Related papers: Disentangling Semantic-to-visual Confusion for Zer…
Image-to-image translation aims to learn the mapping between two visual domains. There are two main challenges for this task: 1) lack of aligned training pairs and 2) multiple possible outputs from a single input image. In this work, we…
Generalized zero-shot learning (GZSL) is a technique to train a deep learning model to identify unseen classes using the attribute. In this paper, we put forth a new GZSL technique that improves the GZSL classification performance greatly.…
Recent advances in unsupervised representation learning often rely on knowing the number of classes to improve feature extraction and clustering. However, this assumption raises an important question: is the number of classes always…
Zero-shot Learning (ZSL) is a transfer learning technique which aims at transferring knowledge from seen classes to unseen classes. This knowledge transfer is possible because of underlying semantic space which is common to seen and unseen…
Various controls over the generated data can be extracted from the latent space of a pre-trained GAN, as it implicitly encodes the semantics of the training data. The discovered controls allow to vary semantic attributes in the generated…
Generalized Zero-Shot Learning (GZSL) is the task of leveraging semantic information (e.g., attributes) to recognize the seen and unseen samples, where unseen classes are not observable during training. It is natural to derive generative…
Controlling the style of natural language by disentangling the latent space is an important step towards interpretable machine learning. After the latent space is disentangled, the style of a sentence can be transformed by tuning the style…
Generative zero-shot learning (ZSL) methods typically synthesize visual features for unseen classes using predefined semantic attributes, followed by training a fully supervised classification model. While effective, these methods require…
Deep-embedding methods aim to discover representations of a domain that make explicit the domain's class structure and thereby support few-shot learning. Disentangling methods aim to make explicit compositional or factorial structure. We…
Generative Adversarial Networks (GANs) rely heavily on large-scale training data for training high-quality image generation models. With limited training data, the GAN discriminator often suffers from severe overfitting which directly leads…
We propose a novel learning approach, in the form of a fully-convolutional neural network (CNN), which automatically and consistently removes specular highlights from a single image by generating its diffuse component. To train the…
Deep learning models exhibit limited generalizability across different domains. Specifically, transferring knowledge from available entangled domain features(source/target domain) and categorical features to new unseen categorical features…
Deep generative models come with the promise to learn an explainable representation for visual objects that allows image sampling, synthesis, and selective modification. The main challenge is to learn to properly model the independent…
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 present neural architectures that disentangle RGB-D images into objects' shapes and styles and a map of the background scene, and explore their applications for few-shot 3D object detection and few-shot concept classification. Our…
In this paper, we propose a novel framework named DRL-CPG to learn disentangled latent representation for controllable person image generation, which can produce realistic person images with desired poses and human attributes (e.g., pose,…
Zero-shot learning (ZSL) aims to recognize novel classes by transferring semantic knowledge from seen classes to unseen classes. Though many ZSL methods rely on a direct mapping between the visual and the semantic space, the calibration…
Zero-shot learning is a new paradigm to classify objects from classes that are not available at training time. Zero-shot learning (ZSL) methods have attracted considerable attention in recent years because of their ability to classify…
Visual-Semantic Embedding (VSE) is a prevalent approach in image-text retrieval by learning a joint embedding space between the image and language modalities where semantic similarities would be preserved. The triplet loss with…
This paper addresses two crucial problems of learning disentangled image representations, namely controlling the degree of disentanglement during image editing, and balancing the disentanglement strength and the reconstruction quality. To…