mlsanityData to 14 Oct 2026

Attention Based Simple Primitives for Open World Compositional Zero-Shot Learning

arXiv 2407.13715 ↗First posted 18 Jul 2024cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Compositional Zero-Shot Learning (CZSL) aims to predict unknown compositions made up of attribute and object pairs. Predicting compositions unseen during training is a challenging task. We are exploring Open World Compositional Zero-Shot Learning (OW-CZSL) in this study, where our test space encompasses all potential combinations of attributes and objects. Our approach involves utilizing the self-attention mechanism between attributes and objects to achieve better generalization from seen to unseen compositions. Utilizing a self-attention mechanism facilitates the model's ability to identify relationships between attribute and objects. The similarity between the self-attended textual and visual features is subsequently calculated to generate predictions during the inference phase. The potential test space may encompass implausible object-attribute combinations arising from unrestricted attribute-object pairings. To mitigate this issue, we leverage external knowledge from ConceptNet to restrict the test space to realistic compositions. Our proposed model, Attention-based Simple Primitives (ASP), demonstrates competitive performance, achieving results comparable to the state-of-the-art.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 33 of its 46 references that are in the map. First posted on arXiv 18 Jul 2024.

Builds on

33 of 46 references.

References · 33

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2020End-to-End Object Detection with Transformerscited by 7,414
  5. 2016Layer Normalizationcited by 5,669
  6. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,375
  7. 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,474
  8. 2016Enriching Word Vectors with Subword Informationcited by 1,583
  9. 2016ConceptNet 5.5: An Open Multilingual Graph of General Knowledgecited by 1,067
  10. 2018Image Transformercited by 772
  11. 2017Feature Generating Networks for Zero-Shot Learningcited by 257
  12. 2020Attribute Prototype Network for Zero-Shot Learningcited by 160
21 more
  1. 2016Learning a Deep Embedding Model for Zero-Shot Learningcited by 153
  2. 2019Task-Driven Modular Networks for Zero-Shot Compositional Learningcited by 121
  3. 2021Learning Graph Embeddings for Compositional Zero-shot Learningcited by 112
  4. 2021Open World Compositional Zero-Shot Learningcited by 101
  5. 2017A Generative Adversarial Approach for Zero-Shot Learning from Noisy Textscited by 96
  6. 2021Learning to Predict Visual Attributes in the Wildcited by 96
  7. 2020Symmetry and Group in Attribute-Object Compositionscited by 89
  8. 2020A causal view of compositional zero-shot recognitioncited by 78
  9. 2020Compositional Learning of Image-Text Query for Image Retrievalcited by 57
  10. 2021Learning Graph Embeddings for Open World Compositional Zero-Shot Learningcited by 49
  11. 2016Semantic Jitter: Dense Supervision for Visual Comparisons via Synthetic Imagescited by 45
  12. 2021Independent Prototype Propagation for Zero-Shot Compositionalitycited by 42
  13. 2022KG-SP: Knowledge Guided Simple Primitives for Open World Compositional Zero-Shot Learningcited by 41
  14. 2020Learning the Redundancy-free Features for Generalized Zero-Shot Object Recognitioncited by 34
  15. 2022Probabilistic Compositional Embeddings for Multimodal Image Retrievalcited by 29
  16. 2019Compositional Generalization in Image Captioningcited by 23
  17. 2022Learning Attention Propagation for Compositional Zero-Shot Learningcited by 20
  18. 2021Zero-Shot Compositional Concept Learningcited by 16
  19. 2019Task-Aware Feature Generation for Zero-Shot Compositional Learningcited by 11
  20. 2018From Classical to Generalized Zero-Shot Learning: a Simple Adaptation Processcited by 5
  21. 2020Learning to Infer Unseen Single-/Multi-Attribute-Object Compositions with Graph Networkscited by 5

Built on by

Not cited yet.