首页/论文/1808.04469

arXiv 1808.044692018-08cs.CV

Deep Randomized Ensembles for Metric Learning

George Washington University（乔治华盛顿大学）；Temple University（天普大学）

Hong Xuan, Richard Souvenir, Robert Pless

备注：: ECCV 2018

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

英文摘要相关论文

英文摘要：

Learning embedding functions, which map semantically related inputs to nearby locations in a feature space supports a variety of classification and information retrieval tasks. In this work, we propose a novel, generalizable and fast method to define a family of embedding functions that can be used as an ensemble to give improved results. Each embedding function is learned by randomly bagging the training labels into small subsets. We show experimentally that these embedding ensembles create effective embedding functions. The ensemble output defines a metric space that improves state of the art performance for image retrieval on CUB-200-2011, Cars-196, In-Shop Clothes Retrieval and VehicleID.

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

Attention-based Ensemble for Deep Metric Learning

Samsung Research, Samsung Electronics（三星电子三星研究院）

Deep metric learning aims to learn an embedding function, modeled as deep neural network. This embedding function usually puts semantically similar images close while dissimilar images far from each other in the learned embedding space. Recently, ensemble has been applied to deep metric learning to yield state-of-the-art results. As one important aspect of ensemble, the learners should be diverse in their feature embeddings. To this end, we propose an attention-based ensemble, which uses multiple attention masks, so that each learner can attend to different parts of the object. We also propose…

2018-08-31cs.CV

Adversarial Vulnerability of Randomized Ensembles

University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）

Despite the tremendous success of deep neural networks across various tasks, their vulnerability to imperceptible adversarial perturbations has hindered their deployment in the real world. Recently, works on randomized ensembles have empirically demonstrated significant improvements in adversarial robustness over standard adversarially trained (AT) models with minimal computational overhead, making them a promising solution for safety-critical resource-constrained applications. However, this impressive performance raises the question: Are these robustness gains provided by randomized ensembles…

2022-06-14cs.CRcs.CVcs.LG

Boosting Randomized Smoothing with Variance Reduced Classifiers

ETH Zurich（苏黎世联邦理工学院）

Randomized Smoothing (RS) is a promising method for obtaining robustness certificates by evaluating a base model under noise. In this work, we: (i) theoretically motivate why ensembles are a particularly suitable choice as base models for RS, and (ii) empirically confirm this choice, obtaining state-of-the-art results in multiple settings. The key insight of our work is that the reduced variance of ensembles over the perturbations introduced in RS leads to significantly more consistent classifications for a given input. This, in turn, leads to substantially increased certifiable radii for samp…

2022-03-30cs.AIcs.CVcs.LG

ECML: An Ensemble Cascade Metric Learning Mechanism towards Face Verification

Huazhong University of Science and Technology（华中科技大学）；Institute of High Performance Computing, A*STAR（新加坡科技研究局高性能计算研究院）；Nanjing University（南京大学）

Face verification can be regarded as a 2-class fine-grained visual recognition problem. Enhancing the feature's discriminative power is one of the key problems to improve its performance. Metric learning technology is often applied to address this need, while achieving a good tradeoff between underfitting and overfitting plays the vital role in metric learning. Hence, we propose a novel ensemble cascade metric learning (ECML) mechanism. In particular, hierarchical metric learning is executed in the cascade way to alleviate underfitting. Meanwhile, at each learning level, the features are split…

2020-07-11cs.CV

Transferability Metrics for Selecting Source Model Ensembles

Google Research（谷歌研究院）

We address the problem of ensemble selection in transfer learning: Given a large pool of source models we want to select an ensemble of models which, after fine-tuning on the target training set, yields the best performance on the target test set. Since fine-tuning all possible ensembles is computationally prohibitive, we aim at predicting performance on the target dataset using a computationally efficient transferability metric. We propose several new transferability metrics designed for this task and evaluate them in a challenging and realistic transfer learning setup for semantic segmentati…

2022-03-31cs.CV

Large Scale Strongly Supervised Ensemble Metric Learning, with Applications to Face Verification and Retrieval

NEC Laboratories America（美国NEC实验室）

Learning Mahanalobis distance metrics in a high- dimensional feature space is very difficult especially when structural sparsity and low rank are enforced to improve com- putational efficiency in testing phase. This paper addresses both aspects by an ensemble metric learning approach that consists of sparse block diagonal metric ensembling and join- t metric learning as two consecutive steps. The former step pursues a highly sparse block diagonal metric by selecting effective feature groups while the latter one further exploits correlations between selected feature groups to obtain an accurate…

