# A causal view of compositional zero-shot recognition

arXiv: https://arxiv.org/abs/2006.14610 · HTML: https://mlsanity.com/paper/2006.14610/

## Key facts

- Cited by 78 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Jun 2020.

## Built on by (most cited first, 30 of 78)

- [Linguistic Binding in Diffusion Models: Enhancing Attribute Correspondence through Attention Map Alignment](https://mlsanity.com/paper/2306.08877/) (2023)
- [Causality-inspired Single-source Domain Generalization for Medical Image Segmentation](https://mlsanity.com/paper/2111.12525/) (2021)
- [Learning Graph Embeddings for Compositional Zero-shot Learning](https://mlsanity.com/paper/2102.01987/) (2021)
- [Counterfactual Zero-Shot and Open-Set Visual Recognition](https://mlsanity.com/paper/2103.00887/) (2021)
- [Disentangling Visual Embeddings for Attributes and Objects](https://mlsanity.com/paper/2205.08536/) (2022)
- [Siamese Contrastive Embedding Network for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2206.14475/) (2022)
- [TransZero: Attribute-guided Transformer for Zero-Shot Learning](https://mlsanity.com/paper/2112.01683/) (2021)
- [Learning Graph Embeddings for Open World Compositional Zero-Shot Learning](https://mlsanity.com/paper/2105.01017/) (2021)
- [Independent Prototype Propagation for Zero-Shot Compositionality](https://mlsanity.com/paper/2106.00305/) (2021)
- [KG-SP: Knowledge Guided Simple Primitives for Open World Compositional Zero-Shot Learning](https://mlsanity.com/paper/2205.06784/) (2022)
- [An Image is Worth More Than a Thousand Words: Towards Disentanglement in the Wild](https://mlsanity.com/paper/2106.15610/) (2021)
- [BatchFormer: Learning to Explore Sample Relationships for Robust Representation Learning](https://mlsanity.com/paper/2203.01522/) (2022)
- [Learning Attention as Disentangler for Compositional Zero-shot Learning](https://mlsanity.com/paper/2303.15111/) (2023)
- [TransZero++: Cross Attribute-Guided Transformer for Zero-Shot Learning](https://mlsanity.com/paper/2112.08643/) (2021)
- [Learning Conditional Attributes for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2305.17940/) (2023)
- [How to Reuse and Compose Knowledge for a Lifetime of Tasks: A Survey on Continual Learning and Functional Composition](https://mlsanity.com/paper/2207.07730/) (2022)
- [Learning Invariant Visual Representations for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2206.00415/) (2022)
- [Prompting Language-Informed Distribution for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2305.14428/) (2023)
- [CausalCity: Complex Simulations with Agency for Causal Discovery and Reasoning](https://mlsanity.com/paper/2106.13364/) (2021)
- [Learning Domain Invariant Representations for Generalizable Person Re-Identification](https://mlsanity.com/paper/2103.15890/) (2021)
- [Causal Triplet: An Open Challenge for Intervention-centric Causal Representation Learning](https://mlsanity.com/paper/2301.05169/) (2023)
- [Learning Attention Propagation for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2210.11557/) (2022)
- [Relation-aware Compositional Zero-shot Learning for Attribute-Object Pair Recognition](https://mlsanity.com/paper/2108.04603/) (2021)
- [DRPT: Disentangled and Recurrent Prompt Tuning for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2305.01239/) (2023)
- [3D Compositional Zero-shot Learning with DeCompositional Consensus](https://mlsanity.com/paper/2111.14673/) (2021)
- [Hierarchical Visual Primitive Experts for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2308.04016/) (2023)
- [Domain Generalization via Rationale Invariance](https://mlsanity.com/paper/2308.11158/) (2023)
- [Learning Clustering-based Prototypes for Compositional Zero-shot Learning](https://mlsanity.com/paper/2502.06501/) (2025)
- [Latent Space Explanation by Intervention](https://mlsanity.com/paper/2112.04895/) (2021)
- [Improving Systematic Generalization Through Modularity and Augmentation](https://mlsanity.com/paper/2202.10745/) (2022)

## Abstract (arXiv)

People easily recognize new visual categories that are new combinations of known components. This compositional generalization capacity is critical for learning in real-world domains like vision and language because the long tail of new combinations dominates the distribution. Unfortunately, learning systems struggle with compositional generalization because they often build on features that are correlated with class labels even if they are not "essential" for the class. This leads to consistent misclassification of samples from a new distribution, like new combinations of known components. Here we describe an approach for compositional generalization that builds on causal ideas. First, we describe compositional zero-shot learning from a causal perspective, and propose to view zero-shot inference as finding "which intervention caused the image?". Second, we present a causal-inspired embedding model that learns disentangled representations of elementary components of visual objects from correlated (confounded) training data. We evaluate this approach on two datasets for predicting new combinations of attribute-object pairs: A well-controlled synthesized images dataset and a real-world dataset which consists of fine-grained types of shoes. We show improvements compared to strong baselines.