Pay Attention to Features, Transfer Learn Faster CNNs

By Kafeng Wang, Xitong Gao, Yiren Zhao, Xingjian Li, Dejing Dou, Chengzhong Xu. 2020

83 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Lorenzo Bonicelli
2. Matteo Boschini
3. Angelo Porrello
4. Simone Calderara
5. Concetto Spampinato
6. Giovanni Bellitto
7. Matteo Pennisi
8. Linfeng Zhang

Citations in the corpus

• Transfer without Forgetting (2022, methodology): “On these grounds, we take inspiration from [66] and use a weighted version of Eq.”
• Task-Oriented Feature Distillation (2020, methodology): “Later, abundant feature distillation methods are proposed to encourage the student models to mimic the features of teacher models [53, 62, 66, 7, 20].”
• Lipschitz Continuity Guided Knowledge Distillation (2021, background): “[41] introduced an attention mechanism to assign weights to different CNNs’ channels for dynamically determining the critical features to dis-”