Discriminative Learning of Latent Features for Zero-Shot Recognition

TL;DR

This paper introduces an end-to-end discriminative learning approach for zero-shot recognition, emphasizing the importance of learning discriminative features for both visual and semantic data, leading to improved performance.

Contribution

It proposes a novel network that automatically discovers discriminative regions and learns discriminative semantic representations, advancing zero-shot learning methods.

Findings

Significant performance improvements over state-of-the-art methods.

Effective discovery of discriminative regions via a zoom network.

Enhanced semantic representations in an augmented space.

Abstract

Zero-shot learning (ZSL) aims to recognize unseen image categories by learning an embedding space between image and semantic representations. For years, among existing works, it has been the center task to learn the proper mapping matrices aligning the visual and semantic space, whilst the importance to learn discriminative representations for ZSL is ignored. In this work, we retrospect existing methods and demonstrate the necessity to learn discriminative representations for both visual and semantic instances of ZSL. We propose an end-to-end network that is capable of 1) automatically discovering discriminative regions by a zoom network; and 2) learning discriminative semantic representations in an augmented space introduced for both user-defined and latent attributes. Our proposed method is tested extensively on two challenging ZSL datasets, and the experiment results show that the proposed method significantly outperforms state-of-the-art methods.