Adaptive Hierarchical Similarity Metric Learning With Noisy Labels

Yan, Jiexi; Luo, Lei; Deng, Cheng; Huang, Heng

doi:10.1109/tip.2023.3242148

Cited by 18 publications

(3 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They also propose a hyperbolic version of Reciprocal Point Learning (Chen et al, 2020a) to provide extra-class space for known categories in the few-shot learning stage. Yan et al (2023) also explore hyperbolic metric learning, incorporating noise-insensitive and adaptive hierarchical similarity to handle noisy labels and multi-level relations. Kim et al (2022) add a hierarchical regularization term on top of the metric learning approaches, with the goal of learning hierarchical ancestors in hyperbolic space without any annotation.…”

Section: Hyperbolic Metric Learningmentioning

confidence: 99%

Hyperbolic Deep Learning in Computer Vision: A Survey

Mettes,

Ghadimi Atigh,

Keller-Ressel

et al. 2024

Int J Comput Vis

View full text Add to dashboard Cite

Deep representation learning is a ubiquitous part of modern computer vision. While Euclidean space has been the de facto standard manifold for learning visual representations, hyperbolic space has recently gained rapid traction for learning in computer vision. Specifically, hyperbolic learning has shown a strong potential to embed hierarchical structures, learn from limited samples, quantify uncertainty, add robustness, limit error severity, and more. In this paper, we provide a categorization and in-depth overview of current literature on hyperbolic learning for computer vision. We research both supervised and unsupervised literature and identify three main research themes in each direction. We outline how hyperbolic learning is performed in all themes and discuss the main research problems that benefit from current advances in hyperbolic learning for computer vision. Moreover, we provide a high-level intuition behind hyperbolic geometry and outline open research questions to further advance research in this direction.

show abstract

Section: Hyperbolic Metric Learningmentioning

confidence: 99%

Hyperbolic Deep Learning in Computer Vision: A Survey

Mettes,

Ghadimi Atigh,

Keller-Ressel

et al. 2024

Int J Comput Vis

View full text Add to dashboard Cite

show abstract

“…Self-supervised learning aims to acquire intermediate features of superior quality that can be effectively applied to various downstream tasks. The existing approaches in selfsupervised learning have predominantly revolved around contrastive method (Chen et al 2022;Yan et al 2023a). MoCo (He et al 2020) built a dynamic dictionary with a queue and a momentum encoder to enhance the training efficacy.…”

Section: Related Workmentioning

confidence: 99%

Asymmetric Mutual Alignment for Unsupervised Zero-Shot Sketch-Based Image Retrieval

Yin,

Yan,

et al. 2024

AAAI

View full text Add to dashboard Cite

In recent years, many methods have been proposed to address the zero-shot sketch-based image retrieval (ZS-SBIR) task, which is a practical problem in many applications. However, in real-world scenarios, on the one hand, we can not obtain training data with the same distribution as the test data, and on the other hand, the labels of training data are not available as usual. To tackle this issue, we focus on a new problem, namely unsupervised zero-shot sketch-based image retrieval (UZS-SBIR), where the available training data does not have labels while the training and testing categories are not overlapping. In this paper, we introduce a new asymmetric mutual alignment method (AMA) including a self-distillation module and a cross-modality mutual alignment module. First, we conduct self-distillation to extract the feature embeddings from unlabeled data. Due to the lack of available information in an unsupervised manner, we employ the cross-modality mutual alignment module to further excavate underlying intra-modality and inter-modality relationships from unlabeled data, and take full advantage of these correlations to align the feature embeddings in image and sketch domains. Meanwhile, the feature representations are enhanced by the intra-modality clustering relations, leading to better generalization ability to unseen classes. Moreover, we conduct an asymmetric strategy to update the teacher and student networks, respectively. Extensive experimental results on several benchmark datasets demonstrate the superiority of our method.

show abstract

“…The core concept of sample-wise similarity learning involves learning representations for individual data samples, aiming to precisely reflect the inherent similarities between them [149,174]. This approach primarily concentrates on deciphering the inherent relationships within the data, considering each data point in relation to every other point in the sample space.…”

Section: Knowledge-guided Pre-trainingmentioning

confidence: 99%

Knowledge-Guided Machine Learning

Karpatne¹,

Kannan²,

Kumar³

2022

View full text Add to dashboard Cite

This paper presents an overview of scientific modeling and discusses the complementary strengths and weaknesses of ML methods for scientific modeling in comparison to process-based models. It also provides an introduction to the current state of research in the emerging field of scientific knowledge-guided machine learning (KGML) that aims to use both scientific knowledge and data in ML frameworks to achieve better generalizability, scientific consistency, and explainability of results. We discuss different facets of KGML research in terms of the type of scientific knowledge used, the form of knowledge-ML integration explored, and the method for incorporating scientific knowledge in ML. We also discuss some of the common categories of use cases in environmental sciences where KGML methods are being developed, using illustrative examples in each category.

show abstract

Adaptive Hierarchical Similarity Metric Learning With Noisy Labels

Cited by 18 publications

References 44 publications

Hyperbolic Deep Learning in Computer Vision: A Survey

Hyperbolic Deep Learning in Computer Vision: A Survey

Asymmetric Mutual Alignment for Unsupervised Zero-Shot Sketch-Based Image Retrieval

Knowledge-Guided Machine Learning

Contact Info

Product

Resources

About