| bibtype |
J -
Journal Article
|
| ARLID |
0459332 |
| utime |
20240103212223.9 |
| mtime |
20160513235959.9 |
| SCOPUS |
84966457206 |
| WOS |
000378662600005 |
| DOI |
10.1016/j.dsp.2016.04.012 |
| title
(primary) (eng) |
Fast convolutional sparse coding using matrix inversion lemma |
| specification |
| page_count |
8 s. |
| media_type |
P |
|
| serial |
| ARLID |
cav_un_epca*0252719 |
| ISSN |
1051-2004 |
| title
|
Digital Signal Processing |
| volume_id |
55 |
| volume |
1 (2016) |
| page_num |
44-51 |
| publisher |
|
|
| keyword |
Convolutional sparse coding |
| keyword |
Feature learning |
| keyword |
Deconvolution networks |
| keyword |
Shift-invariant sparse coding |
| author
(primary) |
| ARLID |
cav_un_auth*0108377 |
| full_dept (cz) |
Zpracování obrazové informace |
| full_dept (eng) |
Department of Image Processing |
| department (cz) |
ZOI |
| department (eng) |
ZOI |
| full_dept |
Department of Image Processing |
| name1 |
Šorel |
| name2 |
Michal |
| institution |
UTIA-B |
| fullinstit |
Ústav teorie informace a automatizace AV ČR, v. v. i. |
|
| author
|
| ARLID |
cav_un_auth*0101209 |
| full_dept (cz) |
Zpracování obrazové informace |
| full_dept |
Department of Image Processing |
| department (cz) |
ZOI |
| department |
ZOI |
| full_dept |
Department of Image Processing |
| name1 |
Šroubek |
| name2 |
Filip |
| institution |
UTIA-B |
| fullinstit |
Ústav teorie informace a automatizace AV ČR, v. v. i. |
|
| source |
|
| cas_special |
| project |
| ARLID |
cav_un_auth*0292734 |
| project_id |
GA13-29225S |
| agency |
GA ČR |
|
| abstract
(eng) |
Convolutional sparse coding is an interesting alternative to standard sparse coding in modeling shift-invariant signals, giving impressive results for example in unsupervised learning of visual features. In state-of-the-art methods, the most time-consuming parts include inversion of a linear operator related to convolution. In this article we show how these inversions can be computed non-iteratively in the Fourier domain using the matrix inversion lemma. This greatly speeds up computation and makes convolutional sparse coding computationally feasible even for large problems. The algorithm is derived in three variants, one of them especially suitable for parallel implementation. We demonstrate algorithms on two-dimensional image data but all results hold for signals of arbitrary dimension. |
| RIV |
JD |
| reportyear |
2017 |
| num_of_auth |
2 |
| mrcbC52 |
4 A hod 4ah 20231122141659.8 |
| inst_support |
RVO:67985556 |
| permalink |
http://hdl.handle.net/11104/0259700 |
| mrcbC64 |
1 Department of Image Processing UTIA-B 10200 COMPUTER SCIENCE, THEORY & METHODS |
| confidential |
S |
| mrcbC86 |
1* Article Engineering Electrical Electronic |
| mrcbT16-e |
ENGINEERINGELECTRICALELECTRONIC |
| mrcbT16-j |
0.554 |
| mrcbT16-s |
0.598 |
| mrcbT16-4 |
Q2 |
| mrcbT16-B |
49.689 |
| mrcbT16-D |
Q3 |
| mrcbT16-E |
Q2 |
| arlyear |
2016 |
| mrcbTft |
\nSoubory v repozitáři: sorel-0459332.pdf |
| mrcbU14 |
84966457206 SCOPUS |
| mrcbU34 |
000378662600005 WOS |
| mrcbU63 |
cav_un_epca*0252719 Digital Signal Processing 1051-2004 1095-4333 Roč. 55 č. 1 2016 44 51 Elsevier |
|