sukjunhwang

PhD Student, Machine Learning @ CMU

Carnegie Mellon UniversityPittsburgh, PA

Pinned Repositories

GenVIS
[CVPR'23] A Generalized Framework for Video Instance Segmentation
Language:Python118 7 104
apex
A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch
Language:Python0 0 00
ClassyVision
An end-to-end PyTorch framework for image and video classification
Language:Jupyter Notebook0 0 00
cocoapi
COCO API Customized for YouTubeVIS evaluation
Language:Jupyter Notebook0 0 00
IFC
Video Instance Segmentation using Inter-Frame Communication Transformers (NeurIPS 2021)
Language:Python88 4 1413
netadapt
This repo contains the official Pytorch reimplementation of the paper "NetAdapt: Platform-Aware Neural Network Adaptation for Mobile Applications".
Language:Python1 1 00
set_classifier
Official PyTorch implementation of: "Cannot See the Forest for the Trees: Aggregating Multiple Viewpoints to Better Classify Objects in Videos" (CVPR 2022)
Language:Python13 1 00
VITA
VITA: Video Instance Segmentation via Object Token Association (NeurIPS 2022)
Language:Python96 7 1511

sukjunhwang/VITA
VITA: Video Instance Segmentation via Object Token Association (NeurIPS 2022)
Language:Python96 7 1511
sukjunhwang/IFC
Video Instance Segmentation using Inter-Frame Communication Transformers (NeurIPS 2021)
Language:Python88 4 1413
sukjunhwang/set_classifier
Official PyTorch implementation of: "Cannot See the Forest for the Trees: Aggregating Multiple Viewpoints to Better Classify Objects in Videos" (CVPR 2022)
Language:Python13 1 00
sukjunhwang/netadapt
This repo contains the official Pytorch reimplementation of the paper "NetAdapt: Platform-Aware Neural Network Adaptation for Mobile Applications".
Language:Python1 1 00
sukjunhwang/apex
A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch
Language:Python0 0 00
sukjunhwang/ClassyVision
An end-to-end PyTorch framework for image and video classification
Language:Jupyter Notebook0 0 00
sukjunhwang/cocoapi
COCO API Customized for YouTubeVIS evaluation
Language:Jupyter Notebook0 0 00
sukjunhwang/detectron2
Detectron2 is FAIR's next-generation research platform for object detection and segmentation.
Language:Python0 0 00
sukjunhwang/imgclsmob
Sandbox for training convolutional networks for computer vision
Language:Python00
sukjunhwang/MaskTrackRCNN
MaskTrackRCNN for video instance segmentation based on mmdetection
Language:Python0 0
sukjunhwang/tao
Code for downloading and using the TAO dataset: http://taodataset.org/