Classification of Occluded Objects using Fast Recurrent Processing
Küçük Resim Yok
Tarih
2015
Yazarlar
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
Elsevier Science Bv
Erişim Hakkı
info:eu-repo/semantics/openAccess
Özet
Recurrent neural networks are powerful tools for handling incomplete data problems in computer vision, thanks to their significant generative capabilities. However, the computational demand for these algorithms is too high to work in real time, without specialized hardware or software solutions. In this paper, we propose a framework for augmenting recurrent processing capabilities into a feedforward network without sacrificing much from computational efficiency. We assume a mixture model and generate samples of the last hidden layer according to the class decisions of the output layer, modify the hidden layer activity using the samples, and propagate to lower layers. For visual occlusion problem, the iterative procedure emulates feedforward-feedback loop, filling-in the missing hidden layer activity with meaningful representations. The proposed algorithm is tested on a widely used dataset and shown to achieve 2x improvement in classification accuracy for occluded objects. When compared to Restricted Boltzmann Machines, our algorithm shows superior performance for occluded object classification.
Açıklama
IEEE 14th International Conference on Machine Learning and Applications ICMLA -- DEC 09-11, 2015 -- Miami, FL
Anahtar Kelimeler
Recurrent Processing; Occlusions; Neural Networks
Kaynak
2015 Ieee 14th International Conference On Machine Learning And Applications (Icmla)
WoS Q Değeri
N/A
Scopus Q Değeri
N/A
