Results 11 to 20 of about 38,613 (267)
Zero-shot Adversarial Quantization [PDF]
2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021 CVPR 2021 ...
Yuang Liu, Wei Zhang 0056, Jun Wang 0006
openaire +2 more sources
IEEE Transactions on Circuits and Systems for Video Technology, 2020 As we move towards large-scale object detection, it is unrealistic to expect annotated training data, in the form of bounding box annotations around objects, for all object classes at sufficient scale, and so methods capable of unseen object detection are required.
Pengkai Zhu +2 more
openaire +2 more sources
Zero-Shot Domain Generalization [PDF]
Proceedings of the British Machine Vision Conference 2020, 2020 Standard supervised learning setting assumes that training data and test data come from the same distribution (domain). Domain generalization (DG) methods try to learn a model that when trained on data from multiple domains, would generalize to a new unseen domain.
Udit Maniyar +4 more
openaire +2 more sources
2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023 Accepted in CVPR ...
Jinqi Luo +4 more
openaire +2 more sources
2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023 CVPR ...
Xu, Jingyi +4 more
openaire +3 more sources
IEEE Transactions on Image Processing, 2023 Accepted to IEEE Transactions on Image Processing (TIP ...
Zihan Ye +4 more
openaire +3 more sources
Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, 2022 Semantic-descriptor-based Generalized Zero-Shot Learning (GZSL) poses challenges in recognizing novel classes in the test phase. The development of generative models enables current GZSL techniques to probe further into the semantic-visual link, culminating in a two-stage form that includes a generator and a classifier.
Chen, D, Shen, Y, Zhang, H, Torr, PHS
openaire +2 more sources
Zero-Shot Instance Segmentation [PDF]
2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021 Deep learning has significantly improved the precision of instance segmentation with abundant labeled data. However, in many areas like medical and manufacturing, collecting sufficient data is extremely hard and labeling this data requires high professional skills.
Ye Zheng +4 more
openaire +2 more sources
Zero-Shot Robustification of Zero-Shot Models
, 2023 International Conference on Learning Representations (ICLR ...
Dyah Adila +3 more
openaire +3 more sources
CoRR, 2022 Considering the increasing concerns about data copyright and privacy issues, we present a novel Absolute Zero-Shot Learning (AZSL) paradigm, i.e., training a classifier with zero real data. The key innovation is to involve a teacher model as the data safeguard to guide the AZSL model training without data leaking. The AZSL model consists of a generator
Rui Gao +8 more
openaire +2 more sources