• Corpus ID: 231719167

Generative Multi-Label Zero-Shot Learning

@article{Gupta2021GenerativeMZ,
  title={Generative Multi-Label Zero-Shot Learning},
  author={Akshita Gupta and Sanath Narayan and Salman Hameed Khan and Fahad Shahbaz Khan and Ling Shao and Joost van de Weijer},
  journal={ArXiv},
  year={2021},
  volume={abs/2101.11606}
}
Multi-label zero-shot learning strives to classify images into multiple unseen categories for which no data is available during training. The test samples can additionally contain seen categories in the generalized variant. Existing approaches rely on learning either shared or labelspecific attention from the seen classes. Nevertheless, computing reliable attention maps for unseen classes during inference in a multi-label setting is still a challenge. In contrast, state-of-the-art single-label… 

Figures and Tables from this paper

Discriminative Region-based Multi-Label Zero-Shot Learning
TLDR
This work proposes an alternate approach towards region-based discriminabilitypreserving multi-label zero-shot classification and utilizes a bi-level attention module (BiAM) to enrich the features by incorporating both region and scene context information.
Semantic Diversity Learning for Zero-Shot Multi-label Classification
TLDR
This study introduces an end-to-end model training for multi-label zero-shot learning that supports semantic diversity of the images and labels and proposes to use an embedding matrix having principal embedding vectors trained using a tailored loss function.

References

SHOWING 1-10 OF 50 REFERENCES
Feature Generating Networks for Zero-Shot Learning
TLDR
A novel generative adversarial network (GAN) that synthesizes CNN features conditioned on class-level semantic information, offering a shortcut directly from a semantic descriptor of a class to a class-conditional feature distribution.
Generative Dual Adversarial Network for Generalized Zero-Shot Learning
TLDR
A novel model is proposed that provides a unified framework for three different approaches: visual->semantic mapping, semantic->visual mapping, and metric learning that preserves higher accuracy and performs better than existing state-of-the-art models in in classifying images from unseen classes.
A Shared Multi-Attention Framework for Multi-Label Zero-Shot Learning
TLDR
This work develops a shared multi-attention model for multi-label zero-shot learning that improves the state of the art by 2.9% and 1.4% F1 score on the NUS-WIDE and the large scale Open Images datasets, respectively.
Multi-modal Cycle-consistent Generalized Zero-Shot Learning
TLDR
This paper proposes the use of a constraint based on a new regularization for the GAN training that forces the generated visual features to reconstruct their original semantic features in a multi-modal cycle-consistent manner.
F-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learning
TLDR
A conditional generative model that combines the strength of VAE and GANs and in addition, via an unconditional discriminator, learns the marginal feature distribution of unlabeled images is developed.
Leveraging the Invariant Side of Generative Zero-Shot Learning
TLDR
A novel method is proposed which can directly generate the unseen features from random noises which are conditioned by the semantic descriptions, and is named leveraging invariant side GAN (LisGAN), which can outperform state-of-the-art methods with significant improvements.
Learning a Deep ConvNet for Multi-Label Classification With Partial Labels
TLDR
This work proposes to train a model with partial labels i.e. only some labels are known per image, and introduces a new classification loss that exploits the proportion of known labels per example.
Multi-label Zero-Shot Learning with Structured Knowledge Graphs
TLDR
A novel deep learning architecture for multi-label zero-shot learning (ML-ZSL), which is able to predict multiple unseen class labels for each input instance, and a framework that incorporates knowledge graphs for describing the relationships between multiple labels is proposed.
Label-Embedding for Image Classification
TLDR
This work proposes to view attribute-based image classification as a label-embedding problem: each class is embedded in the space of attribute vectors, and introduces a function that measures the compatibility between an image and a label embedding.
Zero-Shot Classification with Discriminative Semantic Representation Learning
  • Meng Ye, Yuhong Guo
  • Computer Science
    2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2017
TLDR
This paper proposes a novel zero-shot learning method based on discriminative sparse non-negative matrix factorization, and develops a label propagation based testing procedure to classify the unlabeled instances from the unseen classes in the target domain.
...
1
2
3
4
5
...