Uncertainty-based knowledge distillation for Bayesian deep neural network compression
M Hemmatian, A Shahzadi, S Mozaffari - International Journal of …, 2024 - Elsevier
Deep learning models have been widely employed across various fields. In real-world
scenarios, especially safety-critical applications, quantifying uncertainty is as crucial as …
scenarios, especially safety-critical applications, quantifying uncertainty is as crucial as …
Knowledge in attention assistant for improving generalization in deep teacher–student models
Research on knowledge distillation has become active in deep neural networks. Knowledge
distillation involves training a low-capacity model from a high-capacity model. However …
distillation involves training a low-capacity model from a high-capacity model. However …
FCL: Pedestrian Re-Identification Algorithm Based on Feature Fusion Contrastive Learning
Pedestrian re-identification leverages computer vision technology to achieve cross-camera
matching of pedestrians; it has recently led to significant progress and presents numerous …
matching of pedestrians; it has recently led to significant progress and presents numerous …