Vision Group, EECE of UCAS
Vision Group, affiliated to the EECE of UCAS. The vision group is mainly engaged in the research of image and video prococesing
China
Pinned Repositories
Anti-UAV
Served as a large-scale multi-modal benchmark, Anti-UAV drives the future research on the frontiers of tracking UAVs in the wild. With the above innovations and contributions, we have organized the CVPR 2020 Workshop on the 1st Anti-UAV Challenge. These contributions together significantly benefit the community.
Effective-Fusion-Factor
Effective Fusion Factor in FPN for Tiny Object Detection(WACV2021)
GroupSampling
published in IEEE Transactions on Image Processing (TIP), 2023
Instance-level-Scale-Match
we investigate the scale alignment between pre-training and target datasets, and propose a new refined Scale Match method (termed SM+) for tiny person detection. SM+ improves the scale match from image level to instance level, and effectively promotes the similarity between pre-training dataset and target dataset.
P2BNet
ECCV2022, Point-to-Box Network for Accurate Object Detection via Single Point Supervision
P2Seg-Public
PointTinyBenchmark
Point based and tiny object detection and localization code set of UCAS-VG
Sambor
Sambor: Boosting Segment Anything Model Towards Open-Vocabulary Learning
ssddet
[ICCV 2023] Spatial Self-Distillation for Object Detection with Inaccurate Bounding Boxes
TOV_mmdetection
Include mmdetection version of TinyBenchmark. Official link.
Vision Group, EECE of UCAS's Repositories
ucas-vg/PointTinyBenchmark
Point based and tiny object detection and localization code set of UCAS-VG
ucas-vg/Anti-UAV
Served as a large-scale multi-modal benchmark, Anti-UAV drives the future research on the frontiers of tracking UAVs in the wild. With the above innovations and contributions, we have organized the CVPR 2020 Workshop on the 1st Anti-UAV Challenge. These contributions together significantly benefit the community.
ucas-vg/P2BNet
ECCV2022, Point-to-Box Network for Accurate Object Detection via Single Point Supervision
ucas-vg/Effective-Fusion-Factor
Effective Fusion Factor in FPN for Tiny Object Detection(WACV2021)
ucas-vg/TOV_mmdetection
Include mmdetection version of TinyBenchmark. Official link.
ucas-vg/Sambor
Sambor: Boosting Segment Anything Model Towards Open-Vocabulary Learning
ucas-vg/GroupSampling
published in IEEE Transactions on Image Processing (TIP), 2023
ucas-vg/ssddet
[ICCV 2023] Spatial Self-Distillation for Object Detection with Inaccurate Bounding Boxes
ucas-vg/P2Seg-Public
ucas-vg/Instance-level-Scale-Match
we investigate the scale alignment between pre-training and target datasets, and propose a new refined Scale Match method (termed SM+) for tiny person detection. SM+ improves the scale match from image level to instance level, and effectively promotes the similarity between pre-training dataset and target dataset.
ucas-vg/SAM-CP
ucas-vg/SAPNet
SAPNet: Semantic-aware-SAM-for-Point-Supervised-Instance-Segmentation