En-compactness: Self-distillation embedding & contrastive generation for generalized zero-shot learning
Generalized zero-shot learning (GZSL) requires a classifier trained on seen classes that can
recognize objects from both seen and unseen classes. Due to the absence of unseen …
recognize objects from both seen and unseen classes. Due to the absence of unseen …
En-Compactness: Self-Distillation Embedding & Contrastive Generation for Generalized Zero-Shot Learning
X Kong, Z Gao, X Li, M Hong, J Liu… - 2022 IEEE/CVF …, 2022 - ieeexplore.ieee.org
Generalized zero-shot learning (GZSL) requires a classifier trained on seen classes that can
recognize objects from both seen and unseen classes. Due to the absence of unseen …
recognize objects from both seen and unseen classes. Due to the absence of unseen …
En-Compactness: Self-Distillation Embedding & Contrastive Generation for Generalized Zero-Shot Learning
X Kong, Z Gao, X Li, M Hong, J Liu, C Wang… - 2022 IEEE/CVF …, 2022 - computer.org
Generalized zero-shot learning (GZSL) requires a classifier trained on seen classes that can
recognize objects from both seen and unseen classes. Due to the absence of unseen …
recognize objects from both seen and unseen classes. Due to the absence of unseen …
En-Compactness: Self-Distillation Embedding & Contrastive Generation for Generalized Zero-Shot Learning
X Kong, Z Gao, X Li, M Hong, J Liu, C Wang, Y Xie… - openreview.net
Generalized zero-shot learning (GZSL) requires a classifier trained on seen classes that can
recognize objects from both seen and unseen classes. Due to the absence of unseen …
recognize objects from both seen and unseen classes. Due to the absence of unseen …