Learning Aligned Cross-Modal Representation for Generalized Zero-Shot Classification
This work addresses domain shift in cross-modal representation learning for zero-shot classification, which is an incremental improvement over existing methods.
The paper tackles the domain shift problem in Generalized Zero-Shot Classification by proposing an autoencoder network with Vision-Semantic Alignment and an Information Enhancement Module, achieving state-of-the-art performance on public datasets.
Learning a common latent embedding by aligning the latent spaces of cross-modal autoencoders is an effective strategy for Generalized Zero-Shot Classification (GZSC). However, due to the lack of fine-grained instance-wise annotations, it still easily suffer from the domain shift problem for the discrepancy between the visual representation of diversified images and the semantic representation of fixed attributes. In this paper, we propose an innovative autoencoder network by learning Aligned Cross-Modal Representations (dubbed ACMR) for GZSC. Specifically, we propose a novel Vision-Semantic Alignment (VSA) method to strengthen the alignment of cross-modal latent features on the latent subspaces guided by a learned classifier. In addition, we propose a novel Information Enhancement Module (IEM) to reduce the possibility of latent variables collapse meanwhile encouraging the discriminative ability of latent variables. Extensive experiments on publicly available datasets demonstrate the state-of-the-art performance of our method.