Convolutional Prototype Learning for Zero-Shot Recognition

@article{Liu2020ConvolutionalPL,
  title={Convolutional Prototype Learning for Zero-Shot Recognition},
  author={Zhizhe Liu and Xingxing Zhang and Zhenfeng Zhu and Shuai Zheng and Yao Zhao and Jian Cheng},
  journal={Image Vis. Comput.},
  year={2020},
  volume={98},
  pages={103924}
}
Zero-shot learning (ZSL) has received increasing attention in recent years especially in areas of fine-grained object recognition, retrieval, and image captioning. The key to ZSL is to transfer knowledge from the seen to the unseen classes via auxiliary class attribute vectors. However, the popularly learned projection functions in previous works cannot generalize well since they assume the distribution consistency between seen and unseen domains at sample-level.Besides, the provided non-visual… Expand
ATZSL: Defensive Zero-Shot Recognition in the Presence of Adversaries
TLDR
This paper proposes a generic formulation to provide a systematical solution (named ATZSL) for learning a robust ZSL model, capable of achieving better generalization on various adversarial objects recognition while only losing a negligible performance on clean images for unseen classes, by casting ZSL into a min-max optimization problem. Expand
Taking Modality-free Human Identification as Zero-shot Learning
TLDR
An initial attempt is taken to formulate a novel Modality-Free Human Identification task as a generic zero-shot learning model in a scalable way, capable of bridging the visual and semantic modalities by learning a discriminative prototype of each identity. Expand
Bias alleviating generative adversarial network for generalized zero-shot classification
TLDR
This work learns a bias alleviating generative adversarial network for generalized zero-shot classification by generating seen and unseen samples, simultaneously, and trains the generator to generate more realistic unseen samples by adding semantic similarity and cluster center regularizations to alleviate the bias problem. Expand
Detecting Anomalies in Semantic Segmentation with Prototypes
TLDR
The intuition is that anomalous pixels are those that are dissimilar to all class prototypes known by the model, which means that this approach achieves the new state of the art, with a significant margin over previous works, despite the reduced computational overhead. Expand

References

SHOWING 1-10 OF 69 REFERENCES
Hierarchical Prototype Learning for Zero-Shot Recognition
TLDR
A hierarchical prototype learning formulation is proposed to provide a systematical solution (named HPL) for zero-shot recognition that is able to obtain discriminability on both seen and unseen class domains by learning visual prototypes respectively under the transductive setting. Expand
Discriminative Learning of Latent Features for Zero-Shot Recognition
TLDR
This work proposes an end-to-end network that is capable of automatically discovering discriminative regions by a zoom network and learning discrim inative semantic representations in an augmented space introduced for both user-defined and latent attributes. Expand
Synthesized Classifiers for Zero-Shot Learning
TLDR
This work introduces a set of "phantom" object classes whose coordinates live in both the semantic space and the model space and demonstrates superior accuracy of this approach over the state of the art on four benchmark datasets for zero-shot learning. Expand
Zero-Shot Learning Through Cross-Modal Transfer
TLDR
This work introduces a model that can recognize objects in images even if no training data is available for the object class, and uses novelty detection methods to differentiate unseen classes from seen classes. Expand
Domain-Invariant Projection Learning for Zero-Shot Recognition
TLDR
A novel ZSL model termed domain-invariant projection learning (DIPL), which outperforms the state-of-the-art alternatives by significant margins and shared semantic structure among seen and unseen classes is explored via forming superclasses in the semantic space. Expand
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. Expand
Zero-Shot Learning With Transferred Samples
TLDR
A novel one-step recognition framework that is able to perform recognition in the original feature space by using directly trained classifiers is proposed that demonstrates the superiority of the proposed framework, compared with the state-of-the-art approaches, in various settings. Expand
Semantic Autoencoder for Zero-Shot Learning
TLDR
This work presents a novel solution to ZSL based on learning a Semantic AutoEncoder (SAE), which outperforms significantly the existing ZSL models with the additional benefit of lower computational cost and beats the state-of-the-art when the SAE is applied to supervised clustering problem. Expand
From Zero-Shot Learning to Conventional Supervised Classification: Unseen Visual Data Synthesis
TLDR
A new Zero-shot learning framework that can synthesise visual features for unseen classes without acquiring real images is proposed and extensive experimental results manifest that the proposed approach significantly improve the state-of-the-art results. Expand
Classifier and Exemplar Synthesis for Zero-Shot Learning
TLDR
This paper proposes two ZSL frameworks that learn to synthesize parameters for novel unseen classes through a flexible approach that synthesizes “classifiers” for the unseen classes. Expand
...
1
2
3
4
5
...