Title of Paper:Information Aggregation Semantic Adversarial Network for Cross-Modal Retrieval

Hits:

Journal:2022 International Joint Conference on Neural Networks (IJCNN)

Key Words:—Cross-modal Retrieval, Representation Learning, Adversarial Learning

Abstract:The core of cross-modal retrieval is to measure the
similarity between different modalities of data. The mainstream
is to construct a common subspace using representation learning,
in which different types of data can be directly compared.
However, most of these methods utilize solely a portion of the
information from the dataset, with varying degrees of information
loss in the objective function. In this paper, we present a novel
cross-modal learning framework called Information Aggregation
Semantic Adversarial Network, which minimizes information loss
through adversarial learning and the double constraints of two
subspaces. Among them, the proposed cross-modal information
aggregation constraint based on common subspace aggregates the
global information and fine-grained information simultaneously
to generate a common representation of cross-modal similarity and fight a discriminator used to distinguish the original
modality of the common representation. Furthermore, a semantic
constraint is considered to improve the semantic discrimination
of common representation based on the potential association
between labels and representations of a semantic subspace.
Through the joint exploitation of the above, the information
loss in the cross-modal process is greatly reduced. Extensive
experimental results on three widely-used benchmark datasets
demonstrate that the proposed method is effective in cross-modal
learning and significantly outperforms the state-of-the-art crossmodal retrieval methods.

Discipline:Engineering

Document Type:C

Translation or Not:no

Date of Publication:2022-03-03

Included Journals:ISTP

Correspondence Author:Amy Feng