Results 241 to 250 of about 38,613 (267)
Some of the next articles are maybe not open access.
IEEE Transactions on Image Processing, 2020
In this paper, we study two less-touched challenging problems in single image dehazing neural networks, namely, how to remove haze from a given image in an unsupervised and zeroshot manner. To the ends, we propose a novel method based on the idea of layer disentanglement by viewing a hazy image as the entanglement of several "simpler" layers, i.e., a ...
Boyun Li +5 more
openaire +2 more sources
In this paper, we study two less-touched challenging problems in single image dehazing neural networks, namely, how to remove haze from a given image in an unsupervised and zeroshot manner. To the ends, we propose a novel method based on the idea of layer disentanglement by viewing a hazy image as the entanglement of several "simpler" layers, i.e., a ...
Boyun Li +5 more
openaire +2 more sources
A Unified Approach for Conventional Zero-Shot, Generalized Zero-Shot, and Few-Shot Learning [PDF]
IEEE Transactions on Image Processing, 2018 Prevalent techniques in zero-shot learning do not generalize well to other related problem scenarios. Here, we present a unified approach for conventional zero-shot, generalized zero-shot and few-shot learning problems. Our approach is based on a novel Class Adapting Principal Directions (CAPD) concept that allows multiple embeddings of image features ...
Shafin Rahman +2 more
exaly +5 more sources
Incremental Zero-Shot Learning
IEEE Transactions on Cybernetics, 2022The goal of zero-shot learning (ZSL) is to recognize objects from unseen classes correctly without corresponding training samples. The existing ZSL methods are trained on a set of predefined classes and do not have the ability to learn from a stream of training data.
Kun Wei +3 more
openaire +2 more sources
Hashing in the zero shot framework
2017 Twenty-third National Conference on Communications (NCC), 2017This paper provides a framework to hash images containing instances of unknown object classes. In many object recognition problems, we might have access to huge amount of data. It may so happen that even this huge data do not cover the objects belonging to classes that we see in our day to day life.
Shubham Pachori, Shanmuganathan Raman
openaire +1 more source
Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, 2019
In this work, we tackle the zero-shot metric learning problem and propose a novel method abbreviated as ZSML, with the purpose to learn a distance metric that measures the similarity of unseen categories (even unseen datasets). ZSML achieves strong transferability by capturing multi-nonlinear yet continuous relation among data.
Xinyi Xu +4 more
openaire +1 more source
In this work, we tackle the zero-shot metric learning problem and propose a novel method abbreviated as ZSML, with the purpose to learn a distance metric that measures the similarity of unseen categories (even unseen datasets). ZSML achieves strong transferability by capturing multi-nonlinear yet continuous relation among data.
Xinyi Xu +4 more
openaire +1 more source
Zero-Shot Learning with Superclasses
2018Zero-shot learning (ZSL) can be regarded as transfer learning from seen classes to unseen ones so that the later can be recognized without any training samples. Its main difficulty lies in that there often exists a large domain gap between the seen and unseen class domains.
Yuqi Huo +5 more
openaire +1 more source
A Review of Generalized Zero-Shot Learning Methods
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022Xizhao Wang, Ran Wang, Moloud Abdar
exaly
Improving Existing Segmentators Performance with Zero-Shot Segmentators
Entropy, 2023Loris Nanni +2 more
exaly
Dual Projective Zero-Shot Learning Using Text Descriptions
ACM Transactions on Multimedia Computing, Communications and Applications, 2023Yunbo Rao, Qifei Wang, Jiansu Pu
exaly
Zero-Shot Learning with Joint Generative Adversarial Networks
Electronics (Switzerland), 2023Yueting Shi +2 more
exaly