Feature Generating Networks for Zero-Shot Learning
Citations Over TimeTop 1% of 2018 papers
Abstract
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.
Related Papers
- → Augmentation Invariant and Instance Spreading Feature for Softmax Embedding(2020)143 cited
- → An enhanced siamese angular softmax network with dual joint-attention for person re-identification(2021)6 cited
- → Group Softmax Loss with Discriminative Feature Grouping(2021)2 cited
- → Quadruplet-Center Loss for Face Verification(2019)1 cited
- → Deep Face Recognition Based on Penalty Cosface(2020)1 cited