526互联

self-supervised classification distillation

[论文阅读] Anomaly detection via reverse distillation from one-class embedding

Anomaly detection via reverse distillation from one-class embedding Introduction 在知识蒸馏（KD）中，知识是在教师-学生（T-S）对中传递的。在无监督异常检测的背景下，由于学生在训练过程中只接触到正常样本，所以当查询是 ......
distillation detection embedding one-class Anomaly

DE-RRD: A Knowledge Distillation Framework for Recommender System

目录概DE-RRDDistillation Experts (DE)Relaxed Ranking Distillation (RRD)代码 Kang S., Hwang J., Kweon W. and Yu H. DE-RRD: A knowledge distillation framewor ......
Distillation Recommender Knowledge Framework DE-RRD

Topology Distillation for Recommender System

目录概Topology DistillationFull Topology Distillation (FTD)Hierarchical Topology Distillation (HTD)代码 Kang S., Hwang J., Kweon W. and Yu H. Topology dist ......
Distillation Recommender Topology System for

Collaborative Distillation for Top-N Recommendation

目录概符号说明Collaborative distillation (CD) Lee J., Choi M., Lee J. and Shim H. Collaborative distillation for top-N recommendation. ICDM, 2019. 概 Ranking- ......
Recommendation Collaborative Distillation Top-N for

Relational Knowledge Distillation

目录概符号说明RKD代码 Park W., Kim D., Lu Y. and Cho M. Relational knowledge distillation. CVPR, 2019. 概 符号说明 \(f_T, f_S\), teacher and student model; \(\mathc ......
Distillation Relational Knowledge

Ranking Distillation: Learning Compact Ranking Models With High Performance for Recommender System

目录概符号说明Ranking Distillation代码 Tang J. and Wang K. Ranking Distillation: Learning compact ranking models with high performance for recommender system. ......
Ranking Distillation Performance Recommender Learning

PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models

PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models 阅读笔记（11.2） 摘要：优化MSE指标通常会导致模糊，特别是在高方差(详细)区域。我们提出了一种基于创建正确降尺度的 ......
Self-Supervised Exploration Generative Supervised Upsampling

Paper Reading: Hashing-Based Undersampling Ensemble for Imbalanced Pattern Classification Problems

针对欠采样方法会丢弃大量多数类样本导致信息缺失的问题，本文提出了基于哈希的欠采样集成 HUE 模型，它利用 Bagging 和多数类样本的分布特征来构建多样化的训练子集。首先 HUE 通过散列将大多数类样本划分为不同的特征子空间，然后使用所有少数样本和主要从同一哈希子空间中提取的部分多数样本来构建训... ......
Classification Hashing-Based Undersampling Imbalanced Ensemble

论文解读（MTEM）《Meta-Tsallis-Entropy Minimization: A New Self-Training Approach for Domain Adaptation on Text Classification》

Note：[ wechat：Y466551 | 可加勿骚扰，付费咨询 ] 论文信息 论文标题：Meta-Tsallis-Entropy Minimization: A New Self-Training Approach for Domain Adaptation on Text Classific ......
Meta-Tsallis-Entropy Classification Self-Training Minimization Adaptation

论文解读（DEAL）《DEAL: An Unsupervised Domain Adaptive Framework for Graph-level Classification》

Note：[ wechat：Y466551 | 可加勿骚扰，付费咨询 ] 论文信息 论文标题：DEAL: An Unsupervised Domain Adaptive Framework for Graph-level Classification论文作者：Nan Yin、Li Shen、Baop ......
DEAL Classification Unsupervised Graph-level Framework

论文解读（TAMEPT）《A Two-Stage Framework with Self-Supervised Distillation For Cross-Domain Text Classification》

论文信息 论文标题：A Two-Stage Framework with Self-Supervised Distillation For Cross-Domain Text Classification论文作者：Yunlong Feng, Bohan Li, Libo Qin, Xiao Xu, ......
Self-Supervised Classification Distillation Cross-Domain Supervised

