MM2020 - Rethinking Generative ZSL: An Ensemble Learning Perspective for Recognizing Visual Patches
To appear in ACM Multimedia 2020
Zhi Chen, Sen Wang, Jingjing Li, Zi Huang
The University of Queensland
University of Electronic Science and Technology of China
Zero-shot learning is commonly used to address the very pervasive problem of predicting unseen classes in fine-grained image classification and other tasks. One family of solutions is to learn synthesised unseen visual samples produced by generative models from auxiliary semantic information, such as natural language descriptions. However, for most of these models, performance suffers from noise in the form of irrelevant image backgrounds. Further, most methods do not allocate a calculated weight to each semantic patch. Yet, in the real world, the discriminative power of features can be quantified and directly leveraged to improve accuracy and reduce computational complexity. To address these issues, we propose a novel framework called multi-patch generative adversarial nets (MPGAN) that synthesises local patch features and labels unseen classes with a novel weighted voting strategy. Extensive experiments show that MPGAN has significantly greater accuracy than state-of-the-art methods.