Transferable Contrastive Network for Generalized Zero-Shot Learning
This work addresses a key challenge in GZSL for computer vision, though it appears incremental as it builds on existing contrastive and transfer learning methods.
The paper tackles the problem of overfitting to source classes in generalized zero-shot learning (GZSL) by proposing a Transferable Contrastive Network (TCN) that transfers knowledge from source to target classes using class similarities, resulting in superior performance on five benchmark datasets.
Zero-shot learning (ZSL) is a challenging problem that aims to recognize the target categories without seen data, where semantic information is leveraged to transfer knowledge from some source classes. Although ZSL has made great progress in recent years, most existing approaches are easy to overfit the sources classes in generalized zero-shot learning (GZSL) task, which indicates that they learn little knowledge about target classes. To tackle such problem, we propose a novel Transferable Contrastive Network (TCN) that explicitly transfers knowledge from the source classes to the target classes. It automatically contrasts one image with different classes to judge whether they are consistent or not. By exploiting the class similarities to make knowledge transfer from source images to similar target classes, our approach is more robust to recognize the target images. Experiments on five benchmark datasets show the superiority of our approach for GZSL.