Related papers: Disentangling Semantic-to-visual Confusion for Zer…
Recently, many zero-shot learning (ZSL) methods focused on learning discriminative object features in an embedding feature space, however, the distributions of the unseen-class features learned by these methods are prone to be partly…
Generative based strategy has shown great potential in the Generalized Zero-Shot Learning task. However, it suffers severe generalization problem due to lacking of feature diversity for unseen classes to train a good classifier. In this…
Although zero-shot learning (ZSL) has an inferential capability of recognizing new classes that have never been seen before, it always faces two fundamental challenges of the cross modality and crossdomain challenges. In order to alleviate…
Zero-shot learning (ZSL) aims at recognizing classes for which no visual sample is available at training time. To address this issue, one can rely on a semantic description of each class. A typical ZSL model learns a mapping between the…
Building robust and real-time classifiers with diverse datasets are one of the most significant challenges to deep learning researchers. It is because there is a considerable gap between a model built with training (seen) data and real…
Zero-shot learning, which studies the problem of object classification for categories for which we have no training examples, is gaining increasing attention from community. Most existing ZSL methods exploit deterministic transfer learning…
From the intuitive notion of disentanglement, the image variations corresponding to different factors should be distinct from each other, and the disentangled representation should reflect those variations with separate dimensions. To…
Learning 3D generative models from a dataset of monocular images enables self-supervised 3D reasoning and controllable synthesis. State-of-the-art 3D generative models are GANs which use neural 3D volumetric representations for synthesis.…
Zero-shot Learning (ZSL) aims to enable classifiers to identify unseen classes. This is typically achieved by generating visual features for unseen classes based on learned visual-semantic correlations from seen classes. However, most…
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…
As an effective way of metric learning, triplet loss has been widely used in many deep learning tasks, including face recognition and person-ReID, leading to many states of the arts. The main innovation of triplet loss is using feature map…
Generalised zero-shot learning (GZSL) is a classification problem where the learning stage relies on a set of seen visual classes and the inference stage aims to identify both the seen visual classes and a new set of unseen visual classes.…
We consider unsupervised cell nuclei segmentation in this paper. Exploiting the recently-proposed unpaired image-to-image translation between cell nuclei images and randomly synthetic masks, existing approaches, e.g., CycleGAN, have…
Learning disentangled representation of data without supervision is an important step towards improving the interpretability of generative models. Despite recent advances in disentangled representation learning, existing approaches often…
Scene text images contain not only style information (font, background) but also content information (character, texture). Different scene text tasks need different information, but previous representation learning methods use tightly…
Time-series representation learning is a fundamental task for time-series analysis. While significant progress has been made to achieve accurate representations for downstream applications, the learned representations often lack…
Zero-shot learning (ZSL) for image classification focuses on recognizing novel categories that have no labeled data available for training. The learning is generally carried out with the help of mid-level semantic descriptors associated…
Multi-view multi-label learning frequently suffers from simultaneous feature absence and incomplete annotations, due to challenges in data acquisition and cost-intensive supervision. To tackle the complex yet highly practical problem while…
Disentangled representation learning (DRL) aims to break down observed data into core intrinsic factors for a profound understanding of the data. In real-world scenarios, manually defining and labeling these factors are non-trivial, making…
Zero-shot learning (ZSL) aims to recognize objects of novel classes without any training samples of specific classes, which is achieved by exploiting the semantic information and auxiliary datasets. Recently most ZSL approaches focus on…