SoftTriple Loss: Deep Metric Learning Without Triplet Sampling

Qian, Quan; Shang, Lei; Sun, Baigui; Hu, Juhua; Tacoma, Tacoma; Li, Hao; Jin, Rong

doi:10.1109/iccv.2019.00655

Cited by 334 publications

(259 citation statements)

References 22 publications

Supporting

Mentioning

256

Contrasting

Order By: Relevance

“…[3], and DREML [5]) with a large margin. Impressively, even the single-head version of HDhE (Sh-HDhE) having only the pruned head (Last layer is Res4_1) shows a competitive performance to the latest algorithms (SCHM [8], SoftTriple [9], and Proxy-Anchor [10]). Furthermore, the proposed HDhE gives a performance improvement of over 4% of Recall@1 (CUB-200) from the single-head version of HDhE (Sh-HDhE).…”

Section: E Comparison To State-of-the-art Methodsmentioning

confidence: 99%

Heterogeneous Double-Head Ensemble for Deep Metric Learning

Ro¹,

Choi²

2020

IEEE Access

View full text Add to dashboard Cite

The structure of a multi-head ensemble has been employed by many algorithms in various applications including deep metric learning. However, their structures have been empirically designed in a simple way such as using the same head structure, which leads to a limited ensemble effect due to lack of head diversity. In this paper, for an elaborate design of the multi-head ensemble structure, we establish design concepts based on three structural factors: designing the feature layer for extracting the ensemblefavorable feature vector, designing the shared part for memory savings, and designing the diverse multiheads for performance improvement. Through rigorous evaluation of variants on the basis of the design concepts, we propose a heterogeneous double-head ensemble structure that drastically increases ensemble gain along with memory savings. In verifying experiments on image retrieval datasets, the proposed ensemble structure outperforms the state-of-the-art algorithms by margins of over 5.3%, 6.1%, 5.9%, and 1.8% in CUB-200, Car-196, SOP, and Inshop, respectively. INDEX TERMS Ensemble learning, multi-head structure, deep metric learning, deep architecture design, image retrieval

show abstract

Section: E Comparison To State-of-the-art Methodsmentioning

confidence: 99%

Heterogeneous Double-Head Ensemble for Deep Metric Learning

Ro¹,

Choi²

2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…This idea is an interesting extension of instance-to-class similarity relationship modelling. In this approach, classes are represented by proxies [34], [39]. It is interesting in that more flexibility is given: (1) The number of proxies can be smaller than the number of training classes, in which case multiple classes are assigned to the same proxy.…”

Section: Design Of Loss Functions For Learning Discriminative Deep Representationsmentioning

confidence: 99%

Ranked List Loss for Deep Metric Learning

Wang

Yang

Kodirov³

et al. 2021

IEEE Trans. Pattern Anal. Mach. Intell.

View full text Add to dashboard Cite

The objective of deep metric learning (DML) is to learn embeddings that can capture semantic similarity and dissimilarity information among data points. Existing pairwise or tripletwise loss functions used in DML are known to suffer from slow convergence due to a large proportion of trivial pairs or triplets as the model improves. To improve this, ranking-motivated structured losses are proposed recently to incorporate multiple examples and exploit the structured information among them. They converge faster and achieve state-of-the-art performance. In this work, we unveil two limitations of existing ranking-motivated structured losses and propose a novel ranked list loss to solve both of them. First, given a query, only a fraction of data points is incorporated to build the similarity structure. Consequently, some useful examples are ignored and the structure is less informative. To address this, we propose to build a set-based similarity structure by exploiting all instances in the gallery. The learning setting can be interpreted as few-shot retrieval: given a mini-batch, every example is iteratively used as a query, and the rest ones compose the galley to search, i.e., the support set in few-shot setting. The rest examples are split into a positive set and a negative set. For every mini-batch, the learning objective of ranked list loss is to make the query closer to the positive set than to the negative set by a margin. Second, previous methods aim to pull positive pairs as close as possible in the embedding space. As a result, the intraclass data distribution tends to be extremely compressed. In contrast, we propose to learn a hypersphere for each class in order to preserve useful similarity structure inside it, which functions as regularisation. Extensive experiments demonstrate the superiority of our proposal by comparing with the state-of-the-art methods on the fine-grained image retrieval task. Our source code is available online: https://github.com/XinshaoAmos Wang/Ranked-List-Loss-for-DML.

show abstract

“…This optimizes a distance metric-based or KL-divergence loss on the graph pairs or triplets [2,6,25] necessitating vast training pairs or triplets to capture the entire global characteristics. One way to avoid explicit pair or triplet generation utilizes efficient batch-wise learning via optimizing classification loss [35,38]. However, pairwise node matching in a batch-wise setting is problematic due to graph size variability.…”

Section: Cross-global Attention Node Matchingmentioning

confidence: 99%

Graph Kernel Prediction of Drug Prescription

Yao

Chang

Huang³

et al. 2019

2019 IEEE EMBS International Conference on Biomedical &Amp; Health Informatics (BHI)

View full text Add to dashboard Cite

We present an end-to-end, interpretable, deep-learning architecture to learn a graph kernel that predicts the outcome of chronic disease drug prescription. This is achieved through a deep metric learning collaborative with a Support Vector Machine objective using a graphical representation of Electronic Health Records. We formulate the predictive model as a binary graph classification problem with an adaptive learned graph kernel through novel cross-global attention node matching between patient graphs, simultaneously computing on multiple graphs without training pair or triplet generation. Results using the Taiwanese National Health Insurance Research Database demonstrate that our approach outperforms current start-of-the-art models both in terms of accuracy and interpretability. CCS CONCEPTS • Computing methodologies → Artificial intelligence; • Applied computing → Health informatics.

show abstract

SoftTriple Loss: Deep Metric Learning Without Triplet Sampling

Cited by 334 publications

References 22 publications

Heterogeneous Double-Head Ensemble for Deep Metric Learning

Heterogeneous Double-Head Ensemble for Deep Metric Learning

Ranked List Loss for Deep Metric Learning

Graph Kernel Prediction of Drug Prescription

Contact Info

Product

Resources

About