mlsanityData to 7 Oct 2026

Attribute Localization and Revision Network for Zero-Shot Learning

arXiv 2310.07548 ↗First posted 11 Oct 2023cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Zero-shot learning enables the model to recognize unseen categories with the aid of auxiliary semantic information such as attributes. Current works proposed to detect attributes from local image regions and align extracted features with class-level semantics. In this paper, we find that the choice between local and global features is not a zero-sum game, global features can also contribute to the understanding of attributes. In addition, aligning attribute features with class-level semantics ignores potential intra-class attribute variation. To mitigate these disadvantages, we present Attribute Localization and Revision Network in this paper. First, we design Attribute Localization Module (ALM) to capture both local and global features from image regions, a novel module called Scale Control Unit is incorporated to fuse global and local representations. Second, we propose Attribute Revision Module (ARM), which generates image-level semantics by revising the ground-truth value of each attribute, compensating for performance degradation caused by ignoring intra-class variation. Finally, the output of ALM will be aligned with revised semantics produced by ARM to achieve the training process. Comprehensive experimental results on three widely used benchmarks demonstrate the effectiveness of our model in the zero-shot prediction task.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 28 of its 45 references that are in the map. First posted on arXiv 11 Oct 2023.

Builds on

28 of 45 references.

References · 28

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2013Auto-Encoding Variational Bayescited by 3,980
  3. 2017Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Uglycited by 536
  4. 2017Feature Generating Networks for Zero-Shot Learningcited by 257
  5. 2018Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoderscited by 206
  6. 2014Evaluation of Output Embeddings for Fine-Grained Image Classificationcited by 166
  7. 2019f-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learningcited by 164
  8. 2020Attribute Prototype Network for Zero-Shot Learningcited by 160
  9. 2016An Empirical Study and Analysis of Generalized Zero-Shot Learning for Object Recognition in the Wildcited by 146
  10. 2017Generalized Zero-Shot Learning via Synthesized Examplescited by 114
  11. 2021Contrastive Embedding for Generalized Zero-Shot Learningcited by 94
  12. 2019Leveraging the Invariant Side of Generative Zero-Shot Learningcited by 83
16 more
  1. 2021Goal-Oriented Gaze Estimation for Zero-Shot Learningcited by 68
  2. 2021FREE: Feature Refinement for Generalized Zero-Shot Learningcited by 67
  3. 2017Zero-Shot Visual Recognition using Semantics-Preserving Adversarial Embedding Networkscited by 66
  4. 2019Episode-based Prototype Generating Network for Zero-Shot Learningcited by 66
  5. 2017A Generative Model For Zero Shot Learning Using Conditional Variational Autoencoderscited by 64
  6. 2019Transferable Contrastive Network for Generalized Zero-Shot Learningcited by 64
  7. 2020Leveraging Seen and Unseen Semantic Relationships for Generative Zero-Shot Learningcited by 64
  8. 2019Semantic-Guided Multi-Attention Localization for Zero-Shot Learningcited by 58
  9. 2021TransZero: Attribute-guided Transformer for Zero-Shot Learningcited by 53
  10. 2022MSDN: Mutually Semantic Distillation Network for Zero-Shot Learningcited by 48
  11. 2019Rethinking Zero-Shot Learning: A Conditional Visual Classification Perspectivecited by 42
  12. 2020Learning the Redundancy-free Features for Generalized Zero-Shot Object Recognitioncited by 34
  13. 2022VGSE: Visually-Grounded Semantic Embeddings for Zero-Shot Learningcited by 27
  14. 2022Non-generative Generalized Zero-shot Learning via Task-correlated Disentanglement and Controllable Samples Synthesiscited by 11
  15. 2021Region Semantically Aligned Network for Zero-Shot Learningcited by 6
  16. 2021On Implicit Attribute Localization for Generalized Zero-Shot Learningcited by 3

Built on by

Not cited yet.