Official implementation for the paper "Attentive Prototypes for Source-free Unsupervised Domain Adaptive 3D Object Detection"

Last update: Oct 17, 2022

Related tags

Deep Learning AttentivePrototypeSFUDA

Overview

Attentive Prototypes for Source-free Unsupervised Domain Adaptive 3D Object Detection

PyTorch code release of the paper "Attentive Prototypes for Source-free Unsupervised Domain Adaptive 3D Object Detection",

by Deepti Hegde, Vishal M. Patel

(Currently has instructions for model inference and evaluation only, training steps to be updated soon.)

Follow the instructions for installation and implementation of the method for each base object detection network in the respective folders SECOND-iou and PointRCNN

Dataset preperation

Download the relevant datasets: KITTI , Waymo , nuScenes
Organize each folder inside data like the following

AttentivePrototypeSFUDA

├── data (main data folder)
│   ├── kitti
│   │   │── ImageSets
│   │   │── training
│   │   │   ├──calib & velodyne & label_2 & image_2 & (optional: planes)
│   │   │── testing
│   │   │   ├──calib & velodyne & image_2
|
|
│   ├── nuscenes
│   │   │── v1.0-trainval (or v1.0-mini if you use mini)
│   │   │   │── samples
│   │   │   │── sweeps
│   │   │   │── maps
│   │   │   │── v1.0-trainval  
|
|
│   ├── waymo
│   │   │── ImageSets
│   │   │── raw_data
│   │   │   │── segment-xxxxxxxx.tfrecord
|   |   |   |── ...
|   |   |── waymo_processed_data
│   │   │   │── segment-xxxxxxxx/
|   |   |   |── ...
│   │   │── pcdet_gt_database_train_sampled_xx/
│   │   │── pcdet_waymo_dbinfos_train_sampled_xx.pkl  
|
|
├── PointRCNN
|   ├── data (link to main data folder)
|   ├── pointrcnn_attention
├── SECOND-iou
|   ├── data (link to main data folder)
|   ├── pcdet
|   ├── tools

We implement the proposed method for two object detectors, SECOND-iou and PointRCNN for several domain shift scenarios. You can find the folder of pretrained models here. Find specific model downloads and their corresponding config files below.

| SECOND-iou |

Domain shift	Model file	Configuration file
Waymo -> KITTI	download	link
Waymo -> nuScenes	download	link
nuScenes -> KITTI	download	link

| PointRCNN |

Domain shift	Model file	Configuration file
Waymo -> KITTI	download	link
KITTI -> nuScenes	download	link
nuScenes -> KITTI	download	link

Follow the instructions to implement the method in the folders SECOND-iou and PointRCNN

Official implementation for the paper "Attentive Prototypes for Source-free Unsupervised Domain Adaptive 3D Object Detection"

Related tags

Overview

Attentive Prototypes for Source-free Unsupervised Domain Adaptive 3D Object Detection

Dataset preperation

| SECOND-iou |

| PointRCNN |

Owner

Deepti Hegde

Sequence-tagging using deep learning

Code for the paper: Audio-Visual Scene Analysis with Self-Supervised Multisensory Features

Pseudo-mask Matters in Weakly-supervised Semantic Segmentation

Paddle Graph Learning (PGL) is an efficient and flexible graph learning framework based on PaddlePaddle

Little tool in python to watch anime from the terminal (the better way to watch anime)

Spectrum Surveying: Active Radio Map Estimation with Autonomous UAVs

The materials used in the SaxonJS tutorial presented at Declarative Amsterdam, 2021

Scalable, event-driven, deep-learning-friendly backtesting library

SafePicking: Learning Safe Object Extraction via Object-Level Mapping, ICRA 2022

A state of the art of new lightweight YOLO model implemented by TensorFlow 2.

MacroTools provides a library of tools for working with Julia code and expressions.

这是一个mobilenet-yolov4-lite的库，把yolov4主干网络修改成了mobilenet，修改了Panet的卷积组成，使参数量大幅度缩小。

PyTorch Implement for Path Attention Graph Network

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

This is Unofficial Repo. Lips Don't Lie: A Generalisable and Robust Approach to Face Forgery Detection (CVPR 2021)

Relative Human dataset, CVPR 2022

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

This repository contains the entire code for our work "Two-Timescale End-to-End Learning for Channel Acquisition and Hybrid Precoding"

Code for 'Single Image 3D Shape Retrieval via Cross-Modal Instance and Category Contrastive Learning', ICCV 2021

Robot Reinforcement Learning on the Constraint Manifold