Feature Generating Networks for Zero-Shot Learning
This addresses the problem of data imbalance in zero-shot learning for computer vision applications, offering a novel generative approach that is incremental but effective.
The paper tackles the challenge of generalized zero-shot learning by proposing a generative adversarial network that synthesizes CNN features from class-level semantic information, achieving significant accuracy boosts over state-of-the-art methods on five datasets.
Suffering from the extreme training data imbalance between seen and unseen classes, most of existing state-of-the-art approaches fail to achieve satisfactory results for the challenging generalized zero-shot learning task. To circumvent the need for labeled examples of unseen classes, we propose a novel generative adversarial network (GAN) that synthesizes CNN features conditioned on class-level semantic information, offering a shortcut directly from a semantic descriptor of a class to a class-conditional feature distribution. Our proposed approach, pairing a Wasserstein GAN with a classification loss, is able to generate sufficiently discriminative CNN features to train softmax classifiers or any multimodal embedding method. Our experimental results demonstrate a significant boost in accuracy over the state of the art on five challenging datasets -- CUB, FLO, SUN, AWA and ImageNet -- in both the zero-shot learning and generalized zero-shot learning settings.