4.8 Article

Deep Metric Learning With Adaptively Composite Dynamic Constraints

相关参考文献

注意:仅列出部分参考文献,下载原文获取全部文献信息。
Article Computer Science, Artificial Intelligence

The Group Loss++: A Deeper Look Into Group Loss for Deep Metric Learning

Ismail Elezi et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2022)

Proceedings Paper Computer Science, Artificial Intelligence

Non-isotropy Regularization for Proxy-based Deep Metric Learning

Karsten Roth et al.

Summary: Deep Metric Learning aims to learn representation spaces where semantic relations can be expressed through predefined distance metrics. This paper proposes a non-isotropy regularization method based on proxies, which guides the samples to form non-isotropic distributions around class proxies to better learn local structures.

2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) (2022)

Article Computer Science, Artificial Intelligence

Hardness-Aware Deep Metric Learning

Wenzhao Zheng et al.

Summary: This paper introduces a hardness-aware deep metric learning framework for image clustering and retrieval. By performing linear interpolation on embeddings to adaptively manipulate their hardness levels and generating multiple synthetics for each sample, the framework aims to fully exploit information in all samples and challenge the metric with proper difficulty. Extensive experimental results demonstrate the effectiveness of the proposed framework on various datasets.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2021)

Proceedings Paper Computer Science, Artificial Intelligence

Deep Relational Metric Learning

Wenzhao Zheng et al.

Summary: This paper introduces a deep relational metric learning framework that improves image clustering and retrieval by adaptively learning a set of features, capturing feature correlations with a relational module, and performing relational inference to obtain relation-aware embeddings. This approach achieves competitive results on widely-used datasets.

2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021) (2021)

Proceedings Paper Computer Science, Artificial Intelligence

Learning with Memory-based Virtual Classes for Deep Metric Learning

Byungsoo Ko et al.

Summary: The study presents a novel training strategy for deep metric learning called MemVir, which memorizes embedding features and class weights as virtual classes to improve performance. It gradually increases learning difficulty to enhance stability and final performance.

2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021) (2021)

Proceedings Paper Computer Science, Artificial Intelligence

Deep Compositional Metric Learning

Wenzhao Zheng et al.

Summary: This paper proposes a deep compositional metric learning framework for effective and generalizable similarity measurement between images. By separating sub-embeddings from direct supervisions from the subtasks and applying losses on different composites of the sub-embeddings, the framework achieves better generalization ability without compromising. Employing learnable compositors to combine the sub-embeddings and using a self-reinforced loss to train the compositors, the framework distributes diverse training signals to avoid destroying the discrimination ability.

2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021 (2021)

Article Computer Science, Artificial Intelligence

Deep Metric Learning with BIER: Boosting Independent Embeddings Robustly

Michael Opitz et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2020)

Proceedings Paper Computer Science, Artificial Intelligence

PADS: Policy-Adapted Sampling for Visual Similarity Learning

Karsten Roth et al.

2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) (2020)

Proceedings Paper Computer Science, Artificial Intelligence

Deep Metric Learning via Adaptive Learnable Assessment

Wenzhao Zheng et al.

2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) (2020)

Proceedings Paper Computer Science, Artificial Intelligence

DeepGCNs: Can GCNs Go as Deep as CNNs?

Guohao Li et al.

2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019) (2019)

Proceedings Paper Computer Science, Artificial Intelligence

Sampling Wisely: Deep Image Embedding by Top-k Precision Optimization

Jing Lu et al.

2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019) (2019)

Proceedings Paper Computer Science, Artificial Intelligence

A Theoretically Sound Upper Bound on the Triplet Loss for Improving the Efficiency of Deep Distance Metric Learning

Thanh-Toan Do et al.

2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019) (2019)

Proceedings Paper Computer Science, Artificial Intelligence

Deep Asymmetric Metric Learning via Rich Relationship Mining

Xinyi Xu et al.

2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019) (2019)

Proceedings Paper Computer Science, Artificial Intelligence

Signal-to-Noise Ratio: A Robust Distance Metric for Deep Metric Learning

Tongtong Yuan et al.

2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019) (2019)

Proceedings Paper Computer Science, Artificial Intelligence

Deep Metric Learning to Rank

Fatih Cakir et al.

2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019) (2019)

Proceedings Paper Computer Science, Artificial Intelligence

On Learning Density Aware Embeddings

Soumyadeep Ghosh et al.

2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019) (2019)

Proceedings Paper Computer Science, Artificial Intelligence

Divide and Conquer the Embedding Space for Metric Learning

Artsiom Sanakoyeu et al.

2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019) (2019)

Proceedings Paper Computer Science, Artificial Intelligence

Hard-Aware Deeply Cascaded Embedding

Yuhui Yuan et al.

2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV) (2017)

Proceedings Paper Computer Science, Artificial Intelligence

Efficient Online Local Metric Adaptation via Negative Samples for Person Re-Identification

Jiahuan Zhou et al.

2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV) (2017)

Proceedings Paper Computer Science, Artificial Intelligence

Deep Metric Learning with Angular Loss

Jian Wang et al.

2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV) (2017)

Proceedings Paper Computer Science, Artificial Intelligence

BIER - Boosting Independent Embeddings Robustly

Michael Opitz et al.

2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV) (2017)

Proceedings Paper Computer Science, Artificial Intelligence

Smart Mining for Deep Metric Learning

Ben Harwood et al.

2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV) (2017)

Proceedings Paper Computer Science, Artificial Intelligence

SphereFace: Deep Hypersphere Embedding for Face Recognition

Weiyang Liu et al.

30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017) (2017)

Proceedings Paper Computer Science, Artificial Intelligence

Beyond triplet loss: a deep quadruplet network for person re-identification

Weihua Chen et al.

30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017) (2017)

Article Computer Science, Artificial Intelligence

ImageNet Large Scale Visual Recognition Challenge

Olga Russakovsky et al.

INTERNATIONAL JOURNAL OF COMPUTER VISION (2015)

Article Computer Science, Artificial Intelligence

Object Detection with Discriminatively Trained Part-Based Models

Pedro F. Felzenszwalb et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2010)

Article Computer Science, Artificial Intelligence

Learning to forget: Continual prediction with LSTM

FA Gers et al.

NEURAL COMPUTATION (2000)