A Weakly Supervised Amodal Segmenter with Boundary Uncertainty Estimation

Khoi Nguyen

Last update: Aug 14, 2022

Related tags

Deep Learning Amodal-Instance-Seg-ASBU

Overview

Paper

Khoi Nguyen, Sinisa Todorovic "A Weakly Supervised Amodal Segmenter with Boundary Uncertainty Estimation", accepted to ICCV 2021

Our code is mainly based on the code from the paper: Xiaohang Zhan, Xingang Pan, Bo Dai, Ziwei Liu, Dahua Lin, Chen Change Loy, "Self-Supervised Scene De-occlusion"

Requirements

pytorch>=0.4.1
```
pip install -r requirements.txt
```

Data Preparation

COCOA dataset proposed in Semantic Amodal Segmentation.

Download COCO2014 train and val images from here and unzip.
Download COCOA annotations from here and untar.

Ensure the COCOA folder looks like:

COCOA/
  |-- train2014/
  |-- val2014/
  |-- annotations/
    |-- COCO_amodal_train2014.json
    |-- COCO_amodal_val2014.json
    |-- COCO_amodal_test2014.json
    |-- ...

Create symbolic link:

cd deocclusion
mkdir data
cd data
ln -s /path/to/COCOA

KINS dataset proposed in Amodal Instance Segmentation with KINS Dataset.

Download left color images of object data in KITTI dataset from here and unzip.
Download KINS annotations from here corresponding to this commit.

Ensure the KINS folder looks like:

KINS/
  |-- training/image_2/
  |-- testing/image_2/
  |-- instances_train.json
  |-- instances_val.json

Create symbolic link:

cd deocclusion/data
ln -s /path/to/KINS

Train

train PCNet-M

Train (taking COCOA for example).
```
./train_pcnet_m_std_no_rgb_gaussian.sh
```
Monitoring status and visual results using tensorboard.
```
sh tensorboard.sh $PORT
```

Evaluate

Execute:
```
./test_pcnet_m.sh
```

Bibtex

@InProceedings{Nguyen_2021_ICCV,
    author    = {Nguyen, Khoi and Todorovic, Sinisa},
    title     = {A Weakly Supervised Amodal Segmenter With Boundary Uncertainty Estimation},
    booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
    month     = {October},
    year      = {2021},
    pages     = {7396-7405}
}

Acknowledgement

We developed our approach based on the code from https://github.com/XiaohangZhan/deocclusion/
We used the code and models of GCA-Matting in our demo.
We modified some code from pytorch-inpainting-with-partial-conv to train the PCNet-C.

You might also like...

Aerial Single-View Depth Completion with Image-Guided Uncertainty Estimation (RA-L/ICRA 2020)

Aerial Depth Completion This work is described in the letter "Aerial Single-View Depth Completion with Image-Guided Uncertainty Estimation", by Lucas

70 Dec 22, 2022

Estimating and Exploiting the Aleatoric Uncertainty in Surface Normal Estimation

95 Jan 4, 2023

Face uncertainty quantification or estimation using PyTorch.

Face-uncertainty-pytorch This is a demo code of face uncertainty quantification or estimation using PyTorch. The uncertainty of face recognition is af

3 Sep 16, 2022

Symmetry and Uncertainty-Aware Object SLAM for 6DoF Object Pose Estimation

SUO-SLAM This repository hosts the code for our CVPR 2022 paper "Symmetry and Uncertainty-Aware Object SLAM for 6DoF Object Pose Estimation". ArXiv li

Robot Perception & Navigation Group (RPNG)

97 Jan 3, 2023

noisy labels; missing labels; semi-supervised learning; entropy; uncertainty; robustness and generalisation.

ProSelfLC: CVPR 2021 ProSelfLC: Progressive Self Label Correction for Training Robust Deep Neural Networks For any specific discussion or potential fu

57 Dec 4, 2022

Data-Uncertainty Guided Multi-Phase Learning for Semi-supervised Object Detection

An official implementation of paper Data-Uncertainty Guided Multi-Phase Learning for Semi-supervised Object Detection

11 Nov 23, 2022

Weakly Supervised Learning of Rigid 3D Scene Flow

Weakly Supervised Learning of Rigid 3D Scene Flow This repository provides code and data to train and evaluate a weakly supervised method for rigid 3D

124 Dec 27, 2022

Leveraging Instance-, Image- and Dataset-Level Information for Weakly Supervised Instance Segmentation

Leveraging Instance-, Image- and Dataset-Level Information for Weakly Supervised Instance Segmentation This paper has been accepted and early accessed

39 Sep 20, 2022

A Comprehensive Analysis of Weakly-Supervised Semantic Segmentation in Different Image Domains (IJCV submission)

wsss-analysis The code of: A Comprehensive Analysis of Weakly-Supervised Semantic Segmentation in Different Image Domains, arXiv pre-print 2019 paper.

