A review of generalized zero-shot learning methods
Generalized zero-shot learning (GZSL) aims to train a model for classifying data samples
under the condition that some output classes are unknown during supervised learning. To …
under the condition that some output classes are unknown during supervised learning. To …
Clip2scene: Towards label-efficient 3d scene understanding by clip
Abstract Contrastive Language-Image Pre-training (CLIP) achieves promising results in 2D
zero-shot and few-shot learning. Despite the impressive performance in 2D, applying CLIP …
zero-shot and few-shot learning. Despite the impressive performance in 2D, applying CLIP …
Datasetgan: Efficient labeled data factory with minimal human effort
We introduce DatasetGAN: an automatic procedure to generate massive datasets of high-
quality semantically segmented images requiring minimal human effort. Current deep …
quality semantically segmented images requiring minimal human effort. Current deep …
Towards zero-shot learning: A brief review and an attention-based embedding network
Zero-shot learning (ZSL), an emerging topic in recent years, targets at distinguishing unseen
class images by taking images from seen classes for training the classifier. Existing works …
class images by taking images from seen classes for training the classifier. Existing works …
Contrastive embedding for generalized zero-shot learning
Generalized zero-shot learning (GZSL) aims to recognize objects from both seen and
unseen classes, when only the labeled examples from seen classes are provided. Recent …
unseen classes, when only the labeled examples from seen classes are provided. Recent …
Free: Feature refinement for generalized zero-shot learning
Generalized zero-shot learning (GZSL) has achieved significant progress, with many efforts
dedicated to overcoming the problems of visual-semantic domain gaps and seen-unseen …
dedicated to overcoming the problems of visual-semantic domain gaps and seen-unseen …
Introducing language guidance in prompt-based continual learning
Continual Learning aims to learn a single model on a sequence of tasks without having
access to data from previous tasks. The biggest challenge in the domain still remains …
access to data from previous tasks. The biggest challenge in the domain still remains …
A survey of zero-shot learning: Settings, methods, and applications
Most machine-learning methods focus on classifying instances whose classes have already
been seen in training. In practice, many applications require classifying instances whose …
been seen in training. In practice, many applications require classifying instances whose …
f-vaegan-d2: A feature generating framework for any-shot learning
When labeled training data is scarce, a promising data augmentation approach is to
generate visual features of unknown classes using their attributes. To learn the class …
generate visual features of unknown classes using their attributes. To learn the class …
Feature generating networks for zero-shot learning
Suffering from the extreme training data imbalance between seen and unseen classes, most
of existing state-of-the-art approaches fail to achieve satisfactory results for the challenging …
of existing state-of-the-art approaches fail to achieve satisfactory results for the challenging …