Dual-path Convolutional Image-Text Embeddings with Instance Loss

Document Type

Journal Article

Publication Title

ACM Transactions on Multimedia Computing, Communications and Applications

ISSN

15516857

Volume

16

Issue

2

Publisher

Association for Computing Machinery

School

School of Arts and Humanities

RAS ID

34167

Comments

Zheng, Z., Zheng, L., Garrett, M., Yang, Y., Xu, M., & Shen, Y. D. (2020). Dual-path convolutional image-text embeddings with instance loss. ACM Transactions on Multimedia Computing, Communications, and Applications, 16(2), article 51. https://doi.org/10.1145/3383184

Abstract

© 2020 ACM. Matching images and sentences demands a fine understanding of both modalities. In this article, we propose a new system to discriminatively embed the image and text to a shared visual-textual space. In this field, most existing works apply the ranking loss to pull the positive image/text pairs close and push the negative pairs apart from each other. However, directly deploying the ranking loss on heterogeneous features (i.e., text and image features) is less effective, because it is hard to find appropriate triplets at the beginning. So the naive way of using the ranking loss may compromise the network from learning inter-modal relationship. To address this problem, we propose the instance loss, which explicitly considers the intra-modal data distribution. It is based on an unsupervised assumption that each image/text group can be viewed as a class. So the network can learn the fine granularity from every image/text group. The experiment shows that the instance loss offers better weight initialization for the ranking loss, so that more discriminative embeddings can be learned. Besides, existing works usually apply the off-the-shelf features, i.e., word2vec and fixed visual feature. So in a minor contribution, this article constructs an end-to-end dual-path convolutional network to learn the image and text representations. End-to-end learning allows the system to directly learn from the data and fully utilize the supervision. On two generic retrieval datasets (Flickr30k and MSCOCO), experiments demonstrate that our method yields competitive accuracy compared to state-of-the-art methods. Moreover, in language-based person retrieval, we improve the state of the art by a large margin. The code has been made publicly available.

DOI

10.1145/3383184

Access Rights

subscription content

Share

 
COinS