[CVPR 2021] Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers

Related tags

Deep LearningSETR
Overview

SEgmentation TRansformers -- SETR

image

Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers,
Sixiao Zheng, Jiachen Lu, Hengshuang Zhao, Xiatian Zhu, Zekun Luo, Yabiao Wang, Yanwei Fu, Jianfeng Feng, Tao Xiang, Philip HS Torr, Li Zhang,
CVPR 2021

Installation

Our project is developed based on mmsegmentation. Please follow the official mmsegmentation INSTALL.md and getting_started.md for installation and dataset preparation.

Main results

Cityscapes

Method Crop Size Batch size iteration set mIoU
SETR-Naive 768x768 8 40k val 77.37 model config
SETR-Naive 768x768 8 80k val 77.90 model config
SETR-MLA 768x768 8 40k val 76.65 model config
SETR-MLA 768x768 8 80k val 77.24 model config
SETR-PUP 768x768 8 40k val 78.39 model config
SETR-PUP 768x768 8 80k val 79.34 model config
SETR-Naive-DeiT 768x768 8 40k val 77.85 model config
SETR-Naive-DeiT 768x768 8 80k val 78.66 model config
SETR-MLA-DeiT 768x768 8 40k val 78.04 model config
SETR-MLA-DeiT 768x768 8 80k val 78.98 model config
SETR-PUP-DeiT 768x768 8 40k val 78.79 model config
SETR-PUP-DeiT 768x768 8 80k val 79.45 model config

ADE20K

Method Crop Size Batch size iteration set mIoU mIoU(ms+flip)
SETR-Naive 512x512 16 160k Val 48.06 48.80 model config
SETR-MLA 512x512 8 160k val 48.27 50.03 model config
SETR-MLA 512x512 16 160k val 48.64 50.28 model config
SETR-PUP 512x512 16 160k val 48.58 50.09 model config

Pascal Context

Method Crop Size Batch size iteration set mIoU mIoU(ms+flip)
SETR-Naive 480x480 16 80k val 52.89 53.61 model config
SETR-MLA 480x480 8 80k val 54.39 55.39 model config
SETR-MLA 480x480 16 80k val 54.87 55.83 model config
SETR-PUP 480x480 16 80k val 54.40 55.27 model config

Get Started

Train

./tools/dist_train.sh ${CONFIG_FILE} ${GPU_NUM} 
# For example, train a SETR-PUP on Cityscapes dataset with 8 GPUs
./tools/dist_train.sh configs/SETR/SETR_PUP_768x768_40k_cityscapes_bs_8.py 8

Single-scale testing

./tools/dist_test.sh ${CONFIG_FILE} ${CHECKPOINT_FILE} ${GPU_NUM}  [--eval ${EVAL_METRICS}]
# For example, test a SETR-PUP on Cityscapes dataset with 8 GPUs
./tools/dist_test.sh configs/SETR/SETR_PUP_768x768_40k_cityscapes_bs_8.py \
work_dirs/SETR_PUP_768x768_40k_cityscapes_bs_8/iter_40000.pth \
8 --eval mIoU

Multi-scale testing

Use the config file ending in _MS.py in configs/SETR.

./tools/dist_test.sh ${CONFIG_FILE} ${CHECKPOINT_FILE} ${GPU_NUM}  [--eval ${EVAL_METRICS}]
# For example, test a SETR-PUP on Cityscapes dataset with 8 GPUs
./tools/dist_test.sh configs/SETR/SETR_PUP_768x768_40k_cityscapes_bs_8_MS.py \
work_dirs/SETR_PUP_768x768_40k_cityscapes_bs_8/iter_40000.pth \
8 --eval mIoU

Please see getting_started.md for the more basic usage of training and testing.

Reference

@inproceedings{SETR,
    title={Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers}, 
    author={Zheng, Sixiao and Lu, Jiachen and Zhao, Hengshuang and Zhu, Xiatian and Luo, Zekun and Wang, Yabiao and Fu, Yanwei and Feng, Jianfeng and Xiang, Tao and Torr, Philip H.S. and Zhang, Li},
    booktitle={CVPR},
    year={2021}
}

License

MIT

Acknowledgement

Thanks to previous open-sourced repo:
mmsegmentation
pytorch-image-models

Owner
Fudan Zhang Vision Group
Zhang Vision Group at the School of Data Science of the Fudan University, led by Professor Li Zhang
Fudan Zhang Vision Group
GitHub Repository
Code for Multimodal Neural SLAM for Interactive Instruction Following

Code for Multimodal Neural SLAM for Interactive Instruction Following Code structure The code is adapted from E.T. and most training as well as data p

7 Dec 07, 2022
Repo for the paper Extrapolating from a Single Image to a Thousand Classes using Distillation

Extrapolating from a Single Image to a Thousand Classes using Distillation by Yuki M. Asano* and Aaqib Saeed* (*Equal Contribution) Extrapolating from

