mlsanityData to 7 Oct 2026

Implicit and Explicit Attention for Zero-Shot Learning

arXiv 2110.00860 ↗First posted 2 Oct 2021cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

Most of the existing Zero-Shot Learning (ZSL) methods focus on learning a compatibility function between the image representation and class attributes. Few others concentrate on learning image representation combining local and global features. However, the existing approaches still fail to address the bias issue towards the seen classes. In this paper, we propose implicit and explicit attention mechanisms to address the existing bias problem in ZSL models. We formulate the implicit attention mechanism with a self-supervised image angle rotation task, which focuses on specific image features aiding to solve the task. The explicit attention mechanism is composed with the consideration of a multi-headed self-attention mechanism via Vision Transformer model, which learns to map image features to semantic space during the training stage. We conduct comprehensive experiments on three popular benchmarks: AWA2, CUB and SUN. The performance of our proposed attention mechanisms has proved its effectiveness, and has achieved the state-of-the-art harmonic mean on all the three datasets.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 43 of its 58 references that are in the map. First posted on arXiv 2 Oct 2021.

Builds on

43 of 58 references.

References · 43

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  4. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  5. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  6. 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,462
  7. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,586
  8. 2016Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzlescited by 1,379
  9. 2016Colorful Image Colorizationcited by 1,113
  10. 2015Unsupervised Visual Representation Learning by Context Predictioncited by 1,062
  11. 2021Transformers in Vision: A Surveycited by 1,009
  12. 2021CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classificationcited by 806
31 more
  1. 2021Going deeper with Image Transformerscited by 759
  2. 2021Transformer in Transformercited by 632
  3. 2017Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Uglycited by 536
  4. 2019Domain Generalization by Solving Jigsaw Puzzlescited by 449
  5. 2014Discriminative Unsupervised Feature Learning with Exemplar Convolutional Neural Networkscited by 299
  6. 2017Feature Generating Networks for Zero-Shot Learningcited by 257
  7. 2017Zero-Shot Learning -- The Good, the Bad and the Uglycited by 254
  8. 2016Learning Representations for Automatic Colorizationcited by 251
  9. 2018Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoderscited by 206
  10. 2020Learning Robust Representations via Multi-View Information Bottleneckcited by 189
  11. 2014Evaluation of Output Embeddings for Fine-Grained Image Classificationcited by 166
  12. 2015Label-Embedding for Image Classificationcited by 164
  13. 2019f-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learningcited by 164
  14. 2021TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Upcited by 162
  15. 2020Attribute Prototype Network for Zero-Shot Learningcited by 160
  16. 2016Learning a Deep Embedding Model for Zero-Shot Learningcited by 153
  17. 2016An Empirical Study and Analysis of Generalized Zero-Shot Learning for Object Recognition in the Wildcited by 146
  18. 2019Boosting Few-Shot Visual Learning with Self-Supervisioncited by 140
  19. 2013Zero-Shot Learning by Convex Combination of Semantic Embeddingscited by 135
  20. 2017Semantic Autoencoder for Zero-Shot Learningcited by 133
  21. 2016Latent Embeddings for Zero-shot Classificationcited by 129
  22. 2015Learning to See by Movingcited by 101
  23. 2015Zero-Shot Learning via Semantic Similarity Embeddingcited by 74
  24. 2021Goal-Oriented Gaze Estimation for Zero-Shot Learningcited by 68
  25. 2019Episode-based Prototype Generating Network for Zero-Shot Learningcited by 66
  26. 2019Semantic-Guided Multi-Attention Localization for Zero-Shot Learningcited by 58
  27. 2015Ridge Regression, Hubness, and Zero-Shot Learningcited by 44
  28. 2021Multi-Head Self-Attention via Vision Transformer for Zero-Shot Learningcited by 12
  29. 2020Semantically Tied Paired Cycle Consistency for Any-Shot Sketch-based Image Retrievalcited by 10
  30. 2020Transformer-Encoder Detector Module: Using Context to Improve Robustness to Adversarial Attacks on Object Detectioncited by 4
  31. 2021On Implicit Attribute Localization for Generalized Zero-Shot Learningcited by 3

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 3; 2025: 1.

5 papers.

  1. 2023Progressive Semantic-Visual Mutual Adaption for Generalized Zero-Shot Learningcited by 24
  2. 2024Progressive Semantic-Guided Vision Transformer for Zero-Shot Learningcited by 17
  3. 2024Visual-Augmented Dynamic Semantic Prototype for Generative Zero-Shot Learningcited by 16
  4. 2025Visual and Semantic Prompt Collaboration for Generalized Zero-Shot Learningcited by 4
  5. 2024PSVMA+: Exploring Multi-granularity Semantic-visual Adaption for Generalized Zero-shot Learningcited by 3