Hust Visual Learning Team

YOLOP

You Only Look Once for Panopitic Driving Perception.（https://arxiv.org/abs/2108.11250）

YOLOS

You Only Look at One Sequence (NeurIPS 2021)

QueryInst

Instances as Queries (ICCV 2021)

SparseInst

SparseInst: Sparse Instance Activation for Real-Time Instance Segmentation, CVPR 2022

MIMDet

MIMDet: Unleashing Vanilla Vision Transformer with Masked Image Modeling for Object Detection

TopFormer

TopFormer: Token Pyramid Transformer for Mobile Semantic Segmentation, CVPR2022

BMaskR-CNN

Boundary-preserving Mask R-CNN (ECCV 2020)

TeViT

Temporally Efficient Vision Transformer for Video Instance Segmentation, CVPR 2022, Oral

HAIS

Hierarchical Aggregation for 3D Instance Segmentation (ICCV 2021)

CrossVIS

Crossover Learning for Fast Online Video Instance Segmentation (ICCV 2021)

MSG-Transformer

MSG-Transformer: Exchanging Local Spatial Information by Manipulating Messenger Tokens (CVPR 2022)

AziNorm

AziNorm: Exploiting the Radial Symmetry of Point Cloud for Azimuth-Normalized 3D Perception, CVPR 2022.

NeuSample

Code of "NeuSample: Neural Sample Field for Efficient View Synthesis"

LSFA

Real-Time and Accurate Object Detection in Compressed Video by Long Short-term Feature Aggregation

EfficientPose

mancs

Mancs: A multi-task attentional network with curriculum sampling for person re-identification

BoxCaseg

DGCN

PySA

Pyramid Self-Attention for Semantic Segmentation

ByteTrack

ByteTrack: multi-object tracking by Associating Every Detection Box

tbcl

Storage

checkpoints storage of hustvl

TinyDet

DenseNAS

Densely Connected Search Space for More Flexible Neural Architecture Search

EAT-NAS

EAT-NAS: Elastic Architecture Transfer for Accelerating Large-scale Neural Architecture Search

FairMOT

[IJCV-2021] FairMOT: On the Fairness of Detection and Re-Identification in Multi-Object Tracking

FNA

Fast Neural Network Adaptation via Parameter Remapping and Architecture Search

maskscoring_rcnn

Codes for paper "Mask Scoring R-CNN".

pcl.pytorch

PyTorch codes for our paper "PCL: Proposal Cluster Learning for Weakly Supervised Object Detection".

PTSNet

Proposal, Tracking and Segmentation (PTS): A Cascaded Network for Video Object Segmentation