Implementation of "Unsupervised Domain Adaptive 3D Detection with Multi-Level Consistency"

Last update: Nov 17, 2022

Related tags

Overview

Unsupervised Domain Adaptive 3D Detection with Multi-Level Consistency (ICCV2021)

Paper Link: https://arxiv.org/abs/2107.11355

This implementation builds on top of OpenPCDet. Please kindly refer to its Github repo for introduction and recent updates.

Installation

a. Set up the environment:

Python 3.6+ (3.7 suggested)
Pytorch 1.1+ (1.3 suggested)

b. Clone this repository.

c. Install requirements

pip install -r requirements.txt

d. Install the pcdet library:

python setup.py develop

e. Data preparation

Please refer to GETTING_STARTED.md for data preparation and basic usage of pcdet .

Training and Testing

a. Train a base model on the source domain (KITTI) as the pretrained model for domain adaptation

cd tools/

sh scripts/dist_train.sh ${NUM_GPUS} --cfg_file cfgs/kitti_models/pointrcnn.yaml

# or using slurm
sh scripts/slurm_train.sh ${PARTITION} ${JOB_NAME} ${NUM_GPUS} --cfg_file cfgs/kitti_models/pointrcnn.yaml

b. Train the domain adaptation model

sh scripts/dist_train_mean_teacher.sh ${NUM_GPUS} \
--cfg_file cfgs/kitti_models/pointrcnn_mean_teacher_waymo.yaml \
--pretrained_model ${PATH_TO_PRETRAINED_MODEL_CHECKPOINT}

# or using slurm
sh scripts/slurm_train_mean_teacher.sh ${PARTITION} ${JOB_NAME} ${NUM_GPUS} \
--cfg_file cfgs/kitti_models/pointrcnn_mean_teacher_waymo.yaml \
--pretrained_model ${PATH_TO_PRETRAINED_MODEL_CHECKPOINT}

c. Test on the target domain (Waymo)

python test.py --cfg_file cfgs/waymo_models/pointrcnn_kitti2waymo.yaml \
--ckpt ${PATH_TO_MODEL_CHECKPOINT}

Implementation of "Unsupervised Domain Adaptive 3D Detection with Multi-Level Consistency"

Related tags

Overview

Unsupervised Domain Adaptive 3D Detection with Multi-Level Consistency (ICCV2021)

Installation

Training and Testing

Owner

FCOSR: A Simple Anchor-free Rotated Detector for Aerial Object Detection

Official Pytorch Implementation of 'Learning Action Completeness from Points for Weakly-supervised Temporal Action Localization' (ICCV-21 Oral)

Team Enigma at ArgMining 2021 Shared Task: Leveraging Pretrained Language Models for Key Point Matching

Non-Metric Space Library (NMSLIB): An efficient similarity search library and a toolkit for evaluation of k-NN methods for generic non-metric spaces.

Benchmarking Pipeline for Prediction of Protein-Protein Interactions

TaCL: Improving BERT Pre-training with Token-aware Contrastive Learning

Implementation of CVPR'21: RfD-Net: Point Scene Understanding by Semantic Instance Reconstruction

Data-driven reduced order modeling for nonlinear dynamical systems

MAU: A Motion-Aware Unit for Video Prediction and Beyond, NeurIPS2021

Implementation for our ICCV2021 paper: Internal Video Inpainting by Implicit Long-range Propagation

Unified MultiWOZ evaluation scripts for the context-to-response task.

This is the official code for the paper "Ad2Attack: Adaptive Adversarial Attack for Real-Time UAV Tracking".

PyTorch Implementation of NCSOFT's FastPitchFormant: Source-filter based Decomposed Modeling for Speech Synthesis

PyTorch Live is an easy to use library of tools for creating on-device ML demos on Android and iOS.

A Python framework for conversational search

Code for Mesh Convolution Using a Learned Kernel Basis

Visualizer for neural network, deep learning, and machine learning models

Deploying PyTorch Model to Production with FastAPI in CUDA-supported Docker

MNE: Magnetoencephalography (MEG) and Electroencephalography (EEG) in Python

Doubly Robust Off-Policy Evaluation for Ranking Policies under the Cascade Behavior Model