Epiphqny

Computer vision. Instance segmentation.

The University of Hong KongHong Kong

Pinned Repositories

CondInst
Conditional Convolutions for Instance Segmentation, achives 37.1mAP on coco val
Language:Python137 6 1014
Epiphqny
Config files for my GitHub profile.
0 1 00
Multiple-instance-learning
Pytorch implementation of three Multiple Instance Learning or Multi-classification papers
Language:Python129 3 824
SOLO
SOLO: Segmenting Objects by Locations
Language:Python165 8 817
SOLOv2
SOLOv2: Dynamic, Faster and Stronger, achives 39.5mAP on coco test-dev (36 epochs result)
Language:Python242 9 3537
VisTR
[CVPR2021 Oral] End-to-End Video Instance Segmentation with Transformers
Language:Python737 11 7896
Yolact_fcos
YOLACT: Real-time Instance Segmentation on the FCOS detector (without bbox cropping), achives 35.2mAP on coco val
Language:Python87 8 519
detr
End-to-End Object Detection with Transformers
Language:Python13k 149 5262.3k
magvit2-pytorch
Implementation of MagViT2 Tokenizer in Pytorch
Language:Python440 29 3128
StreamingT2V
StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text
Language:Python981 38 3988

Epiphqny/VisTR
[CVPR2021 Oral] End-to-End Video Instance Segmentation with Transformers
Language:Python737 11 7896
Epiphqny/SOLOv2
SOLOv2: Dynamic, Faster and Stronger, achives 39.5mAP on coco test-dev (36 epochs result)
Language:Python242 9 3537
Epiphqny/SOLO
SOLO: Segmenting Objects by Locations
Language:Python165 8 817
Epiphqny/CondInst
Conditional Convolutions for Instance Segmentation, achives 37.1mAP on coco val
Language:Python137 6 1014
Epiphqny/Multiple-instance-learning
Pytorch implementation of three Multiple Instance Learning or Multi-classification papers
Language:Python129 3 824
Epiphqny/Yolact_fcos
YOLACT: Real-time Instance Segmentation on the FCOS detector (without bbox cropping), achives 35.2mAP on coco val
Language:Python87 8 519
Epiphqny/Epiphqny
Config files for my GitHub profile.
0 1 00