Learning Surrogates via Deep Embedding

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F20%3A00342588" target="_blank" >RIV/68407700:21230/20:00342588 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1007/978-3-030-58577-8_13" target="_blank" >https://doi.org/10.1007/978-3-030-58577-8_13</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-030-58577-8_13" target="_blank" >10.1007/978-3-030-58577-8_13</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Learning Surrogates via Deep Embedding

Popis výsledku v původním jazyce

This paper proposes a technique for training a neural network by minimizing a surrogate loss that approximates the target evaluation metric, which may be non-differentiable. The surrogate is learned via a deep embedding where the Euclidean distance between the prediction and the ground truth corresponds to the value of the evaluation metric. The effectiveness of the proposed technique is demonstrated in a post-tuning setup, where a trained model is tuned using the learned surrogate. Without a significant computational overhead and any bells and whistles, improvements are demonstrated on challenging and practical tasks of scene-text recognition and detection. In the recognition task, the model is tuned using a surrogate approximating the edit distance metric and achieves up to 39% relative improvement in the total edit distance. In the detection task, the surrogate approximates the intersection over union metric for rotated bounding boxes and yields up to 4.25% relative improvement in the F1 score.

Název v anglickém jazyce

Learning Surrogates via Deep Embedding

Popis výsledku anglicky

This paper proposes a technique for training a neural network by minimizing a surrogate loss that approximates the target evaluation metric, which may be non-differentiable. The surrogate is learned via a deep embedding where the Euclidean distance between the prediction and the ground truth corresponds to the value of the evaluation metric. The effectiveness of the proposed technique is demonstrated in a post-tuning setup, where a trained model is tuned using the learned surrogate. Without a significant computational overhead and any bells and whistles, improvements are demonstrated on challenging and practical tasks of scene-text recognition and detection. In the recognition task, the model is tuned using a surrogate approximating the edit distance metric and achieves up to 39% relative improvement in the total edit distance. In the detection task, the surrogate approximates the intersection over union metric for rotated bounding boxes and yields up to 4.25% relative improvement in the F1 score.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/EF16_019%2F0000765" target="_blank" >EF16_019/0000765: Výzkumné centrum informatiky</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2020

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Computer Vision - ECCV 2020, Part XXX

ISBN

978-3-030-58576-1

ISSN

0302-9743

e-ISSN

1611-3349

Počet stran výsledku

17

Strana od-do

205-221

Název nakladatele

Springer International Publishing

Místo vydání

Cham

Místo konání akce

Glasgow

Datum konání akce

23. 8. 2020

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—