Yuki M. Asano 16 Nov 04, 2022
Towards Implicit Text-Guided 3D Shape Generation (CVPR2022)

Towards Implicit Text-Guided 3D Shape Generation Towards Implicit Text-Guided 3D Shape Generation (CVPR2022) Code for the paper [Towards Implicit Text

55 Dec 16, 2022
Crowd-Kit is a powerful Python library that implements commonly-used aggregation methods for crowdsourced annotation and offers the relevant metrics and datasets

Crowd-Kit: Computational Quality Control for Crowdsourcing Documentation Crowd-Kit is a powerful Python library that implements commonly-used aggregat

Toloka 125 Dec 30, 2022
Simple Text-Generator with OpenAI gpt-2 Pytorch Implementation

GPT2-Pytorch with Text-Generator Better Language Models and Their Implications Our model, called GPT-2 (a successor to GPT), was trained simply to pre

Tae-Hwan Jung 775 Jan 08, 2023
YOLTv5 rapidly detects objects in arbitrarily large aerial or satellite images that far exceed the ~600×600 pixel size typically ingested by deep learning object detection frameworks

YOLTv5 rapidly detects objects in arbitrarily large aerial or satellite images that far exceed the ~600×600 pixel size typically ingested by deep learning object detection frameworks.

Adam Van Etten 145 Jan 01, 2023
Code release for NeRF (Neural Radiance Fields)

NeRF: Neural Radiance Fields Project Page | Video | Paper | Data Tensorflow implementation of optimizing a neural representation for a single scene an

6.5k Jan 01, 2023
Capture all information throughout your model's development in a reproducible way and tie results directly to the model code!

Rubicon Purpose Rubicon is a data science tool that captures and stores model training and execution information, like parameters and outcomes, in a r

Capital One 97 Jan 03, 2023
Video-Music Transformer

VMT Video-Music Transformer (VMT) is an attention-based multi-modal model, which generates piano music for a given video. Paper https://arxiv.org/abs/

Chin-Tung Lin 5 Jul 13, 2022
Official implementation for the paper: "Multi-label Classification with Partial Annotations using Class-aware Selective Loss"

Multi-label Classification with Partial Annotations using Class-aware Selective Loss Paper | Pretrained models Official PyTorch Implementation Emanuel

99 Dec 27, 2022
Official Implementation of SWAD (NeurIPS 2021)

SWAD: Domain Generalization by Seeking Flat Minima (NeurIPS'21) Official PyTorch implementation of SWAD: Domain Generalization by Seeking Flat Minima.

Junbum Cha 97 Dec 20, 2022
Algorithmic trading using machine learning.

Algorithmic Trading This machine learning algorithm was built using Python 3 and scikit-learn with a Decision Tree Classifier. The program gathers sto

Sourav Biswas 101 Nov 10, 2022
a general-purpose Transformer based vision backbone

Swin Transformer By Ze Liu*, Yutong Lin*, Yue Cao*, Han Hu*, Yixuan Wei, Zheng Zhang, Stephen Lin and Baining Guo. This repo is the official implement

Microsoft 9.9k Jan 08, 2023
optimization routines for hyperparameter tuning

Hyperopt: Distributed Hyperparameter Optimization Hyperopt is a Python library for serial and parallel optimization over awkward search spaces, which

Marc Claesen 398 Nov 09, 2022
Libraries, tools and tasks created and used at DeepMind Robotics.

Libraries, tools and tasks created and used at DeepMind Robotics.

DeepMind 270 Nov 30, 2022
Official Implementation of SimIPU: Simple 2D Image and 3D Point Cloud Unsupervised Pre-Training for Spatial-Aware Visual Representations

Official Implementation of SimIPU SimIPU: Simple 2D Image and 3D Point Cloud Unsupervised Pre-Training for Spatial-Aware Visual Representations Since

Zhyever 37 Dec 01, 2022
[ICCV'21] PlaneTR: Structure-Guided Transformers for 3D Plane Recovery

PlaneTR: Structure-Guided Transformers for 3D Plane Recovery This is the official implementation of our ICCV 2021 paper News There maybe some bugs in

73 Nov 30, 2022
The source code of the ICCV2021 paper "PIRenderer: Controllable Portrait Image Generation via Semantic Neural Rendering"

The source code of the ICCV2021 paper "PIRenderer: Controllable Portrait Image Generation via Semantic Neural Rendering"

Ren Yurui 261 Jan 09, 2023
A simplistic and efficient pure-python neural network library from Phys Whiz with CPU and GPU support.

A simplistic and efficient pure-python neural network library from Phys Whiz with CPU and GPU support.

Manas Sharma 19 Feb 28, 2022
TransZero++: Cross Attribute-guided Transformer for Zero-Shot Learning

TransZero++ This repository contains the testing code for the paper "TransZero++: Cross Attribute-guided Transformer for Zero-Shot Learning" submitted

Shiming Chen 6 Aug 16, 2022