Attention Based Simple Primitives for Open World Compositional Zero-Shot Learning

TL;DR

This paper introduces ASP, an attention-based model for open world compositional zero-shot learning that uses self-attention and external knowledge to improve generalization to unseen attribute-object pairs.

Contribution

It proposes a novel attention mechanism combined with external knowledge to better predict unseen attribute-object compositions in open world CZSL.

Findings

Achieves competitive performance with state-of-the-art methods.

Effectively models relationships between attributes and objects.

Utilizes external knowledge to restrict and refine the test space.

Abstract

Compositional Zero-Shot Learning (CZSL) aims to predict unknown compositions made up of attribute and object pairs. Predicting compositions unseen during training is a challenging task. We are exploring Open World Compositional Zero-Shot Learning (OW-CZSL) in this study, where our test space encompasses all potential combinations of attributes and objects. Our approach involves utilizing the self-attention mechanism between attributes and objects to achieve better generalization from seen to unseen compositions. Utilizing a self-attention mechanism facilitates the model's ability to identify relationships between attribute and objects. The similarity between the self-attended textual and visual features is subsequently calculated to generate predictions during the inference phase. The potential test space may encompass implausible object-attribute combinations arising from unrestricted attribute-object pairings. To mitigate this issue, we leverage external knowledge from ConceptNet to restrict the test space to realistic compositions. Our proposed model, Attention-based Simple Primitives (ASP), demonstrates competitive performance, achieving results comparable to the state-of-the-art.