← Search

Chenyang Si*

2 accepted papers

2024

HPFF: Hierarchical Locally Supervised Learning with Patch Feature Fusion

ECCV 2024poster

"Traditional deep learning relies on end-to-end backpropagation for training, but it suffers from drawbacks such as high memory consumption and not aligning with biological neural networks. Recent advancements have introduced locally supervised learning, which divides networks into modules with isol…

2024

Momentum Auxiliary Network for Supervised Local Learning

ECCV 2024oral

"Deep neural networks conventionally employ end-to-end backpropagation for their training process, which lacks biological credibility and triggers a locking dilemma during network parameter updates, leading to significant GPU memory use. Supervised local learning, which segments the network into mul…