Dr Yifan Liu

structure_knowledge_distillation. The official code for the paper 'Structured Knowledge Distillation for Semantic Segmentation'. (CVPR 2019 ORAL) and extension to other tasks.

CoupleGenerator. Generate your lover with your photo

ETC-Real-time-Per-frame-Semantic-video-segmentation. Enforcing temporal consistency in real-time per-frame semantic video segmentation

TorchDistiller. Python

Auto_painter. Recently, realistic image generation using deep neural networks has become a hot topic in machine learning and computer vision. Such an image can be generated at pixel level by learning from a large collection of images. Learning to generate colorful cartoon images from black-and-white sketches is not only an interesting research problem, but also a useful application in digital entertainment. In this paper, we investigate the sketch-to-image synthesis problem by using conditional generative adversarial networks (cGAN). We propose a model called auto-painter which can automatically generate compatible colors given a sketch. Wasserstein distance is used in training cGAN to overcome model collapse and enable the model converged much better. The new model is not only capable of painting hand-draw sketch with compatible colors, but also allowing users to indicate preferred colors. Experimental results on different sketch datasets show that the auto-painter performs better than other existing image-to-image methods.

EMM-for-stock-prediction. We propose a model to analyze sentiment of online stock forum and use the information to predict stock volatility in the Chinese market. By generating a sentimental dictionary, we analyze the sentimental tendencies of each post as sentiment indicators. Such sentimental information will be fused with market data for prediction based on Recurrent Neural Networks (RNNs). We manually labeled the sentiment of forum post and make the data public available for research. Empirical evidence shows that 8 of the 10 stocks perform better with sentimental indicators.

Auto_painter_demo. The code of building a web demo for Auto_painter

SSIW. The code of 'The devil is in the labels: Semantic segmentation from sentences'.

CWD. Channel-wise Distillation for Semantic Segmentation

inceptionV2_finetune. Fine-tuning of inceptionV2 on CUB-200 Birds dataset in Tensorflow

stock_predict. This project predicts stock trends on the basis of online user comments and LSTM

OCNet. OCNet achieves the state-of-the-art scene parsing performance on both Cityscapes and ADE20K.

reid-strong-baseline. Bag of Tricks and A Strong Baseline for Deep Person Re-identification

HRNet-Semantic-Segmentation. High-resolution representation learning (HRNets) for Semantic Segmentation

colorization. reading note

pix2pix-tensorflow. Tensorflow port of Image-to-Image Translation with Conditional Adversarial Nets https://phillipi.github.io/pix2pix/

pytorch-segmentation-toolbox. PyTorch Implementations for DeeplabV3 and PSPNet

MegaDepth. Code of single-view depth prediction algorithm on Internet Photos described in "MegaDepth: Learning Single-View Depth Prediction from Internet Photos, Z. Li and N. Snavely, CVPR 2018".

AttnGAN. Python

pytorch-segmentation-detection. Image Segmentation and Object Detection in Pytorch

DenseASPP. DenseASPP for Semantic Segmentation in Street Scenes

PSPNet-tensorflow. An implementation of PSPNet in tensorflow, see tutorial at:

LightNet. LightNet: Light-weight Networks for Semantic Image Segmentation (Cityscapes and Mapillary Vistas Dataset)

KittiSeg. A Kitti Road Segmentation model implemented in tensorflow.

pytorch-mobilenet-v2. A PyTorch implementation of MobileNet V2 architecture and pretrained model.

Semantic-Segmentation-Suite. Semantic Segmentation Suite in TensorFlow. Implement, train, and test new Semantic Segmentation models easily!

detectron2. Detectron2 is FAIR's next-generation platform for object detection and segmentation.

network-slimming. Network Slimming (Pytorch) (ICCV 2017)

antialiased-cnns. Antialiasing cnns to improve stability and accuracy. In ICML 2019.

DORN_pytorch. PyTorch implementation of Deep Ordinal Regression Network for Monocular Depth Estimation

SOLO. SOLO: Segmenting Objects by Locations https://arxiv.org/abs/1912.04488

python-guided-filter. Numpy/Scipy implementation of the (fast) Guided Filter

DeepLabV3Plus-Pytorch. DeepLabv3, DeepLabv3+ and pretrained weights on VOC & Cityscapes

semseg. Semantic Segmentation in Pytorch

guided-filter-pytorch. PyTorch implementation of Guided Image Filtering

DCP. Code for “Discrimination-aware-Channel-Pruning-for-Deep-Neural-Networks”

CC-FPSE. Python

MaskTrackRCNN. MaskTrackRCNN for video instance segmentation based on mmdetection

FCRN. A Pytorch implement of 《Deeper Depth Prediction with Fully Convolutional Residual Networks》

MobileNet-PyTorch. :star2: This is pytorch implemention of mobile architecture (mobilenet and shufflenet)

improved-wgan-pytorch. Improved WGAN in Pytorch

semantic-segmentation-pytorch. Pytorch implementation for Semantic Segmentation/Scene Parsing on MIT ADE20K dataset

Self-Attention-GAN. Pytorch implementation of Self-Attention Generative Adversarial Networks (SAGAN)

StackGAN. Python

conditional-dcgan-keras. Keras implementation of the conditional GAN.

DIGITS. Deep Learning GPU Training System

PhotographicImageSynthesis. Photographic Image Synthesis with Cascaded Refinement Networks

tensorflow-vgg. VGG19 and VGG16 on Tensorflow

erfnet_pytorch. Pytorch code for semantic segmentation using ERFNet

SegNet-Tutorial. Files for a tutorial to train SegNet for road scenes using the CamVid dataset

pytorch-fcn. PyTorch Implementation of Fully Convolutional Networks.

pytorch-segnet. Trying to replicate the SegNet results with pytorch

vgg-16-4-segmentation-tensorflow. raw code！

segnet_pytorch. SegNet implemetation using PyTorch

pix2pix-keras-tensorflow. Python