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

arXiv: https://arxiv.org/abs/2303.00404 · HTML: https://mlsanity.com/paper/2303.00404/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 47 references that are in the map.
- First posted on arXiv 1 Mar 2023.

## Builds on (most cited first, 29 of 29)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [Dual Attention Network for Scene Segmentation](https://mlsanity.com/paper/1809.02983/) (2018)
- [CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification](https://mlsanity.com/paper/2103.14899/) (2021)
- [SCA-CNN: Spatial and Channel-wise Attention in Convolutional Networks for Image Captioning](https://mlsanity.com/paper/1611.05594/) (2016)
- [Task-Driven Modular Networks for Zero-Shot Compositional Learning](https://mlsanity.com/paper/1905.05908/) (2019)
- [Learning Graph Embeddings for Compositional Zero-shot Learning](https://mlsanity.com/paper/2102.01987/) (2021)
- [Open World Compositional Zero-Shot Learning](https://mlsanity.com/paper/2101.12609/) (2021)
- [The Devil is in the Tails: Fine-grained Classification in the Wild](https://mlsanity.com/paper/1709.01450/) (2017)
- [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)
- [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)
- [Learning Graph Embeddings for Open World Compositional Zero-Shot Learning](https://mlsanity.com/paper/2105.01017/) (2021)
- [Semantic Jitter: Dense Supervision for Visual Comparisons via Synthetic Images](https://mlsanity.com/paper/1612.06341/) (2016)
- [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)
- [Progressive Sparse Local Attention for Video object detection](https://mlsanity.com/paper/1903.09126/) (2019)
- [Task Aligned Generative Meta-learning for Zero-shot Learning](https://mlsanity.com/paper/2103.02185/) (2021)
- [Relation-aware Compositional Zero-shot Learning for Attribute-Object Pair Recognition](https://mlsanity.com/paper/2108.04603/) (2021)
- [Zero-Shot Compositional Concept Learning](https://mlsanity.com/paper/2107.05176/) (2021)
- [Task-Aware Feature Generation for Zero-Shot Compositional Learning](https://mlsanity.com/paper/1906.04854/) (2019)
- [Attribute-Modulated Generative Meta Learning for Zero-Shot Classification](https://mlsanity.com/paper/2104.10857/) (2021)
- [Rethink, Revisit, Revise: A Spiral Reinforced Self-Revised Network for Zero-Shot Learning](https://mlsanity.com/paper/2112.00410/) (2021)
- [An Entropy-guided Reinforced Partial Convolutional Network for Zero-Shot Learning](https://mlsanity.com/paper/2111.02139/) (2021)
- [Diversity-boosted Generalization-Specialization Balancing for Zero-shot Learning](https://mlsanity.com/paper/2201.01961/) (2022)

## Built on by (most cited first, 11 of 11)

- [Context-based and Diversity-driven Specificity in Compositional Zero-Shot Learning](https://mlsanity.com/paper/2402.17251/) (2024)
- [Learning Clustering-based Prototypes for Compositional Zero-shot Learning](https://mlsanity.com/paper/2502.06501/) (2025)
- [On the Element-Wise Representation and Reasoning in Zero-Shot Image Recognition: A Systematic Survey](https://mlsanity.com/paper/2408.04879/) (2024)
- [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)
- [A Conditional Probability Framework for Compositional Zero-shot Learning](https://mlsanity.com/paper/2507.17377/) (2025)
- [Unified Framework for Open-World Compositional Zero-shot Learning](https://mlsanity.com/paper/2412.04083/) (2024)
- [MSCI: Addressing CLIP's Inherent Limitations for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2505.10289/) (2025)
- [Interpretable Open-Vocabulary Referring Object Detection with Reverse Contrast Attention](https://mlsanity.com/paper/2507.19891/) (2025)
- [CAMS: Towards Compositional Zero-Shot Learning via Gated Cross-Attention and Multi-Space Disentanglement](https://mlsanity.com/paper/2511.16378/) (2025)
- [RevCD -- Reversed Conditional Diffusion for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2409.00511/) (2024)
- [Semantically Guided Dynamic Visual Prototype Refinement for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2501.07114/) (2025)

## Abstract (arXiv)

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.