mlsanityData to 14 Oct 2026

Symmetry and Group in Attribute-Object Compositions

arXiv 2004.00587 ↗First posted 1 Apr 2020cs.CV cs.LGcited by 89

Not on the map. Why?

Abstract (arXiv)

Attributes and objects can compose diverse compositions. To model the compositional nature of these general concepts, it is a good choice to learn them through transformations, such as coupling and decoupling. However, complex transformations need to satisfy specific principles to guarantee the rationality. In this paper, we first propose a previously ignored principle of attribute-object transformation: Symmetry. For example, coupling peeled-apple with attribute peeled should result in peeled-apple, and decoupling peeled from apple should still output apple. Incorporating the symmetry principle, a transformation framework inspired by group theory is built, i.e. SymNet. SymNet consists of two modules, Coupling Network and Decoupling Network. With the group axioms and symmetry property as objectives, we adopt Deep Neural Networks to implement SymNet and train it in an end-to-end paradigm. Moreover, we propose a Relative Moving Distance (RMD) based recognition method to utilize the attribute change instead of the attribute pattern itself to classify attributes. Our symmetry learning can be utilized for the Compositional Zero-Shot Learning task and outperforms the state-of-the-art on widely-used benchmarks. Code is available at https://github.com/DirtyHarryLYL/SymNet.

Key facts. Cited by 89 papers in the map (data through 14 Oct 2026). First posted on arXiv 1 Apr 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 12; 2022: 19; 2023: 19; 2024: 16; 2025: 18; 2026: 5.

89 papers.

Sort:

By area:

  1. 2021Learning Graph Embeddings for Compositional Zero-shot Learningcited by 112
  2. 2021Open World Compositional Zero-Shot Learningcited by 101
  3. 2022Learning to Compose Soft Prompts for Compositional Zero-Shot Learningcited by 67
  4. 2022Disentangling Visual Embeddings for Attributes and Objectscited by 55
  5. 2022Siamese Contrastive Embedding Network for Compositional Zero-Shot Learningcited by 55
  6. 2021Learning Graph Embeddings for Open World Compositional Zero-Shot Learningcited by 49
  7. 2021Independent Prototype Propagation for Zero-Shot Compositionalitycited by 42
  8. 2022KG-SP: Knowledge Guided Simple Primitives for Open World Compositional Zero-Shot Learningcited by 41
  9. 2022Decomposed Soft Prompt Guided Fusion Enhancing for Compositional Zero-Shot Learningcited by 37
  10. 2022Do Vision-Language Pretrained Models Learn Composable Primitive Concepts?cited by 31
  11. 2022BatchFormer: Learning to Explore Sample Relationships for Robust Representation Learningcited by 29
  12. 2022Open-vocabulary Attribute Detectioncited by 29
38 more
  1. 2023Learning Attention as Disentangler for Compositional Zero-shot Learningcited by 29
  2. 2023Learning Conditional Attributes for Compositional Zero-Shot Learningcited by 28
  3. 2023Troika: Multi-Path Cross-Modal Traction for Compositional Zero-Shot Learningcited by 27
  4. 2022Constructing Balance from Imbalance for Long-tailed Image Recognitioncited by 25
  5. 2022Learning Invariant Visual Representations for Compositional Zero-Shot Learningcited by 24
  6. 2023Prompting Language-Informed Distribution for Compositional Zero-Shot Learningcited by 24
  7. 2022Learning Attention Propagation for Compositional Zero-Shot Learningcited by 20
  8. 2024Context-based and Diversity-driven Specificity in Compositional Zero-Shot Learningcited by 20
  9. 2021Relation-aware Compositional Zero-shot Learning for Attribute-Object Pair Recognitioncited by 19
  10. 2023DRPT: Disentangled and Recurrent Prompt Tuning for Compositional Zero-Shot Learningcited by 17
  11. 2021Zero-Shot Compositional Concept Learningcited by 16
  12. 20213D Compositional Zero-shot Learning with DeCompositional Consensuscited by 16
  13. 2023Hierarchical Visual Primitive Experts for Compositional Zero-Shot Learningcited by 16
  14. 2023GIPCOL: Graph-Injected Soft Prompting for Compositional Zero-Shot Learningcited by 16
  15. 2025Learning Clustering-based Prototypes for Compositional Zero-shot Learningcited by 14
  16. 2022On Leveraging Variational Graph Embeddings for Open World Compositional Zero-Shot Learningcited by 13
  17. 2023Chop & Learn: Recognizing and Generating Object-State Compositionscited by 13
  18. 2022Prompting Large Pre-trained Vision-Language Models For Compositional Concept Learningcited by 12
  19. 2023Compositional Zero-shot Learning via Progressive Language-based Observationscited by 12
  20. 2022Beyond Object Recognition: A New Benchmark towards Object Concept Learningcited by 11
  21. 2023Distilled Reverse Attention Network for Open-world Compositional Zero-Shot Learningcited by 11
  22. 2021DiagViB-6: A Diagnostic Benchmark Suite for Vision Models in the Presence of Shortcut and Generalization Opportunitiescited by 10
  23. 2022ProCC: Progressive Cross-primitive Compatibility for Open-World Compositional Zero-Shot Learningcited by 9
  24. 2024CusConcept: Customized Visual Concept Decomposition with Diffusion Modelscited by 9
  25. 2021Learning Single/Multi-Attribute of Object with Symmetry and Groupcited by 8
  26. 2023Revealing the Proximate Long-Tail Distribution in Compositional Zero-Shot Learningcited by 8
  27. 2023CAILA: Concept-Aware Intra-Layer Adapters for Compositional Zero-Shot Learningcited by 7
  28. 2024TsCA: On the Semantic Consistency Alignment via Conditional Transport for Compositional Zero-Shot Learningcited by 6
  29. 2024On the Element-Wise Representation and Reasoning in Zero-Shot Image Recognition: A Systematic Surveycited by 5
  30. 2023SETI: Systematicity Evaluation of Textual Inferencecited by 4
  31. 2025Zero-shot Compositional Action Recognition with Neural Logic Constraintscited by 4
  32. 2021Generating Compositional Color Representations from Textcited by 3
  33. 2022Reference-Limited Compositional Zero-Shot Learningcited by 3
  34. 2022LOCL: Learning Object-Attribute Composition using Localizationcited by 3
  35. 2022Mutual Balancing in State-Object Components for Compositional Zero-Shot Learningcited by 3
  36. 2023HOPE: A Memory-Based and Composition-Aware Framework for Zero-Shot Learning with Hopfield Network and Soft Mixture of Expertscited by 3
  37. 2026FlowComposer: Composable Flows for Compositional Zero-Shot Learningcited by 3
  38. 2024Not Just Object, But State: Compositional Incremental Learning without Forgettingcited by 2

50 most cited of 89 All 89 (JSON)