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

Last update: Nov 15, 2022

Related tags

Overview

Amodal Segmentation through Out-of-Task and Out-of-Distribution Generalization with a Bayesian Model

Quick Start: Setup environment / Download models and dataset

conda env create -f environment.yml
conda activate amodal
bash download.sh

In the case that download.sh cannot be executed properly, please identify the missing directory and rerun the wget command for the corresponding zip file. If the issue persists, please refer to the download.sh description below.

Run experiments

Table 1: change the file Code/configs.py to set TABLE_NUM = 1 and MODEL_TYPE = 'ML' or MODEL_TYPE = 'E2E' and run the command below.
Table 2: change the file Code/configs.py to set TABLE_NUM = 2 and MODEL_TYPE = 'ML' or MODEL_TYPE = 'E2E' and run the command below.
Table 3: change the file Code/configs.py to set TABLE_NUM = 3 and MODEL_TYPE = 'ML' or MODEL_TYPE = 'E2E' and run the command below.

cd Code
python3 run_experiment.py

Optional: `download.sh` Description

Download models

Download pretrained model weights from here, unzip Models.zip and place the folder as /Models/.
Download RPN results used for evaluatiooon from here, unzip RPN_results.zip and place the folder as /RPN_results/.

Download dataset

Download Occluded Vehicle Dataset from here, unzip Occluded_Vehicles.zip and place the folder as /Dataset/Occluded_Vehicles/.
Download KINS Dataset from here, unzip kitti.zip and place the folder as /Dataset/kitti/.
Download COCOA Dataset from here, unzip COCO.zip and place the folder as /Dataset/COCO/. Additionally, download COCO data train2014 and val2014 and place the folders as /Dataset/COCO/train2014/ and /Dataset/COCO/val2014/.

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

Related tags

Overview

Amodal Segmentation through Out-of-Task and Out-of-Distribution Generalization with a Bayesian Model

Quick Start: Setup environment / Download models and dataset

Run experiments

Optional: `download.sh` Description

Download models

Download dataset

Owner

Yihong Sun

Python Environment for Bayesian Learning

Paper Code：A Self-adaptive Weighted Differential Evolution Approach for Large-scale Feature Selection

A PyTorch implementation of unsupervised SimCSE

code and data for paper "GIANT: Scalable Creation of a Web-scale Ontology"

training script for space time memory network

Multiview 3D object detection on MultiviewC dataset through moft3d.

VIL-100: A New Dataset and A Baseline Model for Video Instance Lane Detection (ICCV 2021)

SparseInst: Sparse Instance Activation for Real-Time Instance Segmentation, CVPR 2022

The official implementation of the research paper "DAG Amendment for Inverse Control of Parametric Shapes"

Code for NeurIPS 2020 article "Contrastive learning of global and local features for medical image segmentation with limited annotations"

Our implementation used for the MICCAI 2021 FLARE Challenge titled 'Efficient Multi-Organ Segmentation Using SpatialConfiguartion-Net with Low GPU Memory Requirements'.

Attack on Confidence Estimation algorithm from the paper "Disrupting Deep Uncertainty Estimation Without Harming Accuracy"

SEAN: Image Synthesis with Semantic Region-Adaptive Normalization (CVPR 2020, Oral)

official implementation for the paper "Simplifying Graph Convolutional Networks"

Voice of Pajlada with model and weights.

Jittor is a high-performance deep learning framework based on JIT compiling and meta-operators.

The Malware Open-source Threat Intelligence Family dataset contains 3,095 disarmed PE malware samples from 454 families

Fake videos detection by tracing the source using video hashing retrieval.

Time series annotation library.

Implementation of "Large Steps in Inverse Rendering of Geometry"

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

Related tags

Overview

Amodal Segmentation through Out-of-Task and Out-of-Distribution Generalization with a Bayesian Model

Quick Start: Setup environment / Download models and dataset

Run experiments

Optional: download.sh Description

Download models

Download dataset

Owner

Yihong Sun

Python Environment for Bayesian Learning

Paper Code：A Self-adaptive Weighted Differential Evolution Approach for Large-scale Feature Selection

A PyTorch implementation of unsupervised SimCSE

code and data for paper "GIANT: Scalable Creation of a Web-scale Ontology"

training script for space time memory network

Multiview 3D object detection on MultiviewC dataset through moft3d.

VIL-100: A New Dataset and A Baseline Model for Video Instance Lane Detection (ICCV 2021)

SparseInst: Sparse Instance Activation for Real-Time Instance Segmentation, CVPR 2022

The official implementation of the research paper "DAG Amendment for Inverse Control of Parametric Shapes"

Code for NeurIPS 2020 article "Contrastive learning of global and local features for medical image segmentation with limited annotations"

Our implementation used for the MICCAI 2021 FLARE Challenge titled 'Efficient Multi-Organ Segmentation Using SpatialConfiguartion-Net with Low GPU Memory Requirements'.

Attack on Confidence Estimation algorithm from the paper "Disrupting Deep Uncertainty Estimation Without Harming Accuracy"

SEAN: Image Synthesis with Semantic Region-Adaptive Normalization (CVPR 2020, Oral)

official implementation for the paper "Simplifying Graph Convolutional Networks"

Voice of Pajlada with model and weights.

Jittor is a high-performance deep learning framework based on JIT compiling and meta-operators.

The Malware Open-source Threat Intelligence Family dataset contains 3,095 disarmed PE malware samples from 454 families

Fake videos detection by tracing the source using video hashing retrieval.

Time series annotation library.

Implementation of "Large Steps in Inverse Rendering of Geometry"

Optional: `download.sh` Description