Guangrun Wang (王广润)

SYSU-30k. SYSU-30k Dataset of "Weakly Supervised Person Re-ID: Differentiable Graphical Learning and A New Benchmark" https://arxiv.org/abs/1904.03845

Adaptively-Connected-Neural-Networks. A re-implementation of our CVPR 2019 paper "Adaptively Connected Neural Networks"

triplet. Code of the paper "Solving Inefficiency of Self-supervised Representation Learning"

Learning-Feature-Pyramids. Code of "Training ImageNet and PASCAL VOC2012 via Learning Feature Pyramids "

Kalman-Normalization. Code of "Batch Kalman Normalization: Towards Training Deep Neural Networks with Micro-Batches"

TreeConv. This is a re-implementation of our KDD 2020 paper "Grammatically Recognizing Images with Tree Convolution."

Adaptively-Connected-Neural-Networks-Pytorch. This is the pytorch implementation of "Adaptively Connected Neural Networks" for the currently popular EfficientNet and the efficient DNA network families.

Semantic-Aware-AE. Python

Learning-Feature-Pyramids-For-COCO. Training COCO 2017 Object Detection and Segmentation via Learning Feature Pyramids

wanggrun.github.io. HTML

Kalman-Normalization-and-Population-Normalization. Code of our NIPS 2018 Paper: "Kalman Normalization"

Grounded-Segment-Anything. Grounded-SAM: Marrying Grounding-DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything

IDW-CNN-V2. Code of "Learning object interactions and descriptions for semantic image segmentation"

4D-Humans. 4DHumans: Reconstructing and Tracking Humans with Transformers

materials_discovery. Python

stable-dreamfusion. A pytorch implementation of text-to-3D dreamfusion, powered by stable diffusion.

ViT-pytorch. Pytorch reimplementation of the Vision Transformer (An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale)

stable-diffusion. A latent text-to-image diffusion model

pytorch-image-models-v2. PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNet-V3/V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more

Spatial-Temporal-Re-identification. Spatial-Temporal Re-identification

FLOPs-of-MACC-in-tensorflow.

Depth-Anything. Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data. Foundation Model for Monocular Depth Estimation