Dual Feature Augmentation Network for Generalized Zero-shot Learning
- URL: http://arxiv.org/abs/2309.13833v1
- Date: Mon, 25 Sep 2023 02:37:52 GMT
- Title: Dual Feature Augmentation Network for Generalized Zero-shot Learning
- Authors: Lei Xiang, Yuan Zhou, Haoran Duan, Yang Long
- Abstract summary: Zero-shot learning (ZSL) aims to infer novel classes without training samples by transferring knowledge from seen classes.
Existing embedding-based approaches for ZSL typically employ attention mechanisms to locate attributes on an image.
We propose a novel Dual Feature Augmentation Network (DFAN), which comprises two feature augmentation modules.
- Score: 14.410978100610489
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Zero-shot learning (ZSL) aims to infer novel classes without training samples
by transferring knowledge from seen classes. Existing embedding-based
approaches for ZSL typically employ attention mechanisms to locate attributes
on an image. However, these methods often ignore the complex entanglement among
different attributes' visual features in the embedding space. Additionally,
these methods employ a direct attribute prediction scheme for classification,
which does not account for the diversity of attributes in images of the same
category. To address these issues, we propose a novel Dual Feature Augmentation
Network (DFAN), which comprises two feature augmentation modules, one for
visual features and the other for semantic features. The visual feature
augmentation module explicitly learns attribute features and employs cosine
distance to separate them, thus enhancing attribute representation. In the
semantic feature augmentation module, we propose a bias learner to capture the
offset that bridges the gap between actual and predicted attribute values from
a dataset's perspective. Furthermore, we introduce two predictors to reconcile
the conflicts between local and global features. Experimental results on three
benchmarks demonstrate the marked advancement of our method compared to
state-of-the-art approaches. Our code is available at
https://github.com/Sion1/DFAN.
Related papers
- Dual Relation Mining Network for Zero-Shot Learning [48.89161627050706]
We propose a Dual Relation Mining Network (DRMN) to enable effective visual-semantic interactions and learn semantic relationship among attributes for knowledge transfer.
Specifically, we introduce a Dual Attention Block (DAB) for visual-semantic relationship mining, which enriches visual information by multi-level feature fusion.
For semantic relationship modeling, we utilize a Semantic Interaction Transformer (SIT) to enhance the generalization of attribute representations among images.
arXiv Detail & Related papers (2024-05-06T16:31:19Z) - High-Discriminative Attribute Feature Learning for Generalized Zero-Shot Learning [54.86882315023791]
We propose an innovative approach called High-Discriminative Attribute Feature Learning for Generalized Zero-Shot Learning (HDAFL)
HDAFL utilizes multiple convolutional kernels to automatically learn discriminative regions highly correlated with attributes in images.
We also introduce a Transformer-based attribute discrimination encoder to enhance the discriminative capability among attributes.
arXiv Detail & Related papers (2024-04-07T13:17:47Z) - SEER-ZSL: Semantic Encoder-Enhanced Representations for Generalized
Zero-Shot Learning [0.7420433640907689]
Generalized Zero-Shot Learning (GZSL) recognizes unseen classes by transferring knowledge from the seen classes.
This paper introduces a dual strategy to address the generalization gap.
arXiv Detail & Related papers (2023-12-20T15:18:51Z) - Attribute-Aware Representation Rectification for Generalized Zero-Shot
Learning [19.65026043141699]
Generalized Zero-shot Learning (GZSL) has yielded remarkable performance by designing a series of unbiased visual-semantics mappings.
We propose a simple yet effective Attribute-Aware Representation Rectification framework for GZSL, dubbed $mathbf(AR)2$.
arXiv Detail & Related papers (2023-11-23T11:30:32Z) - Exploiting Semantic Attributes for Transductive Zero-Shot Learning [97.61371730534258]
Zero-shot learning aims to recognize unseen classes by generalizing the relation between visual features and semantic attributes learned from the seen classes.
We present a novel transductive ZSL method that produces semantic attributes of the unseen data and imposes them on the generative process.
Experiments on five standard benchmarks show that our method yields state-of-the-art results for zero-shot learning.
arXiv Detail & Related papers (2023-03-17T09:09:48Z) - Boosting Zero-shot Learning via Contrastive Optimization of Attribute
Representations [28.46906100680767]
We propose a new framework to boost Zero-shot learning (ZSL) by explicitly learning attribute prototypes beyond images.
A prototype generation module is designed to generate attribute prototypes from attribute semantics.
A hard example-based contrastive optimization scheme is introduced to reinforce attribute-level features in the embedding space.
arXiv Detail & Related papers (2022-07-08T11:05:35Z) - Attribute Prototype Network for Any-Shot Learning [113.50220968583353]
We argue that an image representation with integrated attribute localization ability would be beneficial for any-shot, i.e. zero-shot and few-shot, image classification tasks.
We propose a novel representation learning framework that jointly learns global and local features using only class-level attributes.
arXiv Detail & Related papers (2022-04-04T02:25:40Z) - CAD: Co-Adapting Discriminative Features for Improved Few-Shot
Classification [11.894289991529496]
Few-shot classification is a challenging problem that aims to learn a model that can adapt to unseen classes given a few labeled samples.
Recent approaches pre-train a feature extractor, and then fine-tune for episodic meta-learning.
We propose a strategy to cross-attend and re-weight discriminative features for few-shot classification.
arXiv Detail & Related papers (2022-03-25T06:14:51Z) - TransZero++: Cross Attribute-Guided Transformer for Zero-Shot Learning [119.43299939907685]
Zero-shot learning (ZSL) tackles the novel class recognition problem by transferring semantic knowledge from seen classes to unseen ones.
Existing attention-based models have struggled to learn inferior region features in a single image by solely using unidirectional attention.
We propose a cross attribute-guided Transformer network, termed TransZero++, to refine visual features and learn accurate attribute localization for semantic-augmented visual embedding representations.
arXiv Detail & Related papers (2021-12-16T05:49:51Z) - Attribute Prototype Network for Zero-Shot Learning [113.50220968583353]
We propose a novel zero-shot representation learning framework that jointly learns discriminative global and local features.
Our model points to the visual evidence of the attributes in an image, confirming the improved attribute localization ability of our image representation.
arXiv Detail & Related papers (2020-08-19T06:46:35Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.