48 Dec 18, 2022

Comments

ModuleNotFoundError: No module named 'mmdet.ops'

Hello! The "mmdet" module which should be installed is not written in the "requirements.txt".And I install it but it occurs error that I can not solve it. Could you tell me what version of your "mmcv" and "mmdet" module? Thank you. The log: Traceback (most recent call last): File "main.py", line 9, in from trainer import Trainer File "/home/user15/Amodal-Instance-Seg-ASBU/trainer.py", line 12, in import models File "/home/user15/Amodal-Instance-Seg-ASBU/models/init.py", line 1, in from . import backbone File "/home/user15/Amodal-Instance-Seg-ASBU/models/backbone/init.py", line 1, in from .unet import * File "/home/user15/Amodal-Instance-Seg-ASBU/models/backbone/unet/init.py", line 1, in from .unet_model import * File "/home/user15/Amodal-Instance-Seg-ASBU/models/backbone/unet/unet_model.py", line 8, in from mmdet.ops.dcn.deform_conv import ModulatedDeformConvPack as Deform ModuleNotFoundError: No module named 'mmdet.ops' Killing subprocess 39673 Killing subprocess 39674 Traceback (most recent call last): File "/home/user15/anaconda3/envs/occlusion/lib/python3.7/runpy.py", line 193, in _run_module_as_main "main", mod_spec) File "/home/user15/anaconda3/envs/occlusion/lib/python3.7/runpy.py", line 85, in _run_code exec(code, run_globals) File "/home/user15/anaconda3/envs/occlusion/lib/python3.7/site-packages/torch/distributed/launch.py", line 340, in main() File "/home/user15/anaconda3/envs/occlusion/lib/python3.7/site-packages/torch/distributed/launch.py", line 326, in main sigkill_handler(signal.SIGTERM, None) # not coming back File "/home/user15/anaconda3/envs/occlusion/lib/python3.7/site-packages/torch/distributed/launch.py", line 301, in sigkill_handler raise subprocess.CalledProcessError(returncode=last_return_code, cmd=cmd) subprocess.CalledProcessError: Command '['/home/user15/anaconda3/envs/occlusion/bin/python', '-u', 'main.py', '--local_rank=1', '--config', 'experiments/KINS/pcnet_m/config_train_default_no_rgb.yaml', '--launcher', 'pytorch', '--exp_path', 'experiments/KINS/pcnet_m_default_no_rgb']' returned non-zero exit status 1.

opened by landian60 1
Reproduce results in your paper

Hello! Thanks for your wonderful work.

I have trained your model following the github instructions ./train_pcnet_m_std_no_rgb_gaussian.sh, and tried to calculate the mIOU results on COCOA-test using your code. But I got 88.41 rather than 89.87 as you stated in your paper. Could you please let me know how to get that result? Is it correct for me to use ./train_pcnet_m_std_no_rgb_gaussian.sh which uses the config file of config_train_std_no_rgb_gaussian.yaml?

opened by Championchess 0

A Weakly Supervised Amodal Segmenter with Boundary Uncertainty Estimation

Related tags

Overview

Paper

Requirements

Data Preparation

COCOA dataset proposed in Semantic Amodal Segmentation.

KINS dataset proposed in Amodal Instance Segmentation with KINS Dataset.

Train

train PCNet-M

Evaluate

Bibtex

Acknowledgement

You might also like...

Aerial Single-View Depth Completion with Image-Guided Uncertainty Estimation (RA-L/ICRA 2020)

Estimating and Exploiting the Aleatoric Uncertainty in Surface Normal Estimation

Face uncertainty quantification or estimation using PyTorch.

Symmetry and Uncertainty-Aware Object SLAM for 6DoF Object Pose Estimation

noisy labels; missing labels; semi-supervised learning; entropy; uncertainty; robustness and generalisation.

Data-Uncertainty Guided Multi-Phase Learning for Semi-supervised Object Detection

Weakly Supervised Learning of Rigid 3D Scene Flow

Leveraging Instance-, Image- and Dataset-Level Information for Weakly Supervised Instance Segmentation

A Comprehensive Analysis of Weakly-Supervised Semantic Segmentation in Different Image Domains (IJCV submission)

Comments

ModuleNotFoundError: No module named 'mmdet.ops'

Reproduce results in your paper

Owner

Khoi Nguyen

Codes of paper "Unseen Object Amodal Instance Segmentation via Hierarchical Occlusion Modeling"

Codebase for Amodal Segmentation through Out-of-Task andOut-of-Distribution Generalization with a Bayesian Model

Finding an Unsupervised Image Segmenter in each of your Deep Generative Models

Official PyTorch implementation of Segmenter: Transformer for Semantic Segmentation

"Segmenter: Transformer for Semantic Segmentation" reproduced via mmsegmentation

The official implementation of the CVPR 2021 paper FAPIS: a Few-shot Anchor-free Part-based Instance Segmenter

Hybrid CenterNet - Hybrid-supervised object detection / Weakly semi-supervised object detection

Re-implementation of the Noise Contrastive Estimation algorithm for pyTorch, following "Noise-contrastive estimation: A new estimation principle for unnormalized statistical models." (Gutmann and Hyvarinen, AISTATS 2010)

An official PyTorch Implementation of Boundary-aware Self-supervised Learning for Video Scene Segmentation (BaSSL)

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