An Entropy-guided Reinforced Partial Convolutional Network for Zero-Shot Learning
This work addresses Zero-Shot Learning for AI systems by improving knowledge transfer from observed to unseen classes, representing an incremental advancement through a novel hybrid method.
The paper tackled the problem of Zero-Shot Learning by proposing ERPCNet, a method that extracts and aggregates localities based on semantic relevance and visual correlations without human annotations, achieving state-of-the-art performance on four benchmark datasets in ZSL and GZSL settings.
Zero-Shot Learning (ZSL) aims to transfer learned knowledge from observed classes to unseen classes via semantic correlations. A promising strategy is to learn a global-local representation that incorporates global information with extra localities (i.e., small parts/regions of inputs). However, existing methods discover localities based on explicit features without digging into the inherent properties and relationships among regions. In this work, we propose a novel Entropy-guided Reinforced Partial Convolutional Network (ERPCNet), which extracts and aggregates localities progressively based on semantic relevance and visual correlations without human-annotated regions. ERPCNet uses reinforced partial convolution and entropy guidance; it not only discovers global-cooperative localities dynamically but also converges faster for policy gradient optimization. We conduct extensive experiments to demonstrate ERPCNet's performance through comparisons with state-of-the-art methods under ZSL and Generalized Zero-Shot Learning (GZSL) settings on four benchmark datasets. We also show ERPCNet is time efficient and explainable through visualization analysis.