Multi-Similarity Loss With General Pair Weighting for Deep Metric Learning

Wang, Xun; Han, Xintong; Huang, Weilin; Dong, Dengke; Scott, Matthew R.

doi:10.1109/cvpr.2019.00516

Cited by 696 publications

(632 citation statements)

References 30 publications

Supporting

Mentioning

607

Contrasting

Order By: Relevance

“…The advantage of N-pair loss will be lost in this situation. Unlike all other loss metrics in the literature, the authors in [102] benefited from multi-similarity loss while using self-similarity, negative relative similarity, and positive relative similarity under the general pair weighting framework to capture the similarity between samples. This loss takes both self-similarity and relative similarities into account, which make possible the model to gather and weight informative pair samples more efficiently.…”

Section: Loss Functions For Deep Metric Learningmentioning

confidence: 99%

Deep Metric Learning: A Survey

2019

View full text Add to dashboard Cite

Metric learning aims to measure the similarity among samples while using an optimal distance metric for learning tasks. Metric learning methods, which generally use a linear projection, are limited in solving real-world problems demonstrating non-linear characteristics. Kernel approaches are utilized in metric learning to address this problem. In recent years, deep metric learning, which provides a better solution for nonlinear data through activation functions, has attracted researchers' attention in many different areas. This article aims to reveal the importance of deep metric learning and the problems dealt with in this field in the light of recent studies. As far as the research conducted in this field are concerned, most existing studies that are inspired by Siamese and Triplet networks are commonly used to correlate among samples while using shared weights in deep metric learning. The success of these networks is based on their capacity to understand the similarity relationship among samples. Moreover, sampling strategy, appropriate distance metric, and the structure of the network are the challenging factors for researchers to improve the performance of the network model. This article is considered to be important, as it is the first comprehensive study in which these factors are systematically analyzed and evaluated as a whole and supported by comparing the quantitative results of the methods.

show abstract

Section: Loss Functions For Deep Metric Learningmentioning

confidence: 99%

Deep Metric Learning: A Survey

2019

View full text Add to dashboard Cite

show abstract

“…Only three samples are in a batch that participates in the training. N-pair loss [55] increases the number of negative samples that interact with the query sample to improve the performance of triplet loss. It takes advantage of all sample pairs in the mini-batch and learns more differentiated representations based on structural information between the data.…”

Section: N-pair Lossmentioning

confidence: 99%

Distribution Consistency Loss for Large-Scale Remote Sensing Image Retrieval

Fan

Zhao

2020

Remote Sensing

View full text Add to dashboard Cite

Remote sensing images are featured by massiveness, diversity and complexity. These features put forward higher requirements for the speed and accuracy of remote sensing image retrieval. The extraction method plays a key role in retrieving remote sensing images. Deep metric learning (DML) captures the semantic similarity information between data points by learning embedding in vector space. However, due to the uneven distribution of sample data in remote sensing image datasets, the pair-based loss currently used in DML is not suitable. To improve this, we propose a novel distribution consistency loss to solve this problem. First, we define a new way to mine samples by selecting five in-class hard samples and five inter-class hard samples to form an informative set. This method can make the network extract more useful information in a short time. Secondly, in order to avoid inaccurate feature extraction due to sample imbalance, we assign dynamic weight to the positive samples according to the ratio of the number of hard samples and easy samples in the class, and name the loss caused by the positive sample as the sample balance loss. We combine the sample balance of the positive samples with the ranking consistency of the negative samples to form our distribution consistency loss. Finally, we built an end-to-end fine-tuning network suitable for remote sensing image retrieval. We display comprehensive experimental results drawing on three remote sensing image datasets that are publicly available and show that our method achieves the state-of-the-art performance.

show abstract

“…DML has been a long-standing research hotspot in improving the performance of image retrieval [42][43][44][45][46]52]. There are two different research direction of DML which are clustering-based and pair-based structured losses.…”

Section: Deep Metric Learningmentioning

confidence: 99%

“…As a mass of structured losses [41][42][43][44][45][46][47] have obtained appreciable effectiveness in training networks to learn discriminative embedding features, we would like to make a brief review on the development of pair-based structured loss.…”

Section: Pair-based Structured Lossmentioning

confidence: 99%

“…The key challenge for DML is how to design an informative sample pairs mining strategy and an effective loss function to learn a discriminative embedding space. The pairwise loss functions is a common option used in image retrieval which constructs the training samples into pairs, such as contrastive loss [41], triplet loss [42], N-pairs loss [43], lifted structured loss [44], multi-similarity loss [45] and ranked list loss [46]. The lifted structured loss [44] targeted to utilize a smooth loss function which take the information of all sampled pairs into consideration, but this loss could hardly keep the structured distribution within the intraclasses, and the difference between positive and negative sample pairs might weaken the distinctiveness of the learned deep embedding space.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Global Optimal Structured Embedding Learning for Remote Sensing Image Retrieval

Gou

Xue

et al. 2020

Sensors

View full text Add to dashboard Cite

A rich line of works focus on designing elegant loss functions under the deep metric learning (DML) paradigm to learn a discriminative embedding space for remote sensing image retrieval (RSIR). Essentially, such embedding space could efficiently distinguish deep feature descriptors. So far, most existing losses used in RSIR are based on triplets, which have disadvantages of local optimization, slow convergence and insufficient use of similarity structure in a mini-batch. In this paper, we present a novel DML method named as global optimal structured loss to deal with the limitation of triplet loss. To be specific, we use a softmax function rather than a hinge function in our novel loss to realize global optimization. In addition, we present a novel optimal structured loss, which globally learn an efficient deep embedding space with mined informative sample pairs to force the positive pairs within a limitation and push the negative ones far away from a given boundary. We have conducted extensive experiments on four public remote sensing datasets and the results show that the proposed global optimal structured loss with pairs mining scheme achieves the state-of-the-art performance compared with the baselines.

show abstract

Multi-Similarity Loss With General Pair Weighting for Deep Metric Learning

Cited by 696 publications

References 30 publications

Deep Metric Learning: A Survey

Deep Metric Learning: A Survey

Distribution Consistency Loss for Large-Scale Remote Sensing Image Retrieval

Global Optimal Structured Embedding Learning for Remote Sensing Image Retrieval

Contact Info

Product

Resources

About