mlsanityData to 14 Oct 2026

CAILA: Concept-Aware Intra-Layer Adapters for Compositional Zero-Shot Learning

arXiv 2305.16681 ↗First posted 26 May 2023cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

In this paper, we study the problem of Compositional Zero-Shot Learning (CZSL), which is to recognize novel attribute-object combinations with pre-existing concepts. Recent researchers focus on applying large-scale Vision-Language Pre-trained (VLP) models like CLIP with strong generalization ability. However, these methods treat the pre-trained model as a black box and focus on pre- and post-CLIP operations, which do not inherently mine the semantic concept between the layers inside CLIP. We propose to dive deep into the architecture and insert adapters, a parameter-efficient technique proven to be effective among large language models, into each CLIP encoder layer. We further equip adapters with concept awareness so that concept-specific features of "object", "attribute", and "composition" can be extracted. We assess our method on four popular CZSL datasets, MIT-States, C-GQA, UT-Zappos, and VAW-CZSL, which shows state-of-the-art performance compared to existing methods on all of them.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 40 of its 52 references that are in the map. First posted on arXiv 26 May 2023.

Builds on

40 of 52 references.

References · 40

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  5. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  6. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,236
  7. 2021Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervisioncited by 3,864
  8. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,795
  9. 2021Learning to Prompt for Vision-Language Modelscited by 2,281
  10. 2021Align before Fuse: Vision and Language Representation Learning with Momentum Distillationcited by 1,619
  11. 2022Conditional Prompt Learning for Vision-Language Modelscited by 1,433
  12. 2021CLIP-Adapter: Better Vision-Language Models with Feature Adapterscited by 1,026
28 more
  1. 2022Vision Transformer Adapter for Dense Predictionscited by 565
  2. 2017Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Uglycited by 538
  3. 2021Compacter: Efficient Low-Rank Hypercomplex Adapter Layerscited by 460
  4. 2021VL-Adapter: Parameter-Efficient Transfer Learning for Vision-and-Language Taskscited by 320
  5. 2017Feature Generating Networks for Zero-Shot Learningcited by 257
  6. 2013Zero-Shot Learning Through Cross-Modal Transfercited by 237
  7. 2021Scaling Up Vision-Language Pre-training for Image Captioningcited by 196
  8. 2016Learning Deep Representations of Fine-grained Visual Descriptionscited by 182
  9. 2018Zero-shot Recognition via Semantic Embeddings and Knowledge Graphscited by 155
  10. 2016Learning a Deep Embedding Model for Zero-Shot Learningcited by 153
  11. 2019Task-Driven Modular Networks for Zero-Shot Compositional Learningcited by 121
  12. 2021Learning Graph Embeddings for Compositional Zero-shot Learningcited by 112
  13. 2021Open World Compositional Zero-Shot Learningcited by 101
  14. 2017A Generative Adversarial Approach for Zero-Shot Learning from Noisy Textscited by 96
  15. 2020Symmetry and Group in Attribute-Object Compositionscited by 89
  16. 2018Rethinking Knowledge Graph Propagation for Zero-Shot Learningcited by 87
  17. 2020A causal view of compositional zero-shot recognitioncited by 78
  18. 2021FREE: Feature Refinement for Generalized Zero-Shot Learningcited by 67
  19. 2022Learning to Compose Soft Prompts for Compositional Zero-Shot Learningcited by 67
  20. 2022Disentangling Visual Embeddings for Attributes and Objectscited by 55
  21. 2022Siamese Contrastive Embedding Network for Compositional Zero-Shot Learningcited by 55
  22. 2021Learning Graph Embeddings for Open World Compositional Zero-Shot Learningcited by 49
  23. 2016Semantic Jitter: Dense Supervision for Visual Comparisons via Synthetic Imagescited by 45
  24. 2021Independent Prototype Propagation for Zero-Shot Compositionalitycited by 42
  25. 2022KG-SP: Knowledge Guided Simple Primitives for Open World Compositional Zero-Shot Learningcited by 41
  26. 2022Decomposed Soft Prompt Guided Fusion Enhancing for Compositional Zero-Shot Learningcited by 37
  27. 2019TAFE-Net: Task-Aware Feature Embeddings for Low Shot Learningcited by 32
  28. 2022Learning Attention Propagation for Compositional Zero-Shot Learningcited by 20

Built on by

Cited by year

Citing papers per year: 2024: 4; 2025: 3.

7 papers.

  1. 2024CusConcept: Customized Visual Concept Decomposition with Diffusion Modelscited by 9
  2. 2024On the Element-Wise Representation and Reasoning in Zero-Shot Image Recognition: A Systematic Surveycited by 5
  3. 2024SHINE: Saliency-aware HIerarchical NEgative Ranking for Compositional Temporal Groundingcited by 3
  4. 2025A Conditional Probability Framework for Compositional Zero-shot Learningcited by 2
  5. 2025CAMS: Towards Compositional Zero-Shot Learning via Gated Cross-Attention and Multi-Space Disentanglementcited by 1
  6. 2025H2em: Learning Hierarchical Hyperbolic Embeddings for Compositional Zero-Shot Learningcited by 1
  7. 2024Anticipating Future Object Compositions without Forgettingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Prompting Language-Informed Distribution for Compositional Zero-Shot Learning
  2. 2024Unified Framework for Open-World Compositional Zero-shot Learning
  3. 2025Separated Inter/Intra-Modal Fusion Prompts for Compositional Zero-Shot Learning
  4. 2026DIFFCZSL: Compositional Zero-Shot Learning Regularized by Diffusion Representations
  5. 2025Learning Visual Proxy for Compositional Zero-Shot Learning
  6. 2024Graph-guided Cross-composition Feature Disentanglement for Compositional Zero-shot Learning
  7. 2022Prompting Large Pre-trained Vision-Language Models For Compositional Concept Learning
  8. 2025EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning