Related papers: Domain-Specific Embedding Network for Zero-Shot Re…

In generalized zero shot learning (GZSL), the set of classes are split into seen and unseen classes, where training relies on the semantic features of the seen and unseen classes and the visual representations of only the seen classes,…

Deep Learning has greatly advanced the performance of semantic segmentation, however, its success relies on the availability of large amounts of annotated data for training. Hence, many efforts have been devoted to domain adaptive semantic…

Zero-shot Learning (ZSL) enables classifiers to recognize classes unseen during training, commonly via generative two stage methods: (1) learn visual semantic correlations from seen classes; (2) synthesize unseen class features from…

Zero-Shot Learning (ZSL) targets at recognizing unseen categories by leveraging auxiliary information, such as attribute embedding. Despite the encouraging results achieved, prior ZSL approaches focus on improving the discriminant power of…

This paper provides a novel parsimonious yet efficient design for zero-shot learning (ZSL), dubbed ParsNets, where we are interested in learning a composition of on-device friendly linear networks, each with orthogonality and low-rankness…

Generalized zero-shot learning (GZSL) has achieved significant progress, with many efforts dedicated to overcoming the problems of visual-semantic domain gap and seen-unseen bias. However, most existing methods directly use feature…

Fine-grained object recognition that aims to identify the type of an object among a large number of subcategories is an emerging application with the increasing resolution that exposes new details in image data. Traditional fully supervised…

Most existing Zero-Shot Learning (ZSL) methods have the strong bias problem, in which instances of unseen (target) classes tend to be categorized as one of the seen (source) classes. So they yield poor performance after being deployed in…

Deep Neural Network (DNN) based super-resolution algorithms have greatly improved the quality of the generated images. However, these algorithms often yield significant artifacts when dealing with real-world super-resolution problems due to…

General purpose semantic segmentation relies on a backbone CNN network to extract discriminative features that help classify each image pixel into a 'seen' object class (ie., the object classes available during training) or a background…

Multi-domain learning aims to benefit from simultaneously learning across several different but related domains. In this chapter, we propose a single framework that unifies multi-domain learning (MDL) and the related but better studied area…

We propose spatial semantic embedding network (SSEN), a simple, yet efficient algorithm for 3D instance segmentation using deep metric learning. The raw 3D reconstruction of an indoor environment suffers from occlusions, noise, and is…

One of the recent developments in deep learning is generalized zero-shot learning (GZSL), which aims to recognize objects from both seen and unseen classes, when only the labeled examples from seen classes are provided. Over the past couple…

Most visual recognition methods implicitly assume the data distribution remains unchanged from training to testing. However, in practice domain shift often exists, where real-world factors such as lighting and sensor type change between…

A classic approach toward zero-shot learning (ZSL) is to map the input domain to a set of semantically meaningful attributes that could be used later on to classify unseen classes of data (e.g. visual data). In this paper, we propose to…

Zero-shot learning transfers knowledge from seen classes to novel unseen classes to reduce human labor of labelling data for building new classifiers. Much effort on zero-shot learning however has focused on the standard multi-class…

Domain adaptation for sentiment analysis is challenging due to the fact that supervised classifiers are very sensitive to changes in domain. The two most prominent approaches to this problem are structural correspondence learning and…

A significant shortcoming of current state-of-the-art (SOTA) named-entity recognition (NER) systems is their lack of generalization to unseen domains, which poses a major problem since obtaining labeled data for NER in a new domain is…

This paper studies the problem of generalized zero-shot learning which requires the model to train on image-label pairs from some seen classes and test on the task of classifying new images from both seen and unseen classes. Most previous…

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…