Huan Wang

Efficient-Deep-Learning. Collection of recent methods on (deep) neural network compression and acceleration.

Collaborative-Distillation. [CVPR'20] Collaborative Distillation for Ultra-Resolution Universal Style Transfer (PyTorch)

Regularization-Pruning. [ICLR'21] Neural Pruning via Growing Regularization (PyTorch)

ASSL. [NeurIPS'21 Spotlight] Aligned Structured Sparsity Learning for Efficient Image Super-Resolution (PyTorch)

Awesome-Pruning-at-Initialization. [IJCAI'22 Survey] Recent Advances on Neural Network Pruning at Initialization.

Awesome-Efficient-ViT. Recent Advances on Efficient Vision Transformers

smilelogging. Python logging package for easy reproducible experimenting in research

Why-the-State-of-Pruning-so-Confusing. [Preprint] Why is the State of Neural Network Pruning so Confusing? On the Fairness, Comparison Setup, and Trainability in Network Pruning

Good-DA-in-KD. [NeurIPS'22] What Makes a "Good" Data Augmentation in Knowledge Distillation -- A Statistical Perspective

TPP. [ICLR'23] Trainability Preserving Neural Pruning (PyTorch)

Smile-Pruning. A generic code base for neural network pruning, especially for pruning at initialization.

LightAvatar-TensorFlow. TensorFlow code for our ECCV'24 Workshop paper "LightAvatar: Efficient Head Avatar as Dynamic NeLF"

SRP. [ICLR'22] PyTorch code for our paper "Learning Efficient Image Super-Resolution Networks via Structure-Regularized Pruning"

Caffe_IncReg. [IJCNN'19, IEEE JSTSP'19] Caffe code for our paper "Structured Pruning for Efficient ConvNets via Incremental Regularization"; [BMVC'18] "Structured Probabilistic Pruning for Convolutional Neural Network Acceleration"

WritingTips. "Good scientific writing is not a matter of life and death; it is much more serious than that."

Efficient-NeRF. Python

LowlevelVision. paper collection for low-level vision

UtilsHub. Jupyter Notebook

AdversarialAttacks.

facenet. Tensorflow implementation of the FaceNet face recognizer

mingsun-tse.github.io. Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes

Context-Cluster. [ICLR 2023 Oral] Image as Set of Points