Semi-supevised Semantic Segmentation with High- and Low-level Consistency

Last update: Dec 30, 2022

Related tags

Overview

Semi-supevised Semantic Segmentation with High- and Low-level Consistency

This Pytorch repository contains the code for our work Semi-supervised Semantic Segmentation with High- and Low-level Consistency. The approach uses two network branches that link semi-supervised classification with semi-supervised segmentation including self-training. The approach attains significant improvement over existing methods, especially when trained with very few labeled samples. On several standard benchmarks - PASCAL VOC 2012,PASCAL-Context, and Cityscapes - the approach achieves new state-of-the-art in semi-supervised learning.

We propose a two-branch approach to the task of semi-supervised semantic segmentation. The lower branch predicts pixel-wise class labels and is referred to as the Semi-Supervised Semantic Segmentation GAN(s4GAN). The upper branch performs image-level classification and is denoted as the Multi-Label Mean Teacher(MLMT).

Here, this repository contains the source code for the s4GAN branch. MLMT branch is adapted from Mean-Teacher work for semi-supervised classification. Instructions for setting up the MLMT branch are given below.

Package pre-requisites

The code runs on Python 3 and Pytorch 0.4 The following packages are required.

pip install scipy tqdm matplotlib numpy opencv-python

Dataset preparation

Download ImageNet pretrained Resnet-101(Link) and place it ./pretrained_models/

PASCAL VOC

Download the dataset(Link) and extract in ./data/voc_dataset/

PASCAL Context

Download the annotations(Link) and extract in ./data/pcontext_dataset/

Cityscapes

Download the dataset from the Cityscapes dataset server(Link). Download the files named 'gtFine_trainvaltest.zip', 'leftImg8bit_trainvaltest.zip' and extract in ./data/city_dataset/

Training and Validation on PASCAL-VOC Dataset

Results in the paper are averaged over 3 random splits. Same splits are used for reporting baseline performance for fair comparison.

Training fully-supervised Baseline (FSL)

python train_full.py    --dataset pascal_voc  \
                        --checkpoint-dir ./checkpoints/voc_full \
                        --ignore-label 255 \
                        --num-classes 21

Training semi-supervised s4GAN (SSL)

python train_s4GAN.py   --dataset pascal_voc  \
                        --checkpoint-dir ./checkpoints/voc_semi_0_125 \
                        --labeled-ratio 0.125 \
                        --ignore-label 255 \ 
                        --num-classes 21

Validation

python evaluate.py --dataset pascal_voc  \
                   --num-classes 21 \
                   --restore-from ./checkpoints/voc_semi_0_125/VOC_30000.pth

Training MLMT Branch

python train_mlmt.py \
        --batch-size-lab 16 \
        --batch-size-unlab 80 \
        --labeled-ratio 0.125 \
        --exp-name voc_semi_0_125_MLMT \
        --pkl-file ./checkpoints/voc_semi_0_125/train_voc_split.pkl

Final Evaluation S4GAN + MLMT

python evaluate.py --dataset pascal_voc  \
                   --num-classes 21 \
                   --restore-from ./checkpoints/voc_semi_0_125/VOC_30000.pth \
                   --with-mlmt \
                   --mlmt-file ./mlmt_output/voc_semi_0_125_MLMT/output_ema_raw_100.txt

Training and Validation on PASCAL-Context Dataset

python train_full.py    --dataset pascal_context  \
                        --checkpoint-dir ./checkpoints/pc_full \
                        --ignore-label -1 \
                        --num-classes 60

python train_s4GAN.py  --dataset pascal_context  \
                       --checkpoint-dir ./checkpoints/pc_semi_0_125 \
                       --labeled-ratio 0.125 \
                       --ignore-label -1 \
                       --num-classes 60 \
                       --split-id ./splits/pc/split_0.pkl
                       --num-steps 60000

python evaluate.py     --dataset pascal_context  \
                       --num-classes 60 \
                       --restore-from ./checkpoints/pc_semi_0_125/VOC_40000.pth

Training and Validation on Cityscapes Dataset

python train_full.py    --dataset cityscapes \
                        --checkpoint-dir ./checkpoints/city_full_0_125 \
                        --ignore-label 250 \
                        --num-classes 19 \
                        --input-size '256,512'  

python train_s4GAN.py   --dataset cityscapes \
                        --checkpoint-dir ./checkpoints/city_semi_0_125 \
                        --labeled-ratio 0.125 \
                        --ignore-label 250 \
                        --num-classes 19 \
                        --split-id ./splits/city/split_0.pkl \
                        --input-size '256,512' \
                        --threshold-st 0.7 \
                        --learning-rate-D 1e-5 

python evaluate.py      --dataset cityscapes \
                        --num-classes 19 \
                        --restore-from ./checkpoints/city_semi_0_125/VOC_30000.pth

Acknowledgement

Parts of the code have been adapted from: DeepLab-Resnet-Pytorch, AdvSemiSeg, PyTorch-Encoding

Citation

@ARTICLE{8935407,
  author={S. {Mittal} and M. {Tatarchenko} and T. {Brox}},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence}, 
  title={Semi-Supervised Semantic Segmentation With High- and Low-Level Consistency}, 
  year={2021},
  volume={43},
  number={4},
  pages={1369-1379},
  doi={10.1109/TPAMI.2019.2960224}}

Semi-supevised Semantic Segmentation with High- and Low-level Consistency

Related tags

Overview

Semi-supevised Semantic Segmentation with High- and Low-level Consistency

Package pre-requisites

Dataset preparation

PASCAL VOC

PASCAL Context

Cityscapes

Training and Validation on PASCAL-VOC Dataset

Training fully-supervised Baseline (FSL)

Training semi-supervised s4GAN (SSL)

Validation

Training MLMT Branch

Final Evaluation S4GAN + MLMT

Training and Validation on PASCAL-Context Dataset

Training and Validation on Cityscapes Dataset

Acknowledgement

Citation

Owner

FlingBot: The Unreasonable Effectiveness of Dynamic Manipulations for Cloth Unfolding

Rethinking the U-Net architecture for multimodal biomedical image segmentation

ICCV2021 - A New Journey from SDRTV to HDRTV.

Image data augmentation scheduler for albumentations transforms

ML for NLP and Computer Vision.

Using NumPy to solve the equations of fluid mechanics together with Finite Differences, explicit time stepping and Chorin's Projection methods

Solution of Kaggle competition: Sartorius - Cell Instance Segmentation

CVPR 2021 Challenge on Super-Resolution Space

CMP 414/765 course repository for Spring 2022 semester

[CVPR2021] De-rendering the World's Revolutionary Artefacts

A novel framework to automatically learn high-quality scanning of non-planar, complex anisotropic appearance.

Progressive Domain Adaptation for Object Detection

Implementation of the Point Transformer layer, in Pytorch

Material for my PyConDE & PyData Berlin 2022 Talk "5 Steps to Speed Up Your Data-Analysis on a Single Core"

DR-GAN: Automatic Radial Distortion Rectification Using Conditional GAN in Real-Time

PyTorch Language Model for 1-Billion Word (LM1B / GBW) Dataset

Semantic Segmentation with SegFormer on Drone Dataset.

[CVPR 2022] Structured Sparse R-CNN for Direct Scene Graph Generation

SSD-based Object Detection in PyTorch

Deep Learning Datasets Maker is a QGIS plugin to make datasets creation easier for raster and vector data.