4 papers
Class Conditional Alignment for Partial Domain Adaptation
Mohsen Kheirandishfard, Fariba Zohrizadeh, Farhad Kamangar
Adversarial adaptation models have demonstrated significant progress towards transferring knowledge from a labeled source dataset to an unlabeled target dataset. Partial domain ada…
Multi-Level Representation Learning for Deep Subspace Clustering
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 su…
Image Segmentation using Sparse Subset Selection
Fariba Zohrizadeh, Mohsen Kheirandishfard, Farhad Kamangar
In this paper, we present a new image segmentation method based on the concept of sparse subset selection. Starting with an over-segmentation, we adopt local spectral histogram fea…
Natural Scene Image Segmentation Based on Multi-Layer Feature Extraction
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 pro…