Mae segmentation - Reproduction of semantic segmentation using masked autoencoder (mae)

Last update: Dec 17, 2022

Overview

ADE20k Semantic segmentation with MAE

Getting started

Install the mmsegmentation library and some required packages.

pip install mmcv-full==1.3.0 mmsegmentation==0.11.0
pip install scipy timm==0.3.2

Install apex for mixed-precision training

git clone https://github.com/NVIDIA/apex
cd apex
pip install -v --disable-pip-version-check --no-cache-dir --global-option="--cpp_ext" --global-option="--cuda_ext" ./

Follow the guide in mmseg to prepare the ADE20k dataset.

Fine-tuning for Reproducing Results of MAE ViT-Base

Command:

tools/dist_train.sh configs/mae/upernet_mae_base_12_512_slide_160k_ade20k.py 8 --seed 0  --options model.pretrained=https://dl.fbaipublicfiles.com/mae/pretrain/mae_pretrain_vit_base.pth

Expected results log(paper results: 48.1 mIoU):

+--------+-------+-------+-------+
| Scope  | mIoU  | mAcc  | aAcc  |
+--------+-------+-------+-------+
| global | 48.15 | 58.99 | 83.05 |
+--------+-------+-------+-------+

Evaluation

Command format:

tools/dist_test.sh  <CONFIG_PATH> <CHECKPOINT_PATH> <NUM_GPUS> --eval mIoU

Acknowledgment

This code is built using the mmsegmentation library, Timm library, the Swin repository, XCiT, SETR, BEiT and the MAE repository.

Mae segmentation - Reproduction of semantic segmentation using masked autoencoder (mae)

Related tags

Overview

ADE20k Semantic segmentation with MAE

Getting started

Fine-tuning for Reproducing Results of MAE ViT-Base

Evaluation

Acknowledgment

Owner

SSL_SLAM2: Lightweight 3-D Localization and Mapping for Solid-State LiDAR (mapping and localization separated) ICRA 2021

This folder contains the python code of UR5E's advanced forward kinematics model.

This repository contains the official MATLAB implementation of the TDA method for reverse image filtering

Implementation of average- and worst-case robust flatness measures for adversarial training.

Codebase for Attentive Neural Hawkes Process (A-NHP) and Attentive Neural Datalog Through Time (A-NDTT)

Masked regression code - Masked Regression

[ECCV 2020] Reimplementation of 3DDFAv2, including face mesh, head pose, landmarks, and more.

A collection of SOTA Image Classification Models in PyTorch

a short visualisation script for pyvideo data

Intrinsic Image Harmonization

Official Pytorch implementation of RePOSE (ICCV2021)

A Fast Monotone Rotating Shallow Water model

Official implementation for “Unsupervised Low-Light Image Enhancement via Histogram Equalization Prior”

Step by Step on how to create an vision recognition model using LOBE.ai, export the model and run the model in an Azure Function

A Text Attention Network for Spatial Deformation Robust Scene Text Image Super-resolution (CVPR2022)

Unified Pre-training for Self-Supervised Learning and Supervised Learning for ASR

Code and Data for NeurIPS2021 Paper "A Dataset for Answering Time-Sensitive Questions"

Dyalog-apl-docset - Dyalog APL Dash Docset Generator

Official PyTorch implementation of paper: Standardized Max Logits: A Simple yet Effective Approach for Identifying Unexpected Road Obstacles in Urban-Scene Segmentation (ICCV 2021 Oral Presentation)

Open-L2O: A Comprehensive and Reproducible Benchmark for Learning to Optimize Algorithms