中文
相关论文

相关论文: Decomposition-Based Transfer Distance Metric Learn…

200 篇论文

Transfer learning is a critical technique in training deep neural networks for the challenging medical image segmentation task that requires enormous resources. With the abundance of medical image data, many research institutions release…

计算机视觉与模式识别 · 计算机科学 2023-07-25 Yuncheng Yang , Meng Wei , Junjun He , Jie Yang , Jin Ye , Yun Gu

Deep Metric Learning (DML) methods aim at learning an embedding space in which distances are closely related to the inherent semantic similarity of the inputs. Previous studies have shown that popular benchmark datasets often contain…

计算机视觉与模式识别 · 计算机科学 2023-11-02 Oriol Barbany , Xiaofan Lin , Muhammet Bastan , Arnab Dhua

The goal of domain generalization is to learn from multiple source domains to generalize to unseen target domains under distribution discrepancy. Current state-of-the-art methods in this area are fully supervised, but for many real-world…

机器学习 · 计算机科学 2020-10-01 Hossein Sharifi-Noghabi , Hossein Asghari , Nazanin Mehrasa , Martin Ester

Multi-task learning (MTL) aims to improve the generalization of several related tasks by learning them jointly. As a comparison, in addition to the joint training scheme, modern meta-learning allows unseen tasks with limited labels during…

机器学习 · 计算机科学 2021-06-17 Haoxiang Wang , Han Zhao , Bo Li

Distance metric learning based on triplet loss has been applied with success in a wide range of applications such as face recognition, image retrieval, speaker change detection and recently recommendation with the CML model. However, as we…

信息检索 · 计算机科学 2019-09-25 Viet-Anh Tran , Romain Hennequin , Jimena Royo-Letelier , Manuel Moussallam

Transfer learning is widely used for training deep neural networks (DNN) for building a powerful representation. Even after the pre-trained model is adapted for the target task, the representation performance of the feature extractor is…

机器学习 · 计算机科学 2023-08-22 Seunghee Koh , Hyounguk Shon , Janghyeon Lee , Hyeong Gwon Hong , Junmo Kim

Knowledge transfer from large teacher models to smaller student models has recently been studied for metric learning, focusing on fine-grained classification. In this work, focusing on instance-level image retrieval, we study an asymmetric…

计算机视觉与模式识别 · 计算机科学 2020-07-01 Mateusz Budnik , Yannis Avrithis

Transfer learning aims to improve the performance of a target model by leveraging data from related source populations, which is known to be especially helpful in cases with insufficient target data. In this paper, we study the problem of…

统计方法学 · 统计学 2025-02-19 Tian Gu , Yi Han , Rui Duan

Multi-task learning has recently emerged as a promising solution for a comprehensive understanding of complex scenes. In addition to being memory-efficient, multi-task models, when appropriately designed, can facilitate the exchange of…

计算机视觉与模式识别 · 计算机科学 2024-10-10 Ivan Lopes , Tuan-Hung Vu , Raoul de Charette

Most deep metric learning (DML) methods employ a strategy that forces all positive samples to be close in the embedding space while keeping them away from negative ones. However, such a strategy ignores the internal relationships of…

计算机视觉与模式识别 · 计算机科学 2022-06-20 Zelong Zeng , Fan Yang , Zheng Wang , Shin'ichi Satoh

In this paper, we propose Domain Agnostic Meta Score-based Learning (DAMSL), a novel, versatile and highly effective solution that delivers significant out-performance over state-of-the-art methods for cross-domain few-shot learning. We…

机器学习 · 计算机科学 2021-06-08 John Cai , Bill Cai , Shengmei Shen

Multi-view image compression plays a critical role in 3D-related applications. Existing methods adopt a predictive coding architecture, which requires joint encoding to compress the corresponding disparity as well as residual information.…

图像与视频处理 · 电气工程与系统科学 2023-04-13 Xinjie Zhang , Jiawei Shao , Jun Zhang

We consider Heterogeneous Transfer Learning (HTL) from a source to a new target domain for high-dimensional regression with differing feature sets. Most homogeneous TL methods assume that target and source domains share the same feature…

机器学习 · 统计学 2025-12-02 Jae Ho Chang , Massimiliano Russo , Subhadeep Paul

Deep metric learning applied to various applications has shown promising results in identification, retrieval and recognition. Existing methods often do not consider different granularity in visual similarity. However, in many domain…

计算机视觉与模式识别 · 计算机科学 2021-05-17 Dipu Manandhar , Muhammet Bastan , Kim-Hui Yap

We present a novel approach, in which we learn to cluster data directly from side information, in the form of a small set of pairwise examples. Unlike previous methods, with or without side information, we do not need to know the number of…

机器学习 · 计算机科学 2023-05-31 Michael A. Hobley , Victor A. Prisacariu

Distance-based supervised method, the minimal learning machine, constructs a predictive model from data by learning a mapping between input and output distance matrices. In this paper, we propose new methods and evaluate how their core…

This paper describes an effective and efficient image classification framework nominated distributed deep representation learning model (DDRL). The aim is to strike the balance between the computational intensive deep learning approaches…

计算机视觉与模式识别 · 计算机科学 2016-07-05 Le Dong , Na Lv , Qianni Zhang , Shanshan Xie , Ling He , Mengdie Mao

Meta-learning has been proposed as a framework to address the challenging few-shot learning setting. The key idea is to leverage a large number of similar few-shot tasks in order to learn how to adapt a base-learner to a new task for which…

计算机视觉与模式识别 · 计算机科学 2019-04-10 Qianru Sun , Yaoyao Liu , Tat-Seng Chua , Bernt Schiele

Recently, substantial research efforts in Deep Metric Learning (DML) focused on designing complex pairwise-distance losses, which require convoluted schemes to ease optimization, such as sample mining or pair weighting. The standard…

This paper presents a new approach of transfer learning-based medical image classification to mitigate insufficient labeled data problem in medical domain. Instead of direct transfer learning from source to small number of labeled target…

计算机视觉与模式识别 · 计算机科学 2017-08-11 Hak Gu Kim , Yeoreum Choi , Yong Man Ro