Few-shot Metric Learning: Online Adaptation of Embedding for Retrieval

Jung, Deunsol; Kang, Dahyun; Kwak, Suha; Cho, Minsu

doi:10.1007/978-3-031-26348-4_4

Cited by 4 publications

(2 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Meta learning [50] is also introduced for metric learning [51], where the training set is split into multiple subsets and a meta metric is learned across the different subsets (tasks). Recently, a few-shot metric learning approach [29] is designed to adapt the metric space by rectifying channels of intermediate layers, and a universal metric learning method is proposed in [30] by utilizing prompt learning.…”

Section: Tml Via Metric Approximationmentioning

confidence: 99%

Transfer metric learning: algorithms, applications and outlooks

Luo,

Wen,

et al. 2024

Vicinagearth

View full text Add to dashboard Cite

Distance metric learning (DML) aims to find an appropriate way to reveal the underlying data relationship. It is critical in many machine learning, pattern recognition and data mining algorithms, and usually require large amount of label information (such as class labels or pair/triplet constraints) to achieve satisfactory performance. However, the label information may be insufficient in real-world applications due to the high-labeling cost, and DML may fail in this case. Transfer metric learning (TML) is able to mitigate this issue for DML in the domain of interest (target domain) by leveraging knowledge/information from other related domains (source domains). Although achieved a certain level of development, TML has limited success in various aspects such as selective transfer, theoretical understanding, handling complex data, big data and extreme cases. In this survey, we present a systematic review of the TML literature. In particular, we group TML into different categories according to different settings and metric transfer strategies, such as direct metric approximation, subspace approximation, distance approximation, and distribution approximation. A summarization and insightful discussion of the various TML approaches and their applications will be presented. Finally, we indicate some challenges and provide possible future directions.

show abstract

Section: Tml Via Metric Approximationmentioning

confidence: 99%

Transfer metric learning: algorithms, applications and outlooks

Luo,

Wen,

et al. 2024

Vicinagearth

View full text Add to dashboard Cite

show abstract

“…To encourage G att to generate more representative semantic embedding for an unseen class, we used the idea of building a distance metric in metric learning. Metric learning aims to learn such a distance metric for a type of input data that conforms to semantic distance measures between the data instances [35]; this point has been explored and applied in both few-shot learning [35] and zero-shot learning [36,37]. Inspired by previous work,we propose the semantic-relevant self-adaptive margin center loss (SEMC − loss, L SEMC ) to constraint G att .…”

Section: Loss Design 231 Semantic-relevant Self-adaptive Margin Cente...mentioning

confidence: 99%

Zero-Shot Learning with Joint Generative Adversarial Networks

et al. 2023

View full text Add to dashboard Cite

Zero-shot learning (ZSL) is implemented by transferring knowledge from seen classes to unseen classes through embedding space or feature generation. However, the embedding-based method has a hubness problem, and the generation-based method may contain considerable bias. To solve these problems, a joint model with multiple generative adversarial networks (JG-ZSL) is proposed in this paper. Firstly, we combined the generation-based model and the embedding-based model to build a hybrid ZSL framework by mapping the real samples and the synthetic samples into the embedding space for classification, which alleviates the problem of data imbalance effectively. Secondly, based on the original generation-method model, a coupled GAN is introduced to generate semantic embeddings, which can generate semantic vectors for unseen classes in embedded space to alleviate the bias of mapping results. Finally, semantic-relevant self-adaptive margin center loss was used, which can explicitly encourage intra-class compactness and inter-class separability, and it can also guide coupled GAN to generate discriminative and representative semantic features. All the experiments on the four standard datasets (CUB, AWA1, AWA2, SUN) show that the proposed method is effective.

show abstract