Multi-task learning using uncertainty to weigh losses for scene geometry and semantics, Auxiliary Tasks in Multi-task Learning

An implementation of two academic papers on determining skin colour pixels of images. Used to determine individual typology angle (ITA).

An easy-to-use library for skin tone classification

[ECCV 2022] CelebV-HQ: A Large-Scale Video Facial Attributes Dataset

A C++ Background Subtraction Library with wrappers for Python, MATLAB, Java and GUI on QT

针对pytorch模型的自动化模型结构分析和修改工具集，包含自动分析模型结构的模型压缩算法库

The official implementation of [CVPR2022] Decoupled Knowledge Distillation https://arxiv.org/abs/2203.08679 and [ICCV2023] DOT: A Distillation-Oriented Trainer https://openaccess.thecvf.com/content…

This is an official implementation for "AutoFocusFormer: Image Segmentation off the Grid".

PyTorch Project Specification.

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".

Checkpoints, logs and source code for AAAI-23 paper 'Data-Efficient Image Quality Assessment with Attention-Panel Decoder'

TinyNeuralNetwork is an efficient and easy-to-use deep learning model compression framework.

No-Reference Image Quality Assessment via Transformers, Relative Ranking, and Self-Consistency

An implementation of Coarse-to-fine PatchMatch(CPM) Optical Flow

Fast, accurate optical flows on mobile GPUs.

BriefMatch real-time GPU optical flow

A real time optical flow algorithm implemented on GPU

FaceQAN: Face Image Quality Assessment Through Adversarial Noise Exploration

👁️ 🖼️ 🔥PyTorch Toolbox for Image Quality Assessment, including LPIPS, FID, NIQE, NRQM(Ma), MUSIQ, TOPIQ, NIMA, DBCNN, BRISQUE, PI and more...

Non-local Modeling for Image Quality Assessment

MDFlow: Unsupervised Optical Flow Learning by Reliable Mutual Knowledge Distillation (TCSVT 2022)

[ICLR 2020] Contrastive Representation Distillation (CRD), and benchmark of recent knowledge distillation methods

Jittor implementation of the paper "Hierarchical Layout-Aware Graph Convolutional Network for Unified Aesthetics Assessment"

Self-distillation with Batch Knowledge Ensembling Improves ImageNet Classification

[ICML 2022] "DepthShrinker: A New Compression Paradigm Towards Boosting Real-Hardware Efficiency of Compact Neural Networks", by Yonggan Fu, Haichuan Yang, Jiayi Yuan, Meng Li, Cheng Wan, Raghurama…

[ECCV 2022] LEDNet: Joint Low-light Enhancement and Deblurring in the Dark

72.8% MobileNetV2 1.0 model on ImageNet and a spectrum of pre-trained MobileNetV2 models