000267190 001__ 267190
000267190 005__ 20190812204804.0
000267190 020__ $$a978-1-7281-1975-5
000267190 022__ $$a2472-6737
000267190 0247_ $$a10.1109/WACV.2019.00047$$2doi
000267190 02470 $$2isi$$a000469423400040
000267190 037__ $$aCONF
000267190 245__ $$aDeep Micro-Dictionary Learning and Coding Network
000267190 269__ $$a2019-01-01
000267190 260__ $$c2019-01-01$$bIEEE$$aNew York
000267190 336__ $$aConference Papers
000267190 490__ $$aIEEE Winter Conference on Applications of Computer Vision
000267190 520__ $$aIn this paper, we propose a novel Deep Micro-Dictionary Learning and Coding Network (DDLCN). DDLCN has most of the standard deep learning layers (pooling, fully, connected, input/output, etc.) but the main difference is that the fundamental convolutional layers are replaced by novel compound dictionary learning and coding layers. The dictionary learning layer learns an over-complete dictionary for the input training data. At the deep coding layer, a locality constraint is added to guarantee that the activated dictionary bases are close to each other. Next, the activated dictionary atoms are assembled together and passed to the next compound dictionary learning and coding layers. In this way, the activated atoms in the first layer can be represented by the deeper atoms in the second dictionary. Intuitively, the second dictionary is designed to learn the fine-grained components which are shared among the input dictionary atoms. In this way, a more informative and discriminative low-level representation of the dictionary atoms can be obtained. We empirically compare the proposed DDLCN with several dictionary learning methods and deep learning architectures. The experimental results on four popular benchmark datasets demonstrate that the proposed DDLCN achieves competitive results compared with state-of-the-art approaches.
000267190 650__ $$aEngineering, Electrical & Electronic
000267190 650__ $$aEngineering
000267190 6531_ $$aface recognition
000267190 6531_ $$aimage
000267190 700__ $$aTang, Hao
000267190 700__ $$aWei, Heng
000267190 700__ $$aXiao, Wei
000267190 700__ $$g296697$$aWang, Wei
000267190 700__ $$aXu, Dan
000267190 700__ $$aYan, Yan
000267190 700__ $$aSebe, Nicu
000267190 7112_ $$a19th IEEE Winter Conference on Applications of Computer Vision (WACV)$$dJan 07-11, 2019$$cWaikoloa Village, HI
000267190 773__ $$q386-395$$t2019 IEEE Winter Conference On Applications Of Computer Vision (Wacv)
000267190 8560_ $$fbeatrice.marselli@epfl.ch
000267190 909CO $$pconf$$ooai:infoscience.epfl.ch:267190
000267190 961__ $$abeatrice.marselli@epfl.ch
000267190 973__ $$rREVIEWED$$aEPFL
000267190 981__ $$aoverwrite
000267190 980__ $$aCONF
000267190 999C0 $$zGrolimund, Raphael$$xU10659$$pCVLAB$$mpascal.fua@epfl.ch$$0252087