Beyond Attributes: Adversarial Erasing Embedding Network for Zero-shot Learning

Abstract

In this paper, an adversarial erasing embedding network with the guidance of high-order attributes (AEEN-HOA) is proposed for going further to solve the challenging ZSL/GZSL task. AEEN-HOA consists of two branches, i.e., the upper stream is capable of erasing some initially discovered regions, then the high-order attribute supervision is incorporated to characterize the relationship between the class attributes. Meanwhile, the bottom stream is trained by taking the current background regions to train the same attribute. As far as we know, it is the first time of introducing the erasing operations into the ZSL task. In addition, we first propose a class attribute activation map for the visualization of ZSL output, which shows the relationship between class attribute feature and attention map. Experiments on four standard benchmark datasets demonstrate the superiority of AEEN-HOA framework.

arXiv comment12 pages, 10 figures,working report

References in corpus (12)

• SGDR: Stochastic Gradient Descent with Warm Restarts
• Learning Deep Features for Discriminative Localization
• Semantic Autoencoder for Zero-Shot Learning
• Zero-Shot Learning via Semantic Similarity Embedding
• Zero-Shot Learning -- The Good, the Bad and the Ugly
• Preserving Semantic Relations for Zero-Shot Learning
• Adversarial Complementary Learning for Weakly Supervised Object Localization
• An Empirical Study and Analysis of Generalized Zero-Shot Learning for Object Recognition in the Wild
• Latent Embeddings for Zero-shot Classification
• Discriminative Learning of Latent Features for Zero-Shot Recognition
• Semantically Consistent Regularization for Zero-Shot Recognition
• Self-Erasing Network for Integral Object Attention