mlsanityData to 7 Oct 2026

MAC: A Benchmark for Multiple Attributes Compositional Zero-Shot Learning

arXiv 2406.12757 ↗First posted 18 Jun 2024cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

Compositional Zero-Shot Learning (CZSL) aims to learn semantic primitives (attributes and objects) from seen compositions and recognize unseen attribute-object compositions. Existing CZSL datasets focus on single attributes, neglecting the fact that objects naturally exhibit multiple interrelated attributes. Their narrow attribute scope and single attribute labeling introduce annotation biases, misleading the learning of attributes and causing inaccurate evaluation. To address these issues, we introduce the Multi-Attribute Composition (MAC) dataset, encompassing 22,838 images and 17,627 compositions with comprehensive and representative attribute annotations. MAC shows complex relationship between attributes and objects, with each attribute type linked to an average of 82.2 object types, and each object type associated with 31.4 attribute types. Based on MAC, we propose multi-attribute compositional zero-shot learning that requires deeper semantic understanding and advanced attribute associations, establishing a more realistic and challenging benchmark for CZSL. We also propose Multi-attribute Visual-Primitive Integrator (MVP-Integrator), a robust baseline for multi-attribute CZSL, which disentangles semantic primitives and performs effective visual-primitive association. Experimental results demonstrate that MVP-Integrator significantly outperforms existing CZSL methods on MAC with improved inference efficiency.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 46 of its 65 references that are in the map. First posted on arXiv 18 Jun 2024.

Builds on

46 of 65 references.

References · 46

  1. 2017Attention Is All You Needcited by 59,932
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2020Language Models are Few-Shot Learnerscited by 32,199
  4. 2023Visual Instruction Tuningcited by 7,792
  5. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,195
  6. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,769
  7. 2021Learning to Prompt for Vision-Language Modelscited by 2,269
  8. 2022Conditional Prompt Learning for Vision-Language Modelscited by 1,427
  9. 2021CLIP-Adapter: Better Vision-Language Models with Feature Adapterscited by 1,021
  10. 2021Open-vocabulary Object Detection via Vision and Language Knowledge Distillationcited by 903
  11. 2023Vision-Language Models for Vision Tasks: A Surveycited by 834
  12. 2021How Attentive are Graph Attention Networks?cited by 818
34 more
  1. 2021P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Taskscited by 686
  2. 2022MaPLe: Multi-modal Prompt Learningcited by 685
  3. 2021Extract Free Dense Labels from CLIPcited by 580
  4. 2023Scaling Open-Vocabulary Object Detectioncited by 335
  5. 2022Prompt Distribution Learningcited by 235
  6. 2017Detecting and Recognizing Human-Object Interactionscited by 199
  7. 2023PACO: Parts and Attributes of Common Objectscited by 146
  8. 2019Task-Driven Modular Networks for Zero-Shot Compositional Learningcited by 121
  9. 2021Learning Graph Embeddings for Compositional Zero-shot Learningcited by 112
  10. 2020Learning Human-Object Interaction Detection using Interaction Pointscited by 108
  11. 2024Why are Visually-Grounded Language Models Bad at Image Classification?cited by 101
  12. 2021Open World Compositional Zero-Shot Learningcited by 100
  13. 2021Learning to Predict Visual Attributes in the Wildcited by 95
  14. 2020Symmetry and Group in Attribute-Object Compositionscited by 89
  15. 2020A causal view of compositional zero-shot recognitioncited by 78
  16. 2022Learning to Compose Soft Prompts for Compositional Zero-Shot Learningcited by 66
  17. 2023Visibility Aware Human-Object Interaction Tracking from Single RGB Cameracited by 58
  18. 2022Siamese Contrastive Embedding Network for Compositional Zero-Shot Learningcited by 55
  19. 2021Independent Prototype Propagation for Zero-Shot Compositionalitycited by 42
  20. 2022KG-SP: Knowledge Guided Simple Primitives for Open World Compositional Zero-Shot Learningcited by 41
  21. 2016A Unified View of Multi-Label Performance Measurescited by 36
  22. 2022Decomposed Soft Prompt Guided Fusion Enhancing for Compositional Zero-Shot Learningcited by 36
  23. 2022Open-vocabulary Attribute Detectioncited by 28
  24. 2023Learning Conditional Attributes for Compositional Zero-Shot Learningcited by 28
  25. 2023Troika: Multi-Path Cross-Modal Traction for Compositional Zero-Shot Learningcited by 26
  26. 2022Learning Invariant Visual Representations for Compositional Zero-Shot Learningcited by 24
  27. 2023Prompting Language-Informed Distribution for Compositional Zero-Shot Learningcited by 24
  28. 2022Learning to Detect and Segment for Open Vocabulary Object Detectioncited by 22
  29. 2022Hybrid Routing Transformer for Zero-Shot Learningcited by 20
  30. 2021Relation-aware Compositional Zero-shot Learning for Attribute-Object Pair Recognitioncited by 19
  31. 2023GIPCOL: Graph-Injected Soft Prompting for Compositional Zero-Shot Learningcited by 16
  32. 2022On Leveraging Variational Graph Embeddings for Open World Compositional Zero-Shot Learningcited by 13
  33. 2023Compositional Zero-shot Learning via Progressive Language-based Observationscited by 12
  34. 2022Mutual Balancing in State-Object Components for Compositional Zero-Shot Learningcited by 3

Built on by

Cited by year

Citing papers per year: 2024: 1.

1 paper.

  1. 2024Leveraging MLLM Embeddings and Attribute Smoothing for Compositional Zero-Shot Learningcited by 1