PrimitiveNet: Primitive Instance Segmentation with Local Primitive Embedding under Adversarial Metric (ICCV 2021)

Last update: Dec 06, 2022

Related tags

Overview

PrimitiveNet

Source code for the paper:

Jingwei Huang, Yanfeng Zhang, Mingwei Sun. [PrimitiveNet: Primitive Instance Segmentation with Local Primitive Embedding under Adversarial Metric], ICCV 2021 .

Compile

git submodule update --init --recursive
sh scripts/compile.sh

Download data and checkpoints

Follow the comments in download.sh to download the data and checkpoints.

sh scripts/download.sh

Evaluation on ABC

sh scripts/evaluate.sh

Predicted results on test set are visualized in src/results/visualize. Original network predictions are saved in src/results/predictions.

After all test set predictions are generated, an evaluation for mSegIOU/mLabelIOU/APs will be executed and final results will be saved at src/results/statistics.

Train ABC from scratch

sh scripts/train.sh

Logs and trained models will be saved at src/results/checkpoint.

Execute on a large scene

sh scripts/test_scene.sh

The segmented large scene is stored at src/results/visualize/final.obj.

PrimitiveNet: Primitive Instance Segmentation with Local Primitive Embedding under Adversarial Metric (ICCV 2021)

Related tags

Overview

PrimitiveNet

Compile

Download data and checkpoints

Evaluation on ABC

Train ABC from scratch

Execute on a large scene

Owner

Jingwei Huang

Dogs classification with Deep Metric Learning using some popular losses

FairFuzz: AFL extension targeting rare branches

An Implementation of Fully Convolutional Networks in Tensorflow.

[AAAI 2022] Separate Contrastive Learning for Organs-at-Risk and Gross-Tumor-Volume Segmentation with Limited Annotation

ICNet and PSPNet-50 in Tensorflow for real-time semantic segmentation

Parameter-ensemble-differential-evolution - Shows how to do parameter ensembling using differential evolution.

Implementation of fast algorithms for Maximum Spanning Tree (MST) parsing that includes fast ArcMax+Reweighting+Tarjan algorithm for single-root dependency parsing.

Practical and Real-world applications of ML based on the homework of Hung-yi Lee Machine Learning Course 2021

GLANet - The code for Global and Local Alignment Networks for Unpaired Image-to-Image Translation arxiv

Self-supervised Deep LiDAR Odometry for Robotic Applications

Code for the paper: Learning Adversarially Robust Representations via Worst-Case Mutual Information Maximization (https://arxiv.org/abs/2002.11798)

Lava-DL, but with PyTorch-Lightning flavour

Converting CPT to bert form for use

Official implementation for “Unsupervised Low-Light Image Enhancement via Histogram Equalization Prior”

Transformer - Transformer in PyTorch

Code-free deep segmentation for computational pathology

Character Controllers using Motion VAEs

DaReCzech is a dataset for text relevance ranking in Czech

a Lightweight library for sequential learning agents, including reinforcement learning

Fully Adaptive Bayesian Algorithm for Data Analysis (FABADA) is a new approach of noise reduction methods. In this repository is shown the package developed for this new method based on \citepaper.