"Domain Adaptive Semantic Segmentation without Source Data" (ACM MM 2021)

benfour

Last update: Sep 28, 2022

Related tags

Deep Learning LDBE

Overview

LDBE

Pytorch implementation for two papers (the paper will be released soon):

"Domain Adaptive Semantic Segmentation without Source Data", ACM MM2021.

"Challenging Source-free Domain Adaptive Semantic Segmentation", submitted to TPAMI.

Method

Result

GTA5 -> Cityscapes:

Methods	Source-only	LD	LDBE
mIoU	35.7	45.5	49.2

SYNTHIA -> Cityscapes:

Methods	Source-only	LD	LDBE
mIoU (16-classes)	32.5	42.6	43.5
mIoU (13-classes)	37.6	50.1	51.1

Data

Download GTA5.

Download SYNTHIA. Please use SYNTHIA-RAND-CITYSCAPES

Download Cityscapes.

Make sure the data path is consistent with the path in config file.

Training (TODO)

Stage 0: Training on the source domain data.

Run "run_so.py". The trained model is available at ...

Stage 1: Label denoising (both positive learning and negative learning).

Set method:"ld" in config/ldbe_config.yml. Then, run "run.py". The trained model is available at ...

Stage 2: Boundary enhancement

Set method:"be" in config/ldbe_config.yml. Then, run "run.py". The trained model is available at ...

Acknowledgement

https://github.com/Solacex/CCM

https://github.com/yzou2/CRST

Contact

[email protected]

Comments

Unable to Reproduce the LD Performance
Hello, I found that the codes in run.py:L19-L25 have fixed the random seeds. In this way, the training results of the same config are supposed to be consistent among different running experiments. However, during experiments, I found LD could not reach the 45.5% mIoU. Instead, it reported the results as:

[0.4074220657348633, 0.4311172068119049, 0.4302009344100952, 0.42955252528190613, 0.42495307326316833, 0.4027584195137024, 0.40802302956581116, 0.38000842928886414, 0.38050565123558044]

I am wondering if there exists any modification that affect the results?
opened by luoxin13 1

Code for ACM MM2021 paper "Complementary Trilateral Decoder for Fast and Accurate Salient Object Detection"

CTDNet The PyTorch code for ACM MM2021 paper "Complementary Trilateral Decoder for Fast and Accurate Salient Object Detection" Requirements Python 3.6

28 Oct 20, 2022

The code repository for "RCNet: Reverse Feature Pyramid and Cross-scale Shift Network for Object Detection" (ACM MM'21)

RCNet: Reverse Feature Pyramid and Cross-scale Shift Network for Object Detection (ACM MM'21) By Zhuofan Zong, Qianggang Cao, Biao Leng Introduction F

9 Jul 30, 2022

Bib-parser - Convenient script to parse .bib files with the ACM Digital Library like metadata

Bib Parser Convenient script to parse .bib files with the ACM Digital Library li

1 Jan 26, 2022

git git《Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Tracking》(CVPR 2021) GitHub:git2] 《Masksembles for Uncertainty Estimation》(CVPR 2021) GitHub:git3]

Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Tracking Ning Wang, Wengang Zhou, Jie Wang, and Houqiang Li Accepted by CVPR

236 Dec 22, 2022

Code of the lileonardo team for the 2021 Emotion and Theme Recognition in Music task of MediaEval 2021

Emotion and Theme Recognition in Music The repository contains code for the submission of the lileonardo team to the 2021 Emotion and Theme Recognitio

8 Aug 2, 2022

Implementation of Geometric Vector Perceptron, a simple circuit for 3d rotation equivariance for learning over large biomolecules, in Pytorch. Idea proposed and accepted at ICLR 2021

Geometric Vector Perceptron Implementation of Geometric Vector Perceptron, a simple circuit with 3d rotation equivariance for learning over large biom

59 Nov 24, 2022

[ICLR 2021] "Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective" by Wuyang Chen, Xinyu Gong, Zhangyang Wang

Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective [PDF] Wuyang Chen, Xinyu Gong, Zhangyang Wang In ICLR 2

156 Nov 28, 2022

The official implementation of NeMo: Neural Mesh Models of Contrastive Features for Robust 3D Pose Estimation [ICLR-2021]. https://arxiv.org/pdf/2101.12378.pdf

NeMo: Neural Mesh Models of Contrastive Features for Robust 3D Pose Estimation [ICLR-2021] Release Notes The offical PyTorch implementation of NeMo, p

76 Nov 23, 2022

This is the code for the paper "Contrastive Clustering" (AAAI 2021)

Contrastive Clustering (CC) This is the code for the paper "Contrastive Clustering" (AAAI 2021) Dependency python=3.7 pytorch=1.6.0 torchvision=0.8

210 Dec 30, 2022

"Domain Adaptive Semantic Segmentation without Source Data" (ACM MM 2021)

Related tags

Overview

LDBE

Method

Result

Data

Training (TODO)

Acknowledgement

Contact

You might also like...

Code for ACM MM2021 paper "Complementary Trilateral Decoder for Fast and Accurate Salient Object Detection"

The code repository for "RCNet: Reverse Feature Pyramid and Cross-scale Shift Network for Object Detection" (ACM MM'21)

Bib-parser - Convenient script to parse .bib files with the ACM Digital Library like metadata

git git《Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Tracking》(CVPR 2021) GitHub:git2] 《Masksembles for Uncertainty Estimation》(CVPR 2021) GitHub:git3]

Code of the lileonardo team for the 2021 Emotion and Theme Recognition in Music task of MediaEval 2021

Implementation of Geometric Vector Perceptron, a simple circuit for 3d rotation equivariance for learning over large biomolecules, in Pytorch. Idea proposed and accepted at ICLR 2021

[ICLR 2021] "Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective" by Wuyang Chen, Xinyu Gong, Zhangyang Wang

The official implementation of NeMo: Neural Mesh Models of Contrastive Features for Robust 3D Pose Estimation [ICLR-2021]. https://arxiv.org/pdf/2101.12378.pdf

This is the code for the paper "Contrastive Clustering" (AAAI 2021)

Comments

Unable to Reproduce the LD Performance

Owner

benfour

Edge-oriented Convolution Block for Real-time Super Resolution on Mobile Devices, ACM Multimedia 2021

[ACM MM 2021] Diverse Image Inpainting with Bidirectional and Autoregressive Transformers

Code of the paper "Deep Human Dynamics Prior" in ACM MM 2021.

[ACM MM 2021] Yes, "Attention is All You Need", for Exemplar based Colorization

How to Learn a Domain Adaptive Event Simulator? ACM MM, 2021

Code for ACM MM 2020 paper "NOH-NMS: Improving Pedestrian Detection by Nearby Objects Hallucination"

The official project of SimSwap (ACM MM 2020)

Official Implementation of DDOD (Disentangle your Dense Object Detector), ACM MM2021

DPT: Deformable Patch-based Transformer for Visual Recognition (ACM MM2021)

object detection; robust detection; ACM MM21 grand challenge; Security AI Challenger Phase VII