A Conditional Probability Framework for Compositional Zero-shot Learning

TL;DR

This paper introduces a Conditional Probability Framework for compositional zero-shot learning that models attribute-object dependencies explicitly, improving recognition of unseen object-attribute combinations by leveraging semantic context and cross-attention mechanisms.

Contribution

It proposes a novel framework that explicitly models attribute-object interdependence in CZSL using conditional probabilities and enhances feature learning with textual and cross-attention methods.

Findings

Outperforms existing methods on multiple CZSL benchmarks.

Effectively captures attribute-object dependencies for unseen compositions.

Improves generalization through semantic-aware feature enhancement.

Abstract

Compositional Zero-Shot Learning (CZSL) aims to recognize unseen combinations of known objects and attributes by leveraging knowledge from previously seen compositions. Traditional approaches primarily focus on disentangling attributes and objects, treating them as independent entities during learning. However, this assumption overlooks the semantic constraints and contextual dependencies inside a composition. For example, certain attributes naturally pair with specific objects (e.g., "striped" applies to "zebra" or "shirts" but not "sky" or "water"), while the same attribute can manifest differently depending on context (e.g., "young" in "young tree" vs. "young dog"). Thus, capturing attribute-object interdependence remains a fundamental yet long-ignored challenge in CZSL. In this paper, we adopt a Conditional Probability Framework (CPF) to explicitly model attribute-object dependencies. We decompose the probability of a composition into two components: the likelihood of an object and the conditional likelihood of its attribute. To enhance object feature learning, we incorporate textual descriptors to highlight semantically relevant image regions. These enhanced object features then guide attribute learning through a cross-attention mechanism, ensuring better contextual alignment. By jointly optimizing object likelihood and conditional attribute likelihood, our method effectively captures compositional dependencies and generalizes well to unseen compositions. Extensive experiments on multiple CZSL benchmarks demonstrate the superiority of our approach. Code is available at here.