songhwanjun

Awesome-Noisy-Labels

A Survey

ActiveBias

Co-teaching

MEDUSA

A RGB-D object detection paper accepted at BMVC 2021.

drsa

Deep Recurrent Survival Analysis, an auto-regressive deep model for time-to-event data analysis with censorship handling.

academic-kickstart

📝 Easily create a beautiful website using Academic, Hugo, and Netlify

al-folio

A beautiful, simple, clean, and responsive Jekyll theme for academics

anonymized-project

BatchSelection

BMVCTemplate

Paper template and author instructions for BMVC

Deformable-DETR

Deformable DETR: Deformable Transformers for End-to-End Object Detection.

detr

End-to-End Object Detection with Transformers

DISL-Lab

dual-T-Estimator

EMNLP-Discal

hugo-academic

📝 The website builder for Hugo. Build and deploy a beautiful website in minutes!

lvis-api

Python API for LVIS Dataset

MiDaS

Code for robust monocular depth estimation described in "Ranftl et. al., Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer, arXiv:1907.01341"

old_web

Public-Datasets-for-Noisy-Labels

This repository contains the description of publicly available datasets with real-world label noise. The download link is provided as well.

pytorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration

pytorch-image-models

PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, EfficientNetV2, NFNet, Vision Transformer, MixNet, MobileNet-V3/V2, RegNet, DPN, CSPNet, and more

RecencyBias

SOLQ

"SOLQ: Segmenting Objects by Learning Queries", SOLQ is an end-to-end instance segmentation framework with Transformer.

songhwanjun

songhwanjun.github.io

test

test_academic

vidt

YOLOS

You Only Look at One Sequence (NeurIPS 2021)