Login / Signup

Joint Dual Feature Distillation and Gradient Progressive Pruning for BERT compression.

Zhou ZhangYang LuTengfei WangXing WeiZhen Wei
Published in: Neural Networks (2024)
Keyphrases
  • search space
  • edge detection
  • feature vectors
  • image features
  • compression scheme
  • image processing
  • feature set
  • compression algorithm
  • image gradient
  • pruning method