96 citations · 209 across the 20 of their papers we have counts for
23 papers
End-to-End Supervised Multilabel Contrastive Learning
Ahmad Sajedi, Samir Khaki, Konstantinos N. Plataniotis +1
Multilabel representation learning is recognized as a challenging problem that can be associated with either label dependencies between object categories or data-related issues suc…
Computational Pathology: A Survey Review and The Way Forward
Mahdi S. Hosseini, Babak Ehteshami Bejnordi, Vincent Quoc-Huy Trinh +18
Computational Pathology CPath is an interdisciplinary science that augments developments of computational approaches to analyze and model medical histopathology images. The main ob…
Pseudo-Inverted Bottleneck Convolution for DARTS Search Space
Arash Ahmadian, Louis S. P. Liu, Yue Fei +2
Differentiable Architecture Search (DARTS) has attracted considerable attention as a gradient-based neural architecture search method. Since the introduction of DARTS, there has be…
Exploiting Explainable Metrics for Augmented SGD
Mahdi S. Hosseini, Mathieu Tuli, Konstantinos N. Plataniotis
Explaining the generalization characteristics of deep learning is an emerging topic in advanced machine learning. There are several unanswered questions about how learning under st…
HistoKT: Cross Knowledge Transfer in Computational Pathology
Ryan Zhang, Jiadai Zhu, Stephen Yang +7
The lack of well-annotated datasets in computational pathology (CPath) obstructs the application of deep learning techniques for classifying medical images. %Since pathologist time…
Towards Robust and Automatic Hyper-Parameter Tunning
Mathieu Tuli, Mahdi S. Hosseini, Konstantinos N. Plataniotis
The task of hyper-parameter optimization (HPO) is burdened with heavy computational costs due to the intractability of optimizing both a model's weights and its hyper-parameters si…
P4AI: Approaching AI Ethics through Principlism
Andre Fu, Elisa Ding, Mahdi S. Hosseini +1
The field of computer vision is rapidly evolving, particularly in the context of new methods of neural architecture design. These models contribute to (1) the Climate Crisis - incr…
NoFADE: Analyzing Diminishing Returns on CO2 Investment
Andre Fu, Justin Tran, Andy Xie +6
Climate change continues to be a pressing issue that currently affects society at-large. It is important that we as a society, including the Computer Vision (CV) community take ste…
In Search of Probeable Generalization Measures
Jonathan Jaegerman, Khalil Damouni, Mahdi S. Hosseini +1
Understanding the generalization behaviour of deep neural networks is a topic of recent interest that has driven the production of many studies, notably the development and evaluat…
CONetV2: Efficient Auto-Channel Size Optimization for CNNs
Yi Ru Wang, Samir Khaki, Weihang Zheng +2
Neural Architecture Search (NAS) has been pivotal in finding optimal network configurations for Convolution Neural Networks (CNNs). While many methods explore NAS from a global sea…
Probeable DARTS with Application to Computational Pathology
Sheyang Tang, Mahdi S. Hosseini, Lina Chen +5
AI technology has made remarkable achievements in computational pathology (CPath), especially with the help of deep neural networks. However, the network performance is highly rela…
CONet: Channel Optimization for Convolutional Neural Networks
Mahdi S. Hosseini, Jia Shu Zhang, Zhe Liu +7
Neural Architecture Search (NAS) has shifted network design from using human intuition to leveraging search algorithms guided by evaluation metrics. We study channel size optimizat…
Reconsidering CO2 emissions from Computer Vision
Andre Fu, Mahdi S. Hosseini, Konstantinos N. Plataniotis
Climate change is a pressing issue that is currently affecting and will affect every part of our lives. It's becoming incredibly vital we, as a society, address the climate crisis…
FocusLiteNN: High Efficiency Focus Quality Assessment for Digital Pathology
Zhongling Wang, Mahdi S. Hosseini, Adyn Miles +2
Out-of-focus microscopy lens in digital pathology is a critical bottleneck in high-throughput Whole Slide Image (WSI) scanning platforms, for which pixel-level automated Focus Qual…
AdaS: Adaptive Scheduling of Stochastic Gradients
Mahdi S. Hosseini, Konstantinos N. Plataniotis
The choice of step-size used in Stochastic Gradient Descent (SGD) optimization is empirically selected in most training procedures. Moreover, the use of scheduled learning techniqu…
A Comprehensive Analysis of Weakly-Supervised Semantic Segmentation in Different Image Domains
Lyndon Chan, Mahdi S. Hosseini, Konstantinos N. Plataniotis
Recently proposed methods for weakly-supervised semantic segmentation have achieved impressive performance in predicting pixel classes despite being trained with only image labels…
On the Closed Form Expression of Elementary Symmetric Polynomials and the Inverse of Vandermonde Matrix
Mahdi S. Hosseini, Alfred Chen, Konstantinos N. Plataniotis
Inverse Vandermonde matrix calculation is a long-standing problem to solve nonsingular linear system where the rows of a square matrix are constructed by progression of…
Focus Quality Assessment of High-Throughput Whole Slide Imaging in Digital Pathology
Mahdi S. Hosseini, Yueyang Zhang, Lyndon Chan +3
One of the challenges facing the adoption of digital pathology workflows for clinical use is the need for automated quality control. As the scanners sometimes determine focus inacc…
Convolutional Deblurring for Natural Imaging
Mahdi S. Hosseini, Konstantinos N. Plataniotis
In this paper, we propose a novel design of image deblurring in the form of one-shot convolution filtering that can directly convolve with naturally blurred images for restoration.…
Encoding Visual Sensitivity by MaxPol Convolution Filters for Image Sharpness Assessment
Mahdi S. Hosseini, Yueyang Zhang, Konstantinos N. Plataniotis
In this paper, we propose a novel design of Human Visual System (HVS) response in a convolution filter form to decompose meaningful features that are closely tied with image sharpn…
Finite Differences in Forward and Inverse Imaging Problems--MaxPol Design
Mahdi S. Hosseini, Konstantinos N. Plataniotis
A systematic and comprehensive framework for finite impulse response (FIR) lowpass/fullband derivative kernels is introduced in this paper. Closed form solutions of a number of der…
High-Accuracy Total Variation for Compressed Video Sensing
Mahdi S. Hosseini, Konstantinos N. Plataniotis
Numerous total variation (TV) regularizers, engaged in image restoration problem, encode the gradients by means of simple FIR filter. Despite its low computational process…
Compressed Sensing Recoverability In Imaging Modalities
Mahdi S. Hosseini, Konstantinos N. Plataniotis
The paper introduces a framework for the recoverability analysis in compressive sensing for imaging applications such as CI cameras, rapid MRI and coded apertures. This is done usi…