Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat
Cited by 1,106

The DOI matches its Crossref record; 16 of the 16 references it cites were found in a registry or an index.

Additive Margin Softmax for Face Verification

Open access
Wang, Feng, Cheng, Jian, Liu, Weiyang, Liu, Haijun · 2018 · IEEE Signal Processing Letters

Abstract

In this letter, we propose a conceptually simple and intuitive learning objective function, i.e., additive margin softmax, for face verification. In general, face verification tasks can be viewed as metric learning problems, even though lots of face verification models are trained in classification schemes. It is possible when a large-margin strategy is introduced into the classification model to encourage intraclass variance minimization. As one alternative, angular softmax has been proposed to incorporate the margin. In this letter, we introduce another kind of margin to the softmax loss function, which is more intuitive and interpretable. Experiments on LFW and MegaFace show that our algorithm performs better when the evaluation criteria are designed for very low false alarm rate.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/lsp.2018.2822810

Cites

16 of 16 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Research works printed but not linked: 5

  1. liu, 0, Large-margin softmax loss for convolutional neural networks, Proc 33rd Int Conf Mach Learn, 507
  2. liu, 0, Deep hyperspherical learning, Proc Advances Neural Inf Process Syst, 3953
  3. liu, 0, Rethinking feature discrimination and polymerization for large-scale recognition, Proc Adv Neural Inf Process Syst
  4. parkhi, 0, Deep face recognition, Proc Br Mach Vis Conf, 1, 41.1
  5. liang, 0, Soft-margin softmax for deep classification, Proc 24th Int Conf Neural Inf Process, 413

Cited by

See all 1,106

Metadata

Authors
Wang, F., Cheng, J., Liu, W., & Liu, H.
Venue
IEEE Signal Processing Letters
Published
2018-07
Volume
25
Issue
7
Pages
926-930
ISSN
  • 1070-9908 (ISSN-L)
  • 1558-2361
OpenAlex
W2784163702
Cited by
1,106
References
16
FWCI
53.09
Type
journal article
Language
en
Open access
green
Funders
  • National Natural Science Foundation of China (61671125, 61201271, 61301269)
  • State Key Laboratory of Synthetical Automation for Process Industries (PAL-N201401)

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.