论文解读（IW-Fit）《Better Fine-Tuning via Instance Weighting for Text Classification》

Note：[ wechat：Y466551 | 可加勿骚扰，付费咨询 ] 论文信息 论文标题：Better Fine-Tuning via Instance Weighting for Text Classification论文作者：论文来源：2021 ACL论文地址：download 论文代码：d ......
Classification Fine-Tuning Weighting Instance IW-Fit

论文解读（BSFDA）《Black-box Source-free Domain Adaptation via Two-stage Knowledge Distillation》

Note：[ wechat：Y466551 | 可加勿骚扰，付费咨询 ] 论文信息 论文标题：Black-box Source-free Domain Adaptation via Two-stage Knowledge Distillation论文作者：Shuai Wang, Daoan Zhan ......
Distillation Source-free Adaptation Black-box Knowledge

论文解读（KDSSDA）《Knowledge distillation for semi-supervised domain adaptation》

Note：[ wechat：Y466551 | 可加勿骚扰，付费咨询 ] 论文信息 论文标题：Knowledge distillation for semi-supervised domain adaptation论文作者：Mauricio Orbes-Arteaga, Jorge Cardoso论 ......
semi-supervised distillation adaptation supervised Knowledge

论文解读（KD-UDA）《Joint Progressive Knowledge Distillation and Unsupervised Domain Adaptation》

Note：[ wechat：Y466551 | 可加勿骚扰，付费咨询 ] 论文信息 论文标题：Joint Progressive Knowledge Distillation and Unsupervised Domain Adaptation论文作者：Yanping Fu, Yun Liu论文来源 ......
Distillation Unsupervised Progressive Adaptation Knowledge

论文解读（CTDA）《Contrastive transformer based domain adaptation for multi-source cross-domain sentiment classification》

Note：[ wechat：Y466551 | 可加勿骚扰，付费咨询 ] 论文信息 论文标题：Contrastive transformer based domain adaptation for multi-source cross-domain sentiment classification论 ......
domain classification cross-domain multi-source Contrastive

论文解读（CBL）《CNN-Based Broad Learning for Cross-Domain Emotion Classification》

Note：[ wechat：Y466551 | 付费咨询，非诚勿扰 ] 论文信息 论文标题：CNN-Based Broad Learning for Cross-Domain Emotion Classification论文作者：Rong Zeng, Hongzhan Liu , Sancheng ......
Classification Cross-Domain CNN-Based Learning Emotion

Paper Reading: FT4cip: A new functional tree for classification in class imbalance problems

本文提出了一种类不平衡问题的功能树(FT4cip)，该模型使用了考虑类不平衡的分割评估函数 Twoing，以及使用了一种优化 AUC 的新型剪枝算法。同时对多变量分割使用特征选择，进一步提高分类性能和可解释性。通过大量的实验分析证明，FT4cip 在 AUC 上的分类性能优于 LMT 和 Gama。... ......
classification functional imbalance problems Reading

论文解读（AAD）《Knowledge distillation for BERT unsupervised domain adaptation》

Note：[ wechat：Y466551 | 可加勿骚扰，付费咨询 ] 论文信息 论文标题：Knowledge distillation for BERT unsupervised domain adaptation论文作者：Minho Ryu、Geonseok Lee、Kichun Lee论文来 ......
distillation unsupervised adaptation Knowledge domain

如何用Confusion matrix，classification report，ROC curve (AUC)分析一个二分类问题

ROC https://zhuanlan.zhihu.com/p/246444894 Sure, let's create a random confusion matrix as an example, and then I'll explain what each element in the ......
classification Confusion matrix report 问题

Paper Reading: A Re-Balancing Strategy for Class-Imbalanced Classification Based on Instance Difficulty

