![Loading...](https://link.springer.com/static/c4a417b97a76cc2980e3c25e2271af3129e08bbe/images/pdf-preview/spacer.gif)
-
Article
Image-to-image translation using an offset-based multi-scale codes GAN encoder
Despite the remarkable achievements of generative adversarial networks (GANs) in high-quality image synthesis, applying pre-trained GAN models to image-to-image translation is still challenging. Previous appro...
-
Article
Adversarial-Based Ensemble Feature Knowledge Distillation
Existing knowledge distillation methods usually consider class probabilities or directly align features, which ignore the rich information contained in high-level feature maps. In this paper, we propose a nove...
-
Article
Improving knowledge distillation via pseudo-multi-teacher network
Existing knowledge distillation methods usually directly push the student model to imitate the features or probabilities of the teacher model. However, the knowledge capacity of teachers limits students to lea...