Related papers: Feature Generating Networks for Zero-Shot Learning
Generative Adversarial Networks (GAN) can achieve promising performance on learning complex data distributions on different types of data. In this paper, we first show a straightforward extension of existing GAN algorithm is not applicable…
Softmax GAN is a novel variant of Generative Adversarial Network (GAN). The key idea of Softmax GAN is to replace the classification loss in the original GAN with a softmax cross-entropy loss in the sample space of one single batch. In the…
Sketch-based 3D shape retrieval is a challenging task due to the large domain discrepancy between sketches and 3D shapes. Since existing methods are trained and evaluated on the same categories, they cannot effectively recognize the…
Deep generative models require large amounts of training data. This often poses a problem as the collection of datasets can be expensive and difficult, in particular datasets that are representative of the appropriate underlying…
The performance of generative zero-shot methods mainly depends on the quality of generated features and how well the model facilitates knowledge transfer between visual and semantic domains. The quality of generated features is a direct…
Existing methods using generative adversarial approaches for Zero-Shot Learning (ZSL) aim to generate realistic visual features from class semantics by a single generative network, which is highly under-constrained. As a result, the…
When training samples are scarce, the semantic embedding technique, ie, describing class labels with attributes, provides a condition to generate visual features for unseen objects by transferring the knowledge from seen objects. However,…
Generative adversarial networks (GANs) have shown great success in applications such as image generation and inpainting. However, they typically require large datasets, which are often not available, especially in the context of prediction…
We present variational generative adversarial networks, a general learning framework that combines a variational auto-encoder with a generative adversarial network, for synthesizing images in fine-grained categories, such as faces of a…
Generative Adversarial Networks (GANs) have been shown to produce realistically looking synthetic images with remarkable success, yet their performance seems less impressive when the training set is highly diverse. In order to provide a…
We propose a novel method for training a conditional generative adversarial network (CGAN) without the use of training data, called zero-shot learning of a CGAN (ZS-CGAN). Zero-shot learning of a conditional generator only needs a…
New categories can be discovered by transforming semantic features into synthesized visual features without corresponding training samples in zero-shot image classification. Although significant progress has been made in generating…
We propose a conditional generative adversarial network (GAN) model for zero-shot video generation. In this study, we have explored zero-shot conditional generation setting. In other words, we generate unseen videos from training samples…
Feature generating networks face to the most important question, which is the fitting difference (inconsistence) of the distribution between the generated feature and the real data. This inconsistence further influence the performance of…
Generative Adversarial Networks (GANs) are powerful generative models, but suffer from training instability. The recently proposed Wasserstein GAN (WGAN) makes progress toward stable training of GANs, but sometimes can still generate only…
Generative adversarial networks (GANs) can implicitly learn rich distributions over images, audio, and data which are hard to model with an explicit likelihood. We present a practical Bayesian formulation for unsupervised and…
Generative Adversarial Networks (GANs) have shown promise in augmenting datasets and boosting convolutional neural networks' (CNN) performance on image classification tasks. But they introduce more hyperparameters to tune as well as the…
Large-scale knowledge graphs (KGs) are shown to become more important in current information systems. To expand the coverage of KGs, previous studies on knowledge graph completion need to collect adequate training instances for newly-added…
Many approaches in generalized zero-shot learning rely on cross-modal mapping between the image feature space and the class embedding space. As labeled images are expensive, one direction is to augment the dataset by generating either…
Few-shot recognition in synthetic aperture radar (SAR) imagery remains a critical bottleneck for real-world applications due to extreme data scarcity. A promising strategy involves synthesizing a large dataset with a generative adversarial…