Deep Meta Metric Learning

2019-10-01 · ICCV 2019 10 · Guangyi Chen, Tianren Zhang, Jiwen Lu, Jie Zhou

In this paper, we present a deep meta metric learning (DMML) approach for visual recognition. Unlike most existing deep metric learning methods formulating the learning process by an overall objective, our DMML formulates the metric learning in a meta way, and proves that softmax and triplet loss are consistent in the meta space. Specifically, we sample some subsets from the original training set and learn metrics across different subsets. In each sampled sub-task, we split the training data into a support set as well as a query set, and learn the set-based distance, instead of sample-based one, to verify the query cell from multiple support cells. In addition, we introduce hard sample mining for set-based distance to encourage the intra-class compactness. Experimental results on three visual recognition applications including person re-identification, vehicle re-identification and face verification show that the proposed DMML method outperforms most existing approaches.

📄 PDF Abstract BibTeX

Code (1)

CHENGY12/DMML 공식 구현 pytorch

Tasks

Face Verification Metric Learning Person Re-IdentificationTripletVehicle Re-Identification

Methods 이 논문이 사용한 방법론

Triplet Loss The goal of Triplet loss, in the context of Siamese Networks, is to maximize the joint probability among all score-pairs i.e. the product of all probabilities. By using its…

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

MetaMetrics-MT: Tuning Meta-Metrics for Machine Translation via Human Preference Calibration

2024-11-01 · David Anugraha, Garry Kuwanto, Lucky Susanto, Derry Tanti Wijaya 외

We present MetaMetrics-MT, an innovative metric designed to evaluate machine translation (MT) tasks by aligning closely with human preferences through Bayesian optimization with Gaussian Processes. MetaMetrics-MT enhance…

Bayesian Optimization Gaussian Processes Machine Translation Translation

MetaMetrics: Calibrating Metrics For Generation Tasks Using Human Preferences

2024-10-03 · Genta Indra Winata, David Anugraha, Lucky Susanto, Garry Kuwanto 외

Understanding the quality of a performance evaluation metric is crucial for ensuring that model outputs align with human preferences. However, it remains unclear how well each metric captures the diverse aspects of these…

Few-shot Learning with Meta Metric Learners

2019-01-26 · Yu Cheng, Mo Yu, Xiaoxiao Guo, Bo-Wen Zhou

Few-shot Learning aims to learn classifiers for new classes with only a few training examples per class. Existing meta-learning or metric-learning based few-shot learning approaches are limited in handling diverse domain…

Few-Shot Learning Meta-Learning Metric Learning

A Hybrid Approach with Optimization and Metric-based Meta-Learner for Few-Shot Learning

2019-04-04 · Duo Wang, Yu Cheng, Mo Yu, Xiaoxiao Guo 외

Few-shot learning aims to learn classifiers for new classes with only a few training examples per class. Most existing few-shot learning approaches belong to either metric-based meta-learning or optimization-based meta-l…

Few-Shot Learning General Classification image-classification Image Classification+3

MetaRank: Task-Aware Metric Selection for Model Transferability Estimation

2025-11-26 · Yuhang Liu, Wenjie Zhao, Yunhui Guo arxiv

Selecting an appropriate pre-trained source model is a critical, yet computationally expensive, task in transfer learning. Model Transferability Estimation (MTE) methods address this by providing efficient proxy metrics …

Transfer Learning