Distilled Reverse Attention Network for Open-world Compositional Zero-Shot Learning

TL;DR

This paper introduces a novel Distilled Reverse Attention Network for open-world compositional zero-shot learning, effectively recognizing unseen attribute-object pairs by disentangling and modeling their contextual and local features.

Contribution

The paper proposes a new reverse attention and knowledge distillation strategy to learn disentangled, context-aware representations for attributes and objects in OW-CZSL.

Findings

Achieves state-of-the-art performance on three datasets.

Effectively models attribute-object compositionality in open-world settings.

Outperforms previous methods that rely on external knowledge or correlation pruning.

Abstract

Open-World Compositional Zero-Shot Learning (OW-CZSL) aims to recognize new compositions of seen attributes and objects. In OW-CZSL, methods built on the conventional closed-world setting degrade severely due to the unconstrained OW test space. While previous works alleviate the issue by pruning compositions according to external knowledge or correlations in seen pairs, they introduce biases that harm the generalization. Some methods thus predict state and object with independently constructed and trained classifiers, ignoring that attributes are highly context-dependent and visually entangled with objects. In this paper, we propose a novel Distilled Reverse Attention Network to address the challenges. We also model attributes and objects separately but with different motivations, capturing contextuality and locality, respectively. We further design a reverse-and-distill strategy that learns disentangled representations of elementary components in training data supervised by reverse attention and knowledge distillation. We conduct experiments on three datasets and consistently achieve state-of-the-art (SOTA) performance.