# Relation-aware Compositional Zero-shot Learning for Attribute-Object Pair Recognition

arXiv: https://arxiv.org/abs/2108.04603 · HTML: https://mlsanity.com/paper/2108.04603/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 87 references that are in the map.
- First posted on arXiv 10 Aug 2021.

## Builds on (most cited first, 30 of 42)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks](https://mlsanity.com/paper/1908.02265/) (2019)
- [Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising](https://mlsanity.com/paper/1608.03981/) (2016)
- [Towards Open Set Deep Networks](https://mlsanity.com/paper/1511.06233/) (2015)
- [Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Ugly](https://mlsanity.com/paper/1707.00600/) (2017)
- [12-in-1: Multi-Task Vision and Language Representation Learning](https://mlsanity.com/paper/1912.02315/) (2019)
- [Feature Generating Networks for Zero-Shot Learning](https://mlsanity.com/paper/1712.00981/) (2017)
- [Key-Value Memory Networks for Directly Reading Documents](https://mlsanity.com/paper/1606.03126/) (2016)
- [FractalNet: Ultra-Deep Neural Networks without Residuals](https://mlsanity.com/paper/1605.07648/) (2016)
- [A Decomposable Attention Model for Natural Language Inference](https://mlsanity.com/paper/1606.01933/) (2016)
- [Learning Human-Object Interactions by Graph Parsing Neural Networks](https://mlsanity.com/paper/1808.07962/) (2018)
- [Inverting Visual Representations with Convolutional Networks](https://mlsanity.com/paper/1506.02753/) (2015)
- [f-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learning](https://mlsanity.com/paper/1903.10132/) (2019)
- [Zero-shot Recognition via Semantic Embeddings and Knowledge Graphs](https://mlsanity.com/paper/1803.08035/) (2018)
- [An Empirical Study and Analysis of Generalized Zero-Shot Learning for Object Recognition in the Wild](https://mlsanity.com/paper/1605.04253/) (2016)
- [Semantic Autoencoder for Zero-Shot Learning](https://mlsanity.com/paper/1704.08345/) (2017)
- [Task-Driven Modular Networks for Zero-Shot Compositional Learning](https://mlsanity.com/paper/1905.05908/) (2019)
- [Synthesized Classifiers for Zero-Shot Learning](https://mlsanity.com/paper/1603.00550/) (2016)
- [Symmetry and Group in Attribute-Object Compositions](https://mlsanity.com/paper/2004.00587/) (2020)
- [Zero-Shot Video Object Segmentation via Attentive Graph Neural Networks](https://mlsanity.com/paper/2001.06807/) (2020)
- [A causal view of compositional zero-shot recognition](https://mlsanity.com/paper/2006.14610/) (2020)
- [Zero-Shot Visual Recognition using Semantics-Preserving Adversarial Embedding Networks](https://mlsanity.com/paper/1712.01928/) (2017)
- [Embedding Symbolic Knowledge into Deep Networks](https://mlsanity.com/paper/1909.01161/) (2019)
- [Invertible Zero-Shot Recognition Flows](https://mlsanity.com/paper/2007.04873/) (2020)
- [Spatiotemporal Co-attention Recurrent Neural Networks for Human-Skeleton Motion Prediction](https://mlsanity.com/paper/1909.13245/) (2019)
- [Learning Attributes Equals Multi-Source Domain Generalization](https://mlsanity.com/paper/1605.00743/) (2016)

## Built on by (most cited first, 19 of 19)

- [Disentangling Visual Embeddings for Attributes and Objects](https://mlsanity.com/paper/2205.08536/) (2022)
- [Learning Conditional Attributes for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2305.17940/) (2023)
- [Context-based and Diversity-driven Specificity in Compositional Zero-Shot Learning](https://mlsanity.com/paper/2402.17251/) (2024)
- [Hierarchical Visual Primitive Experts for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2308.04016/) (2023)
- [Chop & Learn: Recognizing and Generating Object-State Compositions](https://mlsanity.com/paper/2309.14339/) (2023)
- [Distilled Reverse Attention Network for Open-world Compositional Zero-Shot Learning](https://mlsanity.com/paper/2303.00404/) (2023)
- [ProCC: Progressive Cross-primitive Compatibility for Open-World Compositional Zero-Shot Learning](https://mlsanity.com/paper/2211.12417/) (2022)
- [Distance Matters in Human-Object Interaction Detection](https://mlsanity.com/paper/2207.01869/) (2022)
- [On the Element-Wise Representation and Reasoning in Zero-Shot Image Recognition: A Systematic Survey](https://mlsanity.com/paper/2408.04879/) (2024)
- [LOCL: Learning Object-Attribute Composition using Localization](https://mlsanity.com/paper/2210.03780/) (2022)
- [A Conditional Probability Framework for Compositional Zero-shot Learning](https://mlsanity.com/paper/2507.17377/) (2025)
- [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)
- [Unified Framework for Open-World Compositional Zero-shot Learning](https://mlsanity.com/paper/2412.04083/) (2024)
- [Compositional Zero-Shot Learning with Contextualized Cues and Adaptive Contrastive Training](https://mlsanity.com/paper/2412.07161/) (2024)
- [Compositional Zero-Shot Learning: A Survey](https://mlsanity.com/paper/2510.11106/) (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)
- [Progressive Reasoning with Primitive Correction for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2607.05911/) (2026)

## Abstract (arXiv)

This paper proposes a novel model for recognizing images with composite attribute-object concepts, notably for composite concepts that are unseen during model training. We aim to explore the three key properties required by the task --- relation-aware, consistent, and decoupled --- to learn rich and robust features for primitive concepts that compose attribute-object pairs. To this end, we propose the Blocked Message Passing Network (BMP-Net). The model consists of two modules. The concept module generates semantically meaningful features for primitive concepts, whereas the visual module extracts visual features for attributes and objects from input images. A message passing mechanism is used in the concept module to capture the relations between primitive concepts. Furthermore, to prevent the model from being biased towards seen composite concepts and reduce the entanglement between attributes and objects, we propose a blocking mechanism that equalizes the information available to the model for both seen and unseen concepts. Extensive experiments and ablation studies on two benchmarks show the efficacy of the proposed model.