首页/论文/2008.09164

arXiv 2008.091642020-08-20cs.CVcs.LG

PyTorch Metric Learning

Cornell Tech（康奈尔科技学院）；Facebook AI（Facebook 人工智能研究院）

Kevin Musgrave, Serge Belongie, Ser-Nam Lim

备注：: Code and documentation is available at https://www.github.com/KevinMusgrave/pytorch-metric-learning

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

英文摘要相关论文

英文摘要：

Deep metric learning algorithms have a wide variety of applications, but implementing these algorithms can be tedious and time consuming. PyTorch Metric Learning is an open source library that aims to remove this barrier for both researchers and practitioners. The modular and flexible design allows users to easily try out different combinations of algorithms in their existing code. It also comes with complete train/test workflows, for users who want results fast. Code and documentation is available at https://www.github.com/KevinMusgrave/pytorch-metric-learning.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

PyTorch Image Quality: Metrics for Image Quality Assessment

Skolkovo Institute of Science and Technology（斯科尔科沃科学技术研究院）；King’s College London（伦敦国王学院）

Image Quality Assessment (IQA) metrics are widely used to quantitatively estimate the extent of image degradation following some forming, restoring, transforming, or enhancing algorithms. We present PyTorch Image Quality (PIQ), a usability-centric library that contains the most popular modern IQA algorithms, guaranteed to be correctly implemented according to their original propositions and thoroughly verified. In this paper, we detail the principles behind the foundation of the library, describe the evaluation strategy that makes it reliable, provide the benchmarks that showcase the performan…

2022-08-31cs.CVeess.IV

TorchGAN: A Flexible Framework for GAN Training and Evaluation

Indian Institute of Technology Kanpur（印度理工学院坎普尔分校）

TorchGAN is a PyTorch based framework for writing succinct and comprehensible code for training and evaluation of Generative Adversarial Networks. The framework's modular design allows effortless customization of the model architecture, loss functions, training paradigms, and evaluation metrics. The key features of TorchGAN are its extensibility, built-in support for a large number of popular models, losses and evaluation metrics, and zero overhead compared to vanilla PyTorch. By using the framework to implement several popular GAN models, we demonstrate its extensibility and ease of use. We a…

2019-09-08cs.CVcs.LGstat.ML

Torchbearer: A Model Fitting Library for PyTorch

University of Southampton（南安普顿大学）

We introduce torchbearer, a model fitting library for pytorch aimed at researchers working on deep learning or differentiable programming. The torchbearer library provides a high level metric and callback API that can be used for a wide range of applications. We also include a series of built in callbacks that can be used for: model persistence, learning rate decay, logging, data visualization and more. The extensive documentation includes an example library for deep learning and dynamic programming problems and can be found at http://torchbearer.readthedocs.io. The code is licensed under the …

2018-09-10cs.AIcs.CVcs.LG

A Comparison of Metric Learning Loss Functions for End-To-End Speaker Verification

Université Paris-Saclay（巴黎-萨克雷大学）；CNRS（法国国家科学研究中心）；LIMSI（机械与工程计算机科学实验室）

Despite the growing popularity of metric learning approaches, very little work has attempted to perform a fair comparison of these techniques for speaker verification. We try to fill this gap and compare several metric learning loss functions in a systematic manner on the VoxCeleb dataset. The first family of loss functions is derived from the cross entropy loss (usually used for supervised classification) and includes the congenerous cosine loss, the additive angular margin loss, and the center loss. The second family of loss functions focuses on the similarity between training samples and in…

2020-03-31cs.LGcs.SDeess.AS

Kaolin: A PyTorch Library for Accelerating 3D Deep Learning Research

NVIDIA（英伟达）；Mila（米拉研究所）；McGill University（麦吉尔大学）；Vector Institute（向量研究所）；University of Toronto（多伦多大学）；Université de Montréal（蒙特利尔大学）

We present Kaolin, a PyTorch library aiming to accelerate 3D deep learning research. Kaolin provides efficient implementations of differentiable 3D modules for use in deep learning systems. With functionality to load and preprocess several popular 3D datasets, and native functions to manipulate meshes, pointclouds, signed distance functions, and voxel grids, Kaolin mitigates the need to write wasteful boilerplate code. Kaolin packages together several differentiable graphics modules including rendering, lighting, shading, and view warping. Kaolin also supports an array of loss functions and ev…

2019-11-13cs.CVcs.LGcs.RO

All's well that FID's well? Result quality and metric scores in GAN models for lip-sychronization tasks

Lund University（隆德大学）

We test the performance of GAN models for lip-synchronization. For this, we reimplement LipGAN in Pytorch, train it on the dataset GRID and compare it to our own variation, L1WGAN-GP, adapted to the LipGAN architecture and also trained on GRID.

