mlsanityData to 7 Oct 2026

Zero-Shot Compositional Concept Learning

arXiv 2107.05176 ↗First posted 12 Jul 2021cs.CV cs.CLcited by 16

Not on the map. Why?

Abstract (arXiv)

In this paper, we study the problem of recognizing compositional attribute-object concepts within the zero-shot learning (ZSL) framework. We propose an episode-based cross-attention (EpiCA) network which combines merits of cross-attention mechanism and episode-based training strategy to recognize novel compositional concepts. Firstly, EpiCA bases on cross-attention to correlate concept-visual information and utilizes the gated pooling layer to build contextualized representations for both images and concepts. The updated representations are used for a more in-depth multi-modal relevance calculation for concept recognition. Secondly, a two-phase episode training strategy, especially the transductive phase, is adopted to utilize unlabeled test examples to alleviate the low-resource learning problem. Experiments on two widely-used zero-shot compositional learning (ZSCL) benchmarks have demonstrated the effectiveness of the model compared with recent approaches on both conventional and generalized ZSCL settings.

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). Builds on 18 of its 29 references that are in the map. First posted on arXiv 12 Jul 2021.

Builds on

18 of 29 references.

References · 18

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  4. 2016Matching Networks for One Shot Learningcited by 2,246
  5. 2019ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Taskscited by 2,219
  6. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
  7. 2018Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labelscited by 994
  8. 2018Stacked Cross Attention for Image-Text Matchingcited by 414
  9. 2015Attention-Based Models for Speech Recognitioncited by 400
  10. 2019A Baseline for Few-Shot Image Classificationcited by 298
  11. 2019Task-Driven Modular Networks for Zero-Shot Compositional Learningcited by 121
  12. 2020IMRAM: Iterative Matching with Recurrent Attention Memory for Cross-Modal Image-Text Retrievalcited by 115
6 more
  1. 2020Symmetry and Group in Attribute-Object Compositionscited by 89
  2. 2019Learning to Self-Train for Semi-Supervised Few-Shot Classificationcited by 83
  3. 2016Semantic Jitter: Dense Supervision for Visual Comparisons via Synthetic Imagescited by 45
  4. 2019Rethinking Zero-Shot Learning: A Conditional Visual Classification Perspectivecited by 42
  5. 2019TAFE-Net: Task-Aware Feature Embeddings for Low Shot Learningcited by 32
  6. 2018Attributes as Operators: Factorizing Unseen Attribute-Object Compositionscited by 20

Built on by

Cited by year

Citing papers per year: 2022: 4; 2023: 5; 2024: 6; 2025: 1.

16 papers.

Sort:

By area:

  1. 2022Learning to Compose Soft Prompts for Compositional Zero-Shot Learningcited by 66
  2. 2022Disentangling Visual Embeddings for Attributes and Objectscited by 55
  3. 2023Learning Conditional Attributes for Compositional Zero-Shot Learningcited by 28
  4. 2022Meta Learning for Natural Language Processing: A Surveycited by 26
  5. 2024Context-based and Diversity-driven Specificity in Compositional Zero-Shot Learningcited by 20
  6. 2023Distilled Reverse Attention Network for Open-world Compositional Zero-Shot Learningcited by 11
  7. 2024TsCA: On the Semantic Consistency Alignment via Conditional Transport for Compositional Zero-Shot Learningcited by 6
  8. 2022LOCL: Learning Object-Attribute Composition using Localizationcited by 3
  9. 2023Compositional Learning of Visually-Grounded Concepts Using Reinforcementcited by 2
  10. 2024Sequential Compositional Generalization in Multimodal Modelscited by 1
  11. 2024Compositional Zero-Shot Learning with Contextualized Cues and Adaptive Contrastive Trainingcited by 1
  12. 2023Describe me an Aucklet: Generating Grounded Perceptual Category Descriptionscited by 0
4 more
  1. 2023Prompt Tuning for Zero-shot Compositional Learningcited by 0
  2. 2024Attention Based Simple Primitives for Open World Compositional Zero-Shot Learningcited by 0
  3. 2024Focus-Consistent Multi-Level Aggregation for Compositional Zero-Shot Learningcited by 0
  4. 2025Human-like compositional learning of visually-grounded concepts using synthetic environmentscited by 0