This is the official implementation of 3D-CVF: Generating Joint Camera and LiDAR Features Using Cross-View Spatial Feature Fusion for 3D Object Detection, built on SECOND.
Follow the installation steps in SECOND, or use the docker image we provide.
docker pull yckimm/second:second_v1.5
sh train_bash_1st.sh
sh train_bash_2nd.sh
Thanks to the SECOND codebase maintained by traveller59.
Data-Efficient GANs with DiffAugment project | paper | datasets | video | slides Generated using only 100 images of Obama, grumpy cats, pandas, the Br
Narya The Narya API allows you track soccer player from camera inputs, and evaluate them with an Expected Discounted Goal (EDG) Agent. This repository
Unsupervised Image Captioning by Yang Feng, Lin Ma, Wei Liu, and Jiebo Luo Introduction Most image captioning models are trained using paired image-se
Code-and-Dataset-for-CapSal This project provides the code and datasets for 'CapSal: Leveraging Captioning to Boost Semantics for Salient Object Detec
This repo holds the code for our weak supervision framework, ASTRA, described in our NAACL 2021 paper: "Self-Training with Weak Supervision"
RepMLP: Re-parameterizing Convolutions into Fully-connected Layers for Image Recognition (PyTorch) Paper: https://arxiv.org/abs/2105.01883 Citation: @
You are caught stealing my winning lottery ticket! Making a lottery ticket claim its ownership Codes for [NeurIPS'21] You are caught stealing my winni
PEDPF Parameter Efficient Deep Probabilistic Forecasting (PEDPF) is a repository containing code to run experiments for several deep learning based pr
Introduction 1. Usage (For MSS) 1.1 Prepare running environment 1.2 Use pretrained model 1.3 Train new MSS models from scratch 1.3.1 How to train 1.3.
An implementation of the methods presented in Causal-BALD: Deep Bayesian Active Learning of Outcomes to Infer Treatment-Effects from Observational Data.
NesT is a simple method, which aggragrates nested local transformers on image blocks. The idea makes vision transformers attain better accuracy, data efficiency, and convergence on the ImageNet bench
Accelerated deep learning R&D PyTorch framework for Deep Learning research and development. It focuses on reproducibility, rapid experimentation, and
WarpDrive is a flexible, lightweight, and easy-to-use open-source reinforcement learning (RL) framework that implements end-to-end multi-agent RL on a single GPU (Graphics Processing Unit).
DeepCreamPy Decensoring Hentai with Deep Neural Networks. Formerly named DeepMindBreak. A deep learning-based tool to automatically replace censored a
Kaggle Feedback Prize - Evaluating Student Writing 15th solution First of all, I would like to thank the excellent notebooks and discussions from http
ihoneyBakFileScan_Modify 批量网站备份文件泄露扫描工具 2022.2.8 添加、修改内容 增加备份文件fuzz规则 修改备份文件大小判断
Finetune SSL models for MOS prediction This is code for our paper under review for ICASSP 2022: "Generalization Ability of MOS Prediction Networks" Er
The accompanying codes reproduce all figures and statistics presented in "Controlling for multiple covariates" by Mark Tygert. This repository also pr
SPTAG: A library for fast approximate nearest neighbor search SPTAG SPTAG (Space Partition Tree And Graph) is a library for large scale vector approxi
Model Zoo of BDD100K Dataset
1.2k Dec 26, 2022
121 Dec 30, 2022
207 Dec 24, 2022
48 Aug 19, 2022
148 Nov 20, 2022
260 Jan 03, 2023
8 Nov 01, 2022
10 Jun 13, 2022
100 Dec 25, 2022
9 Apr 04, 2022
169 Dec 20, 2022
3.1k Jan 06, 2023
334 Jan 06, 2023
616 Jan 06, 2023
6 Mar 24, 2022
220 Jan 05, 2023
32 Nov 22, 2022
1 Dec 02, 2021
200 Dec 27, 2022