Articles About Machine Learning

SinNeRF: Training Neural Radiance Fields on Complex Scenes from a Single Image

pip install -r requirements.txt python eval.py –dataset_name llff –root_dir /dataset/nerf_llff_data/room –N_importance 64 –img_wh 504 378 –model nerf –ckpt_path room.ckpt –timestamp test Refactoring in progress. @InProceedings{Xu_2022_SinNeRF, author = {Xu, Dejia and Jiang, Yifan and Wang, Peihao and Fan, Zhiwen and Shi, Humphrey and Wang, Zhangyang}, title = {SinNeRF: Training Neural Radiance Fields on Complex Scenes from a Single Image}, journal={arXiv preprint arXiv:2204.00928},    

Read more

Colar: Effective and Efficient Online Action Detection by Consulting Exemplars, CVPR 2022

This repository is the official implementation of Colar. In this work, we study the online action detection and develop an effective and efficient exemplar-consultation mechanism. Paper from arXiv. Requirements To install requirements: conda env create -n env_name -f environment.yaml Before running the code, please activate this conda environment. Data Preparation a. Download pre-extracted features from baiduyun (code:cola) Please ensure the data structure is as below ├── data └── thumos14    

Read more

Dynamic MLP for Fine-Grained Image Classification by Leveraging Geographical and Temporal Information

Dynamic MLP, which is parameterized by the learned embeddings of variable locations and dates to help fine-grained image classification. Requirements Experiment Environment python 3.6 pytorch 1.7.1+cu101 torchvision 0.8.2 Get pretrained models for SK-Res2Net following here.Get datasets following here. Train the model 1. Train image-only model Specify –image_only for training image-only models. ResNet-50 (67.924% Top-1 acc) CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 python3 train.py –name res50_image_only –

Read more

BatchFormer: Learning to Explore Sample Relationships for Robust Representation Learning

All Codes in the paper will be coming soon. Here is the Pytorch Code of BatchFormer def BatchFormer(x, y, encoder, is_training): # x: input features with the shape [N, C] # encoder: TransformerEncoderLayer(C,4,C,0.5) if not is_training: return x, y pre_x = x x = encoder(x.unsqueeze(1)).squeeze(1) x = torch.cat([pre_x, x], dim=0) y = torch.cat([y, y], dim=0) return x, y If you find this repository helpful, please consider cite:

Read more

Quality Assurance for AI

Backend Requirements Frontend Requirements Backend local development Start the stack with Docker Compose: Now you can open your browser and interact with these URLs: Frontend, built with Docker, with routes handled based on the path: http://localhost Backend, JSON based web API based on OpenAPI: http://localhost/api/ Automatic interactive documentation with Swagger UI (from the OpenAPI backend): http://localhost/docs Alternative automatic documentation with ReDoc (from the OpenAPI backend): http://localhost/redoc PGAdmin, PostgreSQL web administration: http://localhost:5050 Note: you can disable (comment) this component in the […]

Read more

Breaching privacy in federated learning scenarios for vision and text

This PyTorch framework implements a number of gradient inversion attacks that breach privacy in federated learning scenarios,covering examples with small and large aggregation sizes and examples both vision and text domains. This includes implementations of recent work such as: But also a range of implementations of other attacks from optimization attacks (such as “Inverting Gradients” and “See through Gradients”) to recent analytic and recursive attacks. Jupyter notebook examples for these attacks can be found in the examples/ folder. Overview: This […]

Read more

Learning Signed Distance Field for Multi-view Surface Reconstruction

This is the official implementation for the ICCV 2021 paper Learning Signed Distance Field for Multi-view Surface Reconstruction In this work, we introduce a novel neural surface reconstruction framework that leverages the knowledge of stereo matching and feature consistency to optimize the implicit surface representation. More specifically, we apply a signed distance field (SDF) and a surface light field to represent the scene geometry and appearance respectively. The SDF is directly supervised by geometry from stereo matching, and is refined […]

Read more

FAMIE: A Fast Active Learning Framework for Multilingual Information Extraction

FAMIE: A Fast Active Learning Framework for Multilingual Information Extraction FAMIE is a comprehensive and efficient active learning (AL) toolkit for multilingual information extraction (IE). FAMIE is designed to address a fundamental problem in existing AL frameworks where annotators need to wait for a long time between annotation batches due to the time-consuming nature of model training and data selection at each AL iteration. With a novel proxy AL mechanism and the integration of our SOTA multilingual toolkit Trankit, FAMIE […]

Read more

Point-Set Registrations for Ultrasound Probe Calibrations

-Undergraduate Thesis-Updated January 25, 2022 Author: Matteo Tanzi Year: 2022 Purpose: Undergraduate Thesis Currently, algorithms for point-based, line-based and dynamic registrations are being developped to be ported into 3D Slicer as modules Github Repository Structure This github repository contains Jupyter Notebooks and Python Programs The Python Programs are found within the programs folder – descriptions can be found below The Jupyter Notebooks – Found within Documentation – will outline the research and development techniques used for the point-set registration programs, […]

Read more

Call of Duty World League: Search & Destroy Outcome Predictions

Growing up as an avid Call of Duty player, I was always curious about what factors led to a team winning or losing a match. Was it strictly based on the number of kills each player obtained? Was it who played the objective more? Or was it something different? Finally, after years of waiting, I decided that it was time to find my answers. Coupling my love for Call of Duty and my passion for data science, I began to […]

Read more
1 2 3 185