I may be slow to respond.
Stars
[ICLR 2020] Contrastive Representation Distillation (CRD), and benchmark of recent knowledge distillation methods
《动手学深度学习》:面向中文读者、能运行、可讨论。中英文版被70多个国家的500多所大学用于教学。
EANet: Enhancing Alignment for Cross-Domain Person Re-identification
Task-driven feature pooling for image classification ICCV15
Codes for UODTN; Open domain recognition; CVPR19
Generative Dual Adversarial Network for Generalized Zero-shot Learning
Attentive Region Embedding Network for Zero-shot Learning (CVPR 2019)
This project is the Torch implementation of our ICCV 2017 paper: Centered Weight Normalization in Accelerating Training of Deep Neural Networks