Silvia Laura Pintea

Silvia Laura Pintea

Auto-generated profile, based on publicly available information

Silvia Laura Pintea

Delft University of Technology

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
10 October 2018 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
TSTobias Stahl
Tobias Stahl
SPSilvia L. Pintea
Silvia L. Pintea
JGJan C. van Gemert
Jan C. van Gemert
We propose a general object counting method that does not use any prior category information. We learn from local image divisions to predict global image-level counts without using any form of local annotations. Our method separates the input image into a set of image divisions—each fully covering the image. Each image division is composed of a set of region proposals or uniform grid cells. Our approach learns in an end-to-end deep learning architecture to predict global image-level counts from local image divisions. The method incorporates a counting layer which predicts object counts in the complete image, by enforcing consistency in counts when dealing with overlapping image regions. Our counting layer is based on the inclusion–exclusion principle from set theory. We analyze the individual building blocks of our proposed approach on Pascal-VOC2007 and evaluate our method on the MS-COCO large scale generic object data set as well as on three class-specific counting data sets: UCSD pedestrian data set, and CARPK, and PUCPR+ car data sets.

17 November 2020
Verified
Book Chapter
Closed access
PDF file
YLYancong Lin
Yancong Lin
SPSilvia L. Pintea
Silvia L. Pintea
JGJan C. van Gemert
Jan C. van Gemert

29 September 2021 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
SPSilvia L. Pintea
Silvia L. Pintea
NTNergis Tomen
Nergis Tomen
SGStanley F. Goes
Stanley F. Goes
MLMarco Loog
Marco Loog
JGJan C. van Gemert
Jan C. van Gemert
Resolution in deep convolutional neural networks (CNNs) is typically bounded by the receptive field size through filter sizes, and subsampling layers or strided convolutions on feature maps. The optimal resolution may vary significantly depending on the dataset. Modern CNNs hard-code their resolution hyper-parameters in the network architecture which makes tuning such hyper-parameters cumbersome. We propose to do away with hard-coded resolution hyper-parameters and aim to learn the appropriate resolution from data. We use scale-space theory to obtain a self-similar parametrization of filters and make use of the N-Jet: a truncated Taylor series to approximate a filter by a learned combination of Gaussian derivative filters. The parameter $\sigma $ of the Gaussian basis controls both the amount of detail the filter encodes and the spatial extent of the filter. Since $\sigma $ is a continuous parameter, we can optimize it with respect to the loss. The proposed N-Jet layer achieves comparable performance when used in state-of-the art architectures, while learning the correct resolution in each layer automatically. We evaluate our N-Jet layer on both classification and segmentation, and we show that learning $\sigma $ is especially beneficial when dealing with inputs at multiple sizes.

23 January 2019
Verified
Book Chapter
Closed access
PDF file
SPSilvia L. Pintea
Silvia L. Pintea
JZJian Zheng
Jian Zheng
XLXilin Li
Xilin Li
PBPaulina J. M. Bank
Paulina J. M. Bank
JHJacobus J. van Hilten
Jacobus J. van Hilten
JGJan C. van Gemert
Jan C. van Gemert

21 December 2021 in Computational Geosciences
Verified
Journal Article
Open access
PDF file
SPSilvia L. Pintea
Silvia L. Pintea
SSSiddharth Sharma
Siddharth Sharma
FVFemke C. Vossepoel
Femke C. Vossepoel
JGJan C. van Gemert
Jan C. van Gemert
MLMarco Loog
Marco Loog
DVDirk J. Verschuur
Dirk J. Verschuur
This article investigates bypassing the inversion steps involved in a standard litho-type classification pipeline and performing the litho-type classification directly from imaged seismic data. We consider a set of deep learning methods that map the seismic data directly into litho-type classes, trained on two variants of synthetic seismic data: (i) one in which we image the seismic data using a local Radon transform to obtain angle gathers, (ii) and another in which we start from the subsurface-offset gathers, based on correlations over the seismic data. Our results indicate that this single-step approach provides a faster alternative to the established pipeline while being convincingly accurate. We observe that adding the background model as input to the deep network optimization is essential in correctly categorizing litho-types. Also, starting from the angle gathers obtained by imaging in the Radon domain is more informative than using the subsurface offset gathers as input.

24 November 2016
Verified
Book Chapter
Closed access
PDF file
SPS. L. Pintea
S. L. Pintea
JGJ. C. van Gemert
J. C. van Gemert