mlsanityData to 7 Oct 2026

Multi-Head Self-Attention via Vision Transformer for Zero-Shot Learning

arXiv 2108.00045 ↗First posted 30 Jul 2021cs.CV cs.LGcited by 12

Not on the map. Why?

Abstract (arXiv)

Zero-Shot Learning (ZSL) aims to recognise unseen object classes, which are not observed during the training phase. The existing body of works on ZSL mostly relies on pretrained visual features and lacks the explicit attribute localisation mechanism on images. In this work, we propose an attention-based model in the problem settings of ZSL to learn attributes useful for unseen class recognition. Our method uses an attention mechanism adapted from Vision Transformer to capture and learn discriminative attributes by splitting images into small patches. We conduct experiments on three popular ZSL benchmarks (i.e., AWA2, CUB and SUN) and set new state-of-the-art harmonic mean results {on all the three datasets}, which illustrate the effectiveness of our proposed method.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 26 of its 36 references that are in the map. First posted on arXiv 30 Jul 2021.

Builds on

26 of 36 references.

References · 26

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  5. 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,462
  6. 2021Transformers in Vision: A Surveycited by 1,009
  7. 2021CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classificationcited by 806
  8. 2021Going deeper with Image Transformerscited by 759
  9. 2021Transformer in Transformercited by 632
  10. 2017Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Uglycited by 536
  11. 2018Dynamic Few-Shot Visual Learning without Forgettingcited by 385
  12. 2017Feature Generating Networks for Zero-Shot Learningcited by 257
14 more
  1. 2017Zero-Shot Learning -- The Good, the Bad and the Uglycited by 254
  2. 2018Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoderscited by 206
  3. 2020Learning Robust Representations via Multi-View Information Bottleneckcited by 189
  4. 2014Evaluation of Output Embeddings for Fine-Grained Image Classificationcited by 166
  5. 2015Label-Embedding for Image Classificationcited by 164
  6. 2019f-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learningcited by 164
  7. 2020Attribute Prototype Network for Zero-Shot Learningcited by 160
  8. 2016An Empirical Study and Analysis of Generalized Zero-Shot Learning for Object Recognition in the Wildcited by 146
  9. 2013Zero-Shot Learning by Convex Combination of Semantic Embeddingscited by 135
  10. 2017Semantic Autoencoder for Zero-Shot Learningcited by 133
  11. 2016Latent Embeddings for Zero-shot Classificationcited by 129
  12. 2015Zero-Shot Learning via Semantic Similarity Embeddingcited by 74
  13. 2019Semantic-Guided Multi-Attention Localization for Zero-Shot Learningcited by 58
  14. 2020Transformer-Encoder Detector Module: Using Context to Improve Robustness to Adversarial Attacks on Object Detectioncited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 2; 2023: 1; 2024: 4; 2025: 3; 2026: 1.

12 papers.

  1. 2022DUET: Cross-modal Semantic Grounding for Contrastive Zero-shot Learningcited by 33
  2. 2023Progressive Semantic-Visual Mutual Adaption for Generalized Zero-Shot Learningcited by 24
  3. 2024Progressive Semantic-Guided Vision Transformer for Zero-Shot Learningcited by 17
  4. 2024Visual-Augmented Dynamic Semantic Prototype for Generative Zero-Shot Learningcited by 16
  5. 2024A Review of Transformer-Based Models for Computer Vision Tasks: Capturing Global Context and Spatial Relationshipscited by 11
  6. 2022Boosting Zero-shot Learning via Contrastive Optimization of Attribute Representationscited by 8
  7. 2021Implicit and Explicit Attention for Zero-Shot Learningcited by 5
  8. 2025Visual and Semantic Prompt Collaboration for Generalized Zero-Shot Learningcited by 4
  9. 2024PSVMA+: Exploring Multi-granularity Semantic-visual Adaption for Generalized Zero-shot Learningcited by 3
  10. 2025Few-Shot Inspired Generative Zero-Shot Learningcited by 0
  11. 2025Multi-Granularity Mutual Refinement Network for Zero-Shot Learningcited by 0
  12. 2026CV-DCLR: Causal-Visual Dynamic Label Refinement for Robust Zero-Shot Learningcited by 0