546 citations · 570 across the 4 of their papers we have counts for
5 papers
Appearance invariance in convolutional networks with neighborhood similarity
Tolga Tasdizen, Mehdi Sajjadi, Mehran Javanmardi +1
We present a neighborhood similarity layer (NSL) which induces appearance invariance in a network when used in conjunction with convolutional layers. We are motivated by the observ…
SSHMT: Semi-supervised Hierarchical Merge Tree for Electron Microscopy Image Segmentation
Ting Liu, Miaomiao Zhang, Mehran Javanmardi +2
Region-based methods have proven necessary for improving segmentation accuracy of neuronal structures in electron microscopy (EM) images. Most region-based segmentation methods use…
Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learning
Mehdi Sajjadi, Mehran Javanmardi, Tolga Tasdizen
Effective convolutional neural networks are trained on large sets of labeled data. However, creating large labeled datasets is a very costly and time-consuming task. Semi-supervise…
Mutual Exclusivity Loss for Semi-Supervised Deep Learning
Mehdi Sajjadi, Mehran Javanmardi, Tolga Tasdizen
In this paper we consider the problem of semi-supervised learning with deep Convolutional Neural Networks (ConvNets). Semi-supervised learning is motivated on the observation that…
Unsupervised Total Variation Loss for Semi-supervised Deep Learning of Semantic Segmentation
Mehran Javanmardi, Mehdi Sajjadi, Ting Liu +1
We introduce a novel unsupervised loss function for learning semantic segmentation with deep convolutional neural nets (ConvNet) when densely labeled training images are not availa…