2012-12-25cs.CV

更多相关论文收起更多论文

RISE: Randomized Input Sampling for Explanation of Black-box Models

Boston University（波士顿大学）

Deep neural networks are being used increasingly to automate data analysis and decision making, yet their decision-making process is largely unclear and is difficult to explain to the end users. In this paper, we address the problem of Explainable AI for deep neural networks that take images as input and output a class probability. We propose an approach called RISE that generates an importance map indicating how salient each pixel is for the model's prediction. In contrast to white-box approaches that estimate pixel importance using gradients or other internal network state, RISE works on bla…

2018-09-25cs.CV

随机盲图像质量评估：用于可认证盲图像质量评估的中值随机平滑

Stochastic BIQA: Median Randomized Smoothing for Certified Blind Image Quality Assessment

MSU Institute for Artificial Intelligence（莫斯科国立大学人工智能研究所）；ISP RAS Research Center for Trusted Artificial Intelligence（俄罗斯科学院信息学与自动化研究所可信人工智能研究中心）；Lomonosov Moscow State University（罗蒙诺索夫莫斯科国立大学）；Artificial Intelligence Research Institute（人工智能研究所）；Innopolis University（因诺波利斯大学）

本文提出基于中值随机平滑的可认证鲁棒无参考图像质量评估方法，结合卷积去噪器和排序损失，在三个数据集上取得更优的SROCC和PLCC分数。

2024-11-19cs.CVeess.IV

Random Vector Functional Link Neural Network based Ensemble Deep Learning

Nanyang Technological University（南洋理工大学）；Indian Institute of Technology Indore（印度理工学院印多尔分校）

In this paper, we propose a deep learning framework based on randomized neural network. In particular, inspired by the principles of Random Vector Functional Link (RVFL) network, we present a deep RVFL network (dRVFL) with stacked layers. The parameters of the hidden layers of the dRVFL are randomly generated within a suitable range and kept fixed while the output weights are computed using the closed form solution as in a standard RVFL network. We also propose an ensemble deep network (edRVFL) that can be regarded as a marriage of ensemble learning with deep learning. Unlike traditional ensem…

2019-06-30cs.CV

Toward Multidiversified Ensemble Clustering of High-Dimensional Data: From Subspaces to Metrics and Beyond

South China Agricultural University（华南农业大学）；Pazhou Lab（琶洲实验室）；Sun Yat-sen University（中山大学）；Guangdong Key Laboratory of Information Security Technology（广东省信息安全技术重点实验室）；Key Laboratory of Machine Intelligence and Advanced Computing, Ministry of Education（教育部机器智能与先进计算重点实验室）；Nanyang Technological University（南洋理工大学）

The rapid emergence of high-dimensional data in various areas has brought new challenges to current ensemble clustering research. To deal with the curse of dimensionality, recently considerable efforts in ensemble clustering have been made by means of different subspace-based techniques. However, besides the emphasis on subspaces, rather limited attention has been paid to the potential diversity in similarity/dissimilarity metrics. It remains a surprisingly open problem in ensemble clustering how to create and aggregate a large population of diversified metrics, and furthermore, how to jointly…

2021-09-05cs.CVcs.LG

Exploiting Uncertainties from Ensemble Learners to Improve Decision-Making in Healthcare AI

University of California, Berkeley（加州大学伯克利分校）；University of Chicago（芝加哥大学）；Lawrence Berkeley National Laboratory（劳伦斯伯克利国家实验室）

Ensemble learning is widely applied in Machine Learning (ML) to improve model performance and to mitigate decision risks. In this approach, predictions from a diverse set of learners are combined to obtain a joint decision. Recently, various methods have been explored in literature for estimating decision uncertainties using ensemble learning; however, determining which metrics are a better fit for certain decision-making applications remains a challenging task. In this paper, we study the following key research question in the selection of uncertainty metrics: when does an uncertainty metric …

2020-07-12cs.CVcs.LGstat.ML

一种优化多样性的深度集成方法用于准确的植物叶病检测

A Diversity-optimized Deep Ensemble Approach for Accurate Plant Leaf Disease Detection

本文提出SQ框架，通过优化集成多样性提升植物叶病检测的准确性和效率。

2025-11-21cs.CVcs.LG