Distributed Zero-Shot Learning for Visual Recognition

TL;DR

This paper introduces a Distributed Zero-Shot Learning framework that leverages decentralized data with novel regularizers and consensus mechanisms to improve unseen class recognition in visual tasks.

Contribution

It proposes a new DistZSL framework with cross-node attribute regularization and global attribute-to-visual consensus to address data heterogeneity in distributed learning.

Findings

DistZSL outperforms state-of-the-art methods on benchmark datasets.

The framework effectively handles data heterogeneity across distributed nodes.

Experimental results show significant improvements in zero-shot recognition accuracy.

Abstract

In this paper, we propose a Distributed Zero-Shot Learning (DistZSL) framework that can fully exploit decentralized data to learn an effective model for unseen classes. Considering the data heterogeneity issues across distributed nodes, we introduce two key components to ensure the effective learning of DistZSL: a cross-node attribute regularizer and a global attribute-to-visual consensus. Our proposed cross-node attribute regularizer enforces the distances between attribute features to be similar across different nodes. In this manner, the overall attribute feature space would be stable during learning, and thus facilitate the establishment of visual-to-attribute(V2A) relationships. Then, we introduce the global attribute-tovisual consensus to mitigate biased V2A mappings learned from individual nodes. Specifically, we enforce the bilateral mapping between the attribute and visual feature distributions to be consistent across different nodes. Thus, the learned consistent V2A mapping can significantly enhance zero-shot learning across different nodes. Extensive experiments demonstrate that DistZSL achieves superior performance to the state-of-the-art in learning from distributed data.