HOPE: A Memory-Based and Composition-Aware Framework for Zero-Shot Learning with Hopfield Network and Soft Mixture of Experts
This addresses the challenge of handling unfamiliar class combinations in compositional zero-shot learning for computer vision applications, representing an incremental improvement with a novel hybrid method.
The paper tackles the problem of classifying unseen object compositions in zero-shot learning by proposing HOPE, a framework that combines a Modern Hopfield Network for memory-based label retrieval with a Mixture of Experts for composition classification, achieving state-of-the-art performance on benchmarks like MIT-States and UT-Zappos.
Compositional Zero-Shot Learning (CZSL) has emerged as an essential paradigm in machine learning, aiming to overcome the constraints of traditional zero-shot learning by incorporating compositional thinking into its methodology. Conventional zero-shot learning has difficulty managing unfamiliar combinations of seen and unseen classes because it depends on pre-defined class embeddings. In contrast, Compositional Zero-Shot Learning leverages the inherent hierarchies and structural connections among classes, creating new class representations by combining attributes, components, or other semantic elements. In our paper, we propose a novel framework that for the first time combines the Modern \underline{H}opfield Network with a Mixture \underline{o}f \underline{E}x\underline{p}erts (HOPE) to classify the compositions of previously unseen objects. Specifically, the Modern Hopfield Network creates a memory that stores label prototypes and identifies relevant labels for a given input image. Subsequently, the Mixture of Expert models integrates the image with the appropriate prototype to produce the final composition classification. Our approach achieves SOTA performance on several benchmarks, including MIT-States and UT-Zappos. We also examine how each component contributes to improved generalization.