受人类学习过程的启发，本文根据学习速度设计了样本难度模型，并提出了一种新的实例级再平衡策略。具体来说模型在每个训练周期记录每个实例的预测，并根据预测的变化来测量该样本的难度难度。然后对困难实例赋予更高的权重，对数据进行重新采样。本文从理论上证明了提出的重采样策略的正确性和收敛性，并进行一些实证实验来... ......
Class-Imbalanced Classification Re-Balancing Imbalanced Difficulty

[AAAI 2023]Self-Supervised Bidirectional Learning for Graph Matching

# Self-Supervised Bidirectional Learning for Graph Matching ## 动机 Graph Matching（GM）是个NP难问题。随着机器学习的兴起，该问题也有望被更高效地解决。然而，现有的监督学习仍然需要为了训练去计算大量的ground tru ......
Self-Supervised Bidirectional Supervised Learning Matching

[论文速览] A Closer Look at Self-supervised Lightweight Vision Transformers

## Pre title: A Closer Look at Self-supervised Lightweight Vision Transformers accepted: ICML 2023 paper: https://arxiv.org/abs/2205.14443 code: https ......
Self-supervised Transformers Lightweight supervised Closer

Paper Reading: Self-paced Ensemble for Highly Imbalanced Massive Data Classification

目前很多方法都不能很好地处理高度不平衡、大规模和有噪声的分类任务，主要原因是它们忽视了不平衡学习所隐含的困难。本文引入“分类硬度”的概念来刻画不平衡问题的困难所在，该概念表示为特定分类器正确分类样本的难度。基于这个概念，本文提出了一种新的学习框架——自定步速集成(self-pace Ensemble... ......
Classification Imbalanced Self-paced Ensemble Massive

【论文阅读】CrossViT：Cross-Attention Multi-Scale Vision Transformer for Image Classification

> # 🚩前言 > > - 🐳博客主页：😚[睡晚不猿序程](https://www.cnblogs.com/whp135/)😚 > - ⌚首发时间：23.7.10 > - ⏰最近更新时间：23.7.10 > - 🙆本文由 **睡晚不猿序程** 原创 > - 🤡作者是蒻蒟本蒟，如果文章里有 ......
Cross-Attention Classification Multi-Scale Transformer Attention

画出 sklearn 中支持向量机分类函数 SVC 的分类结果图（Draw the classification result graph of the svm classification function SVC in sklearn library）

在最近的学习中，看到代码中展示了如何画出支持向量机分类结果的决策面、最大间隙面和支持向量，即确定用支持向量机分类函数 SVC 进行分类后得到分类超平面和间隙面函数以及支持向量坐标的方法，分享给大家~ 1. 训练 svm 分类器 SVC 代码 1 from sklearn import svm 2 i ......
classification sklearn 向量 函数 SVC

Supervised Machine Learning Regression and Classification - Week 1

# 1. 机器学习定义 > Field of study that gives computers the ability to learn without being explicitly programmed. -- Arthur Samuel(1959) ![](https://img2023 ......
Classification Supervised Regression Learning Machine

Neural network image classification using Intel oneAPI tool

With the continuous development of artificial intelligence technology, image classification has become a popular research area. In this field, deep le ......
classification network Neural oneAPI Intel

Deep One-Class Classification

# Deep One-Class Classifification Deep SVDD (Deep Support Vector Data Description)训练一个神经网络，最小化包含数据表征的超球的体积（如图1所示） ![image-20230606193307205](https://i ......
Classification One-Class Class Deep One

Incrementer：Transformer for Class-Incremental Semantic Segmentation with Knowledge Distillation Focusing on Old Class论文阅读笔记

## 摘要 目前已有的连续语义分割方法通常基于卷积神经网络，需要添加额外的卷积层来分辨新类别，且在蒸馏特征时没有对属于旧类别/新类别的区域加以区分。为此，作者提出了基于Transformer的网络incrementer，在学习新类别时只需要往decoder中加入对应的token。同时，作者还提出了对 ......
Class Class-Incremental Distillation Segmentation Incrementer
共85篇  :2/3页 首页上一页2下一页尾页