# Learning Invariant Visual Representations for Compositional Zero-Shot Learning

arXiv: https://arxiv.org/abs/2206.00415 · HTML: https://mlsanity.com/paper/2206.00415/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 46 references that are in the map.
- First posted on arXiv 1 Jun 2022.

## Builds on (most cited first, 30 of 33)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Invariant Risk Minimization](https://mlsanity.com/paper/1907.02893/) (2019)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [Deep CORAL: Correlation Alignment for Deep Domain Adaptation](https://mlsanity.com/paper/1607.01719/) (2016)
- [Generalizing to Unseen Domains: A Survey on Domain Generalization](https://mlsanity.com/paper/2103.03097/) (2021)
- [Domain Generalization: A Survey](https://mlsanity.com/paper/2103.02503/) (2021)
- [Out-of-Distribution Generalization via Risk Extrapolation (REx)](https://mlsanity.com/paper/2003.00688/) (2020)
- [Domain Generalization via Invariant Feature Representation](https://mlsanity.com/paper/1301.2115/) (2013)
- [Domain Generalization by Solving Jigsaw Puzzles](https://mlsanity.com/paper/1903.06864/) (2019)
- [Self-Challenging Improves Cross-Domain Generalization](https://mlsanity.com/paper/2007.02454/) (2020)
- [Wasserstein Auto-Encoders](https://mlsanity.com/paper/1711.01558/) (2017)
- [Visual Relationship Detection with Language Priors](https://mlsanity.com/paper/1608.00187/) (2016)
- [Learning to Learn Single Domain Generalization](https://mlsanity.com/paper/2003.13216/) (2020)
- [Generalizing Across Domains via Cross-Gradient Training](https://mlsanity.com/paper/1804.10745/) (2018)
- [Gradient Matching for Domain Generalization](https://mlsanity.com/paper/2104.09937/) (2021)
- [Feature Generating Networks for Zero-Shot Learning](https://mlsanity.com/paper/1712.00981/) (2017)
- [Zero-Shot Learning -- The Good, the Bad and the Ugly](https://mlsanity.com/paper/1703.04394/) (2017)
- [Invariance Principle Meets Information Bottleneck for Out-of-Distribution Generalization](https://mlsanity.com/paper/2106.06607/) (2021)
- [SelfReg: Self-supervised Contrastive Regularization for Domain Generalization](https://mlsanity.com/paper/2104.09841/) (2021)
- [A Meta-Transfer Objective for Learning to Disentangle Causal Mechanisms](https://mlsanity.com/paper/1901.10912/) (2019)
- [An Empirical Study and Analysis of Generalized Zero-Shot Learning for Object Recognition in the Wild](https://mlsanity.com/paper/1605.04253/) (2016)
- [Learning explanations that are hard to vary](https://mlsanity.com/paper/2009.00329/) (2020)
- [Task-Driven Modular Networks for Zero-Shot Compositional Learning](https://mlsanity.com/paper/1905.05908/) (2019)
- [Anchor regression: heterogeneous data meets causality](https://mlsanity.com/paper/1801.06229/) (2018)
- [Domain Agnostic Learning with Disentangled Representations](https://mlsanity.com/paper/1904.12347/) (2019)
- [Open World Compositional Zero-Shot Learning](https://mlsanity.com/paper/2101.12609/) (2021)
- [Towards Principled Disentanglement for Domain Generalization](https://mlsanity.com/paper/2111.13839/) (2021)
- [Symmetry and Group in Attribute-Object Compositions](https://mlsanity.com/paper/2004.00587/) (2020)
- [A causal view of compositional zero-shot recognition](https://mlsanity.com/paper/2006.14610/) (2020)

## Built on by (most cited first, 24 of 24)

- [Learning Attention as Disentangler for Compositional Zero-shot Learning](https://mlsanity.com/paper/2303.15111/) (2023)
- [Learning Conditional Attributes for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2305.17940/) (2023)
- [Troika: Multi-Path Cross-Modal Traction for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2303.15230/) (2023)
- [Prompting Language-Informed Distribution for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2305.14428/) (2023)
- [DRPT: Disentangled and Recurrent Prompt Tuning for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2305.01239/) (2023)
- [Hierarchical Visual Primitive Experts for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2308.04016/) (2023)
- [Learning Clustering-based Prototypes for Compositional Zero-shot Learning](https://mlsanity.com/paper/2502.06501/) (2025)
- [Compositional Zero-shot Learning via Progressive Language-based Observations](https://mlsanity.com/paper/2311.14749/) (2023)
- [On the Element-Wise Representation and Reasoning in Zero-Shot Image Recognition: A Systematic Survey](https://mlsanity.com/paper/2408.04879/) (2024)
- [Reference-Limited Compositional Zero-Shot Learning](https://mlsanity.com/paper/2208.10046/) (2022)
- [HOPE: A Memory-Based and Composition-Aware Framework for Zero-Shot Learning with Hopfield Network and Soft Mixture of Experts](https://mlsanity.com/paper/2311.14747/) (2023)
- [Not Just Object, But State: Compositional Incremental Learning without Forgetting](https://mlsanity.com/paper/2411.01739/) (2024)
- [A Conditional Probability Framework for Compositional Zero-shot Learning](https://mlsanity.com/paper/2507.17377/) (2025)
- [Recognizing Unseen States of Unknown Objects by Leveraging Knowledge Graphs](https://mlsanity.com/paper/2307.12179/) (2023)
- [CSCNET: Class-Specified Cascaded Network for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2403.05924/) (2024)
- [MAC: A Benchmark for Multiple Attributes Compositional Zero-Shot Learning](https://mlsanity.com/paper/2406.12757/) (2024)
- [Leveraging MLLM Embeddings and Attribute Smoothing for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2411.12584/) (2024)
- [CAMS: Towards Compositional Zero-Shot Learning via Gated Cross-Attention and Multi-Space Disentanglement](https://mlsanity.com/paper/2511.16378/) (2025)
- [H2em: Learning Hierarchical Hyperbolic Embeddings for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2512.20029/) (2025)
- [Simple Primitives with Feasibility- and Contextuality-Dependence for Open-World Compositional Zero-shot Learning](https://mlsanity.com/paper/2211.02895/) (2022)
- [Compositional Zero-Shot Learning for Attribute-Based Object Reference in Human-Robot Interaction](https://mlsanity.com/paper/2312.13655/) (2023)
- [Focus-Consistent Multi-Level Aggregation for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2408.17083/) (2024)
- [Semantically Guided Dynamic Visual Prototype Refinement for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2501.07114/) (2025)
- [Prompt-Based Continual Compositional Zero-Shot Learning](https://mlsanity.com/paper/2512.09172/) (2025)

## Abstract (arXiv)

Compositional Zero-Shot Learning (CZSL) aims to recognize novel compositions using knowledge learned from seen attribute-object compositions in the training set. Previous works mainly project an image and a composition into a common embedding space to measure their compatibility score. However, both attributes and objects share the visual representations learned above, leading the model to exploit spurious correlations and bias towards seen pairs. Instead, we reconsider CZSL as an out-of-distribution generalization problem. If an object is treated as a domain, we can learn object-invariant features to recognize the attributes attached to any object reliably. Similarly, attribute-invariant features can also be learned when recognizing the objects with attributes as domains. Specifically, we propose an invariant feature learning framework to align different domains at the representation and gradient levels to capture the intrinsic characteristics associated with the tasks. Experiments on two CZSL benchmarks demonstrate that the proposed method significantly outperforms the previous state-of-the-art.