1 code implementation • 18 Jun 2020 • Mohsen Kheirandishfard, Fariba Zohrizadeh, Farhad Kamangar
This paper is concerned with developing a novel approach to tackle the problem of subspace clustering.
no code implementations • 14 Mar 2020 • Mohsen Kheirandishfard, Fariba Zohrizadeh, Farhad Kamangar
Partial domain adaptation (PDA) investigates the scenarios in which the source domain is large and diverse, and the target label space is a subset of the source label space.
1 code implementation • 19 Jan 2020 • Mohsen Kheirandishfard, Fariba Zohrizadeh, Farhad Kamangar
This paper proposes a novel deep subspace clustering approach which uses convolutional autoencoders to transform input images into new representations lying on a union of linear subspaces.
1 code implementation • 8 Apr 2018 • Fariba Zohrizadeh, Mohsen Kheirandishfard, Farhad Kamangar
Then, the superpixel features are fed into a novel convex model which efficiently leverages the features to group the superpixels into a proper number of coherent regions.
no code implementations • 24 May 2016 • Fariba Zohrizadeh, Mohsen Kheirandishfard, Farhad Kamangar
This paper addresses the problem of natural image segmentation by extracting information from a multi-layer array which is constructed based on color, gradient, and statistical properties of the local neighborhoods in an image.