From Anchor Generation to Distribution Alignment: Learning a Discriminative Embedding Space for Zero-Shot Recognition
This work addresses classification confusion in zero-shot learning, which is an incremental improvement for computer vision tasks.
The paper tackles the problem of irregular template distribution in zero-shot learning by proposing a novel framework that generates discriminative anchors and aligns sample distributions, achieving state-of-the-art performance on benchmark datasets.
In zero-shot learning (ZSL), the samples to be classified are usually projected into side information templates such as attributes. However, the irregular distribution of templates makes classification results confused. To alleviate this issue, we propose a novel framework called Discriminative Anchor Generation and Distribution Alignment Model (DAGDA). Firstly, in order to rectify the distribution of original templates, a diffusion based graph convolutional network, which can explicitly model the interaction between class and side information, is proposed to produce discriminative anchors. Secondly, to further align the samples with the corresponding anchors in anchor space, which aims to refine the distribution in a fine-grained manner, we introduce a semantic relation regularization in anchor space. Following the way of inductive learning, our approach outperforms some existing state-of-the-art methods, on several benchmark datasets, for both conventional as well as generalized ZSL setting. Meanwhile, the ablation experiments strongly demonstrate the effectiveness of each component.