we present a novel set-based embedding method, which is distinct from previous work in two aspects. First, we present a new similarity function called smooth-Chamfer similarity, which is designed to alleviate the side effects of existing similarity functions for set-based embedding. Second, we propose a novel set prediction module to produce a set of embedding vectors that effectively captures diverse semantics of input by the slot attention mechanism. Our method is evaluated on the COCO and Flickr30K datasets across different visual backbones, where it outperforms existing methods including ones that demand substantially larger computation at inference.
- URI
- https://oasis.postech.ac.kr/handle/2014.oak/122809
- Article Type
- Conference
- Citation
- 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023, page. 23422 - 23431, 2023-06
- Files in This Item:
- There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.