2022-12-28cs.CVstat.ML

更多相关论文收起更多论文

Face.evoLVe: A High-Performance Face Recognition Library

Baidu Research（百度研究院）；National University of Defense Technology（国防科技大学）；Institute of North Electronic Equipment（北方电子设备研究所）

In this paper, we develop face.evoLVe -- a comprehensive library that collects and implements a wide range of popular deep learning-based methods for face recognition. First of all, face.evoLVe is composed of key components that cover the full process of face analytics, including face alignment, data processing, various backbones, losses, and alternatives with bags of tricks for improving performance. Later, face.evoLVe supports multi-GPU training on top of different deep learning platforms, such as PyTorch and PaddlePaddle, which facilitates researchers to work on both large-scale datasets wi…

2022-05-05cs.AIcs.CVcs.MM

FaceX-Zoo: A PyTorch Toolbox for Face Recognition

JD AI Research（京东人工智能研究院）

Deep learning based face recognition has achieved significant progress in recent years. Yet, the practical model production and further research of deep face recognition are in great need of corresponding public support. For example, the production of face representation network desires a modular training scheme to consider the proper choice from various candidates of state-of-the-art backbone and training supervision subject to the real-world face recognition demand; for performance analysis and comparison, the standard and automatic evaluation with a bunch of models on multiple benchmarks wi…

2021-10-17cs.CV

Revisiting Training Strategies and Generalization Performance in Deep Metric Learning

Mila, Université de Montréal（蒙特利尔大学 Mila 研究院）；HCI/IWR, Heidelberg University（海德堡大学 HCI/IWR）；University of Toronto（多伦多大学）；The Alan Turing Institute, University of Oxford（牛津大学艾伦·图灵研究所）

Deep Metric Learning (DML) is arguably one of the most influential lines of research for learning visual similarities with many proposed approaches every year. Although the field benefits from the rapid progress, the divergence in training protocols, architectures, and parameter choices make an unbiased comparison difficult. To provide a consistent reference point, we revisit the most widely used DML objective functions and conduct a study of the crucial parameter choices as well as the commonly neglected mini-batch sampling process. Under consistent comparison, DML objectives show much higher…

2020-08-01cs.CV

Self-distillation with Online Diffusion on Batch Manifolds Improves Deep Metric Learning

The University of Tokyo（东京大学）；National Institute of Informatics（国立信息学研究所）

Recent deep metric learning (DML) methods typically leverage solely class labels to keep positive samples far away from negative ones. However, this type of method normally ignores the crucial knowledge hidden in the data (e.g., intra-class information variation), which is harmful to the generalization of the trained model. To alleviate this problem, in this paper we propose Online Batch Diffusion-based Self-Distillation (OBD-SD) for DML. Specifically, we first propose a simple but effective Progressive Self-Distillation (PSD), which distills the knowledge progressively from the model itself d…

2022-11-14cs.CV

急切模式下的捆绑调整

Bundle Adjustment in the Eager Mode

Spatial AI & Robotics (SAIR) Lab, University at Buffalo（空间人工智能与机器人实验室，布法罗大学）；Georgia Institute of Technology（佐治亚理工学院）；Purdue University（普渡大学）；Carnegie Mellon University（卡内基梅隆大学）

本文提出了一种与PyTorch无缝集成的高效急切模式捆绑调整库，通过稀疏感知的自动微分设计和GPU加速的稀疏运算，提升了在机器人应用中捆绑调整的运行效率和性能。

2026-05-18cs.CVcs.RO

PyGAD: An Intuitive Genetic Algorithm Python Library

University of Ottawa（渥太华大学）

This paper introduces PyGAD, an open-source easy-to-use Python library for building the genetic algorithm. PyGAD supports a wide range of parameters to give the user control over everything in its life cycle. This includes, but is not limited to, population, gene value range, gene data type, parent selection, crossover, and mutation. PyGAD is designed as a general-purpose optimization library that allows the user to customize the fitness function. Its usage consists of 3 main steps: build the fitness function, create an instance of the pygad.GA class, and calling the pygad.GA.run() method. The…

2021-06-11cs.CVcs.LGcs.NE

图像识别中深度学习框架转换错误的故障定位

Fault Localization for Buggy Deep Learning Framework Conversions in Image Recognition

University of Edinburgh（爱丁堡大学）；University of Glasgow（格拉斯哥大学）

本文针对深度学习框架转换易出错的问题，提出了一种基于转换工具、参数、超参数和图表示四阶段分析的故障定位与修复方法，并在 Apache TVM 上成功检测并修复了 InceptionV3 模型转换中的精度误差，将转换错误降至零。

2024-03-25cs.CVcs.LGcs.SE