A list of papers, docs, codes about model quantization. This repo is aimed to provide the info for model quantization research, we are continuously improving the project. Welcome to PR the works (papers, repositories) that are missed by the repo.

MarStech vision sensor is a low cost sensor for STEM Education

LIDIA: Lightweight Learned Image Denoising with Instance Adaptation (NTIRE, 2020)

The collection of training tricks of binarized neural networks.

Hypercomplex Neural Networks with PyTorch

Code for TMM 2022 "Accurate Head Pose Estimation Using Image Rectification and Lightweight Convolutional Neural Network"

A list of papers, docs, codes about diffusion distillation.This repo collects various distillation methods for the Diffusion model. Welcome to PR the works (papers, repositories) missed by the repo.

Official implementation of NanoNet: Real-time medical Image segmentation architecture (IEEE CBMS)

资源受限环境下、大规模肺炎早筛方法。采用DSHNet生成少类样本数据，解决数据不平衡的问题，然后利用RSFNet进行分类，最后结合剪枝策略实现轻量化！MedGAN-ResLite-V2 is released! ❤

An official implementation of CVPR 2019 paper "All You Need Is a Few Shifts: Designing Efficient Convolutional Neural Networks for Image Classification".

Lightweight neural network for cancer detection in bone scans using PyTorch. Code repository for the paper "A Lightweight Convolutional Neural Network for Detection of Osseous Metastasis using Feature Fusion and Attention Strategies". Presented at CVIPPR 2024.

Approximating a 3DCNN with a 2DCNN

(SIGMOD 2021) Pool of Experts: Realtime Querying Specialized Knowledge in Massive Neural Networks

A pytorch implementation of CVPR2019 paper "All You Need Is a Few Shifts: Designing Efficient Convolutional Neural Networks for Image Classification".

Human pose estimation model

Binarized Neural Network (BNN) implementation using TensorFlow 2 and PyTorch, with inference using Numpy and C.

Facial Landmark Detection Using Knowledge Distillation-Based Neural Networks

Pytroch implementation of a mini ResNet.

Lightweight deep-learning pipeline for 9-class gallbladder ultrasound (patient-level 5-fold CV, blur-QC, class imbalance handling, Grad-CAM++).