Rethink, Revisit, Revise: A Spiral Reinforced Self-Revised Network for Zero-Shot Learning

TL;DR

This paper introduces a spiral learning framework for Zero-Shot Learning that revisits visual representations through attribute groups, enhancing the model's ability to learn complex correlations and outperform existing methods.

Contribution

It proposes a Reinforced Self-Revised framework with a spiral learning process that revisits attribute groups to improve generalization in ZSL.

Findings

Outperforms state-of-the-art on four benchmark datasets

Effectively captures complex semantic correlations

Enhances explainability through attribute group analysis

Abstract

Current approaches to Zero-Shot Learning (ZSL) struggle to learn generalizable semantic knowledge capable of capturing complex correlations. Inspired by \emph{Spiral Curriculum}, which enhances learning processes by revisiting knowledge, we propose a form of spiral learning which revisits visual representations based on a sequence of attribute groups (e.g., a combined group of \emph{color} and \emph{shape}). Spiral learning aims to learn generalized local correlations, enabling models to gradually enhance global learning and thus understand complex correlations. Our implementation is based on a 2-stage \emph{Reinforced Self-Revised (RSR)} framework: \emph{preview} and \emph{review}. RSR first previews visual information to construct diverse attribute groups in a weakly-supervised manner. Then, it spirally learns refined localities based on attribute groups and uses localities to revise global semantic correlations. Our framework outperforms state-of-the-art algorithms on four benchmark datasets in both zero-shot and generalized zero-shot settings, which demonstrates the effectiveness of spiral learning in learning generalizable and complex correlations. We also conduct extensive analysis to show that attribute groups and reinforced decision processes can capture complementary semantic information to improve predictions and aid explainability.