mlsanityData to 14 Oct 2026

Learning Conditional Attributes for Compositional Zero-Shot Learning

arXiv 2305.17940 ↗First posted 29 May 2023cs.CVcited by 28

Not on the map. Why?

Abstract (arXiv)

Compositional Zero-Shot Learning (CZSL) aims to train models to recognize novel compositional concepts based on learned concepts such as attribute-object combinations. One of the challenges is to model attributes interacted with different objects, e.g., the attribute ``wet" in ``wet apple" and ``wet cat" is different. As a solution, we provide analysis and argue that attributes are conditioned on the recognized object and input image and explore learning conditional attribute embeddings by a proposed attribute learning framework containing an attribute hyper learner and an attribute base learner. By encoding conditional attributes, our model enables to generate flexible attribute embeddings for generalization from seen to unseen compositions. Experiments on CZSL benchmarks, including the more challenging C-GQA dataset, demonstrate better performances compared with other state-of-the-art approaches and validate the importance of learning conditional attributes. Code is available at https://github.com/wqshmzh/CANet-CZSL

Key facts. Cited by 28 papers in the map (data through 14 Oct 2026). Builds on 29 of its 46 references that are in the map. First posted on arXiv 29 May 2023.

Builds on

29 of 46 references.

References · 29

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2016Layer Normalizationcited by 5,669
  4. 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,474
  5. 2016Enriching Word Vectors with Subword Informationcited by 1,583
  6. 2016An Empirical Study and Analysis of Generalized Zero-Shot Learning for Object Recognition in the Wildcited by 146
  7. 2019Task-Driven Modular Networks for Zero-Shot Compositional Learningcited by 121
  8. 2021Learning Graph Embeddings for Compositional Zero-shot Learningcited by 112
  9. 2021Open World Compositional Zero-Shot Learningcited by 101
  10. 2016Learning feed-forward one-shot learnerscited by 93
  11. 2016Fully-adaptive Feature Sharing in Multi-Task Networks with Applications in Person Attribute Classificationcited by 93
  12. 2020Symmetry and Group in Attribute-Object Compositionscited by 89
17 more
  1. 2019AdaCos: Adaptively Scaling Cosine Logits for Effectively Learning Deep Face Representationscited by 83
  2. 2020A causal view of compositional zero-shot recognitioncited by 78
  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. 2016Semantic Jitter: Dense Supervision for Visual Comparisons via Synthetic Imagescited by 45
  7. 2021Independent Prototype Propagation for Zero-Shot Compositionalitycited by 42
  8. 2019TAFE-Net: Task-Aware Feature Embeddings for Low Shot Learningcited by 32
  9. 2022Learning Invariant Visual Representations for Compositional Zero-Shot Learningcited by 24
  10. 2016Deep Attributes Driven Multi-Camera Person Re-identificationcited by 21
  11. 2021Relation-aware Compositional Zero-shot Learning for Attribute-Object Pair Recognitioncited by 19
  12. 2021Zero-Shot Compositional Concept Learningcited by 16
  13. 2022On Leveraging Variational Graph Embeddings for Open World Compositional Zero-Shot Learningcited by 13
  14. 2016Learning to generalize to new compositions in image understandingcited by 12
  15. 2016End-to-End Localization and Ranking for Relative Attributescited by 9
  16. 2020Learning to Infer Unseen Single-/Multi-Attribute-Object Compositions with Graph Networkscited by 5
  17. 2021Translational Concept Embedding for Generalized Compositional Zero-shot Learningcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 4; 2024: 12; 2025: 9; 2026: 3.

28 papers.

Sort:

By area:

  1. 2024OneRestore: A Universal Restoration Framework for Composite Degradationcited by 92
  2. 2024Context-based and Diversity-driven Specificity in Compositional Zero-Shot Learningcited by 20
  3. 2025Learning Clustering-based Prototypes for Compositional Zero-shot Learningcited by 14
  4. 2025Does Data Scaling Lead to Visual Compositional Generalization?cited by 13
  5. 2023Compositional Zero-shot Learning via Progressive Language-based Observationscited by 12
  6. 2024C2C: Component-to-Composition Learning for Zero-Shot Compositional Action Recognitioncited by 9
  7. 2024On the Element-Wise Representation and Reasoning in Zero-Shot Image Recognition: A Systematic Surveycited by 5
  8. 2023Open-Pose 3D Zero-Shot Learning: Benchmark and Challengescited by 4
  9. 2023HOPE: A Memory-Based and Composition-Aware Framework for Zero-Shot Learning with Hopfield Network and Soft Mixture of Expertscited by 3
  10. 2026FlowComposer: Composable Flows for Compositional Zero-Shot Learningcited by 3
  11. 2024Not Just Object, But State: Compositional Incremental Learning without Forgettingcited by 2
  12. 2025Learning Visual Proxy for Compositional Zero-Shot Learningcited by 2
16 more
  1. 2025Visual Adaptive Prompting for Compositional Zero-Shot Learningcited by 2
  2. 2025A Conditional Probability Framework for Compositional Zero-shot Learningcited by 2
  3. 2023Recognizing Unseen States of Unknown Objects by Leveraging Knowledge Graphscited by 1
  4. 2024CSCNET: Class-Specified Cascaded Network for Compositional Zero-Shot Learningcited by 1
  5. 2024MAC: A Benchmark for Multiple Attributes Compositional Zero-Shot Learningcited by 1
  6. 2024Leveraging MLLM Embeddings and Attribute Smoothing for Compositional Zero-Shot Learningcited by 1
  7. 2024Unified Framework for Open-World Compositional Zero-shot Learningcited by 1
  8. 2025MSCI: Addressing CLIP's Inherent Limitations for Compositional Zero-Shot Learningcited by 1
  9. 2024Coarse or Fine? Recognising Action End States without Labelscited by 0
  10. 2024Anticipating Future Object Compositions without Forgettingcited by 0
  11. 2024Focus-Consistent Multi-Level Aggregation for Compositional Zero-Shot Learningcited by 0
  12. 2025Semantically Guided Dynamic Visual Prototype Refinement for Compositional Zero-Shot Learningcited by 0
  13. 2025SalientFusion: Context-Aware Compositional Zero-Shot Food Recognitioncited by 0
  14. 2025Prompt-Based Continual Compositional Zero-Shot Learningcited by 0
  15. 2026Structure-aware Prompt Adaptation from Seen to Unseen for Open-Vocabulary Compositional Zero-Shot Learningcited by 0
  16. 2026Progressive Reasoning with Primitive Correction for Compositional Zero-Shot Learningcited by 0