Jiyang-Zheng

detectron2

Detectron2 is FAIR's next-generation platform for object detection, segmentation and other visual recognition tasks.

DirectVoxGO

Direct voxel grid optimization for fast radiance field reconstruction.

DivideMix

Code for paper: DivideMix: Learning with Noisy Labels as Semi-supervised Learning

dual-t-reducing-estimation-error-for-transition-matrix-in-label-noise-learning

EOPSN

[CVPR 2021] Exemplar-Based Open-Set Panoptic Segmentation Network (EOPSN)

instant-ngp

Instant neural graphics primitives: lightning fast NeRF and more

iVAE

VAEs and nonlinear ICA: a unifying framework

Jiyang-Zheng.github.io

MaskFormer

Per-Pixel Classification is Not All You Need for Semantic Segmentation (NeurIPS 2021, spotlight)

moco

PyTorch implementation of MoCo: https://arxiv.org/abs/1911.05722

Jiyang-Zheng/detectron2

Detectron2 is FAIR's next-generation platform for object detection, segmentation and other visual recognition tasks.

Jiyang-Zheng/DirectVoxGO

Direct voxel grid optimization for fast radiance field reconstruction.

Jiyang-Zheng/DivideMix

Code for paper: DivideMix: Learning with Noisy Labels as Semi-supervised Learning

Jiyang-Zheng/dual-t-reducing-estimation-error-for-transition-matrix-in-label-noise-learning

Jiyang-Zheng/EOPSN

[CVPR 2021] Exemplar-Based Open-Set Panoptic Segmentation Network (EOPSN)

Jiyang-Zheng/instant-ngp

Instant neural graphics primitives: lightning fast NeRF and more

Jiyang-Zheng/iVAE

VAEs and nonlinear ICA: a unifying framework

Jiyang-Zheng/Jiyang-Zheng.github.io

Jiyang-Zheng/MaskFormer

Per-Pixel Classification is Not All You Need for Semantic Segmentation (NeurIPS 2021, spotlight)

Jiyang-Zheng/moco

PyTorch implementation of MoCo: https://arxiv.org/abs/1911.05722

Jiyang-Zheng/nerf-navigation

Code for the Nerf Navigation Paper. Implements a trajectory optimiser and state estimator which use NeRFs as an environment representation

Jiyang-Zheng/OWOD

(CVPR 2021 Oral) Open World Object Detection

Jiyang-Zheng/UNO

Official implementation of "A Unified Objective for Novel Class Discovery", ICCV2021 (Oral)