Learning Surrogates via Deep Embedding
The result's identifiers
Result code in 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>
Result on the web
<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>
Alternative languages
Result language
angličtina
Original language name
Learning Surrogates via Deep Embedding
Original language description
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.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
<a href="/en/project/EF16_019%2F0000765" target="_blank" >EF16_019/0000765: Research Center for Informatics</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach
Others
Publication year
2020
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Computer Vision - ECCV 2020, Part XXX
ISBN
978-3-030-58576-1
ISSN
0302-9743
e-ISSN
1611-3349
Number of pages
17
Pages from-to
205-221
Publisher name
Springer International Publishing
Place of publication
Cham
Event location
Glasgow
Event date
Aug 23, 2020
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—