6 citations · 11 across the 4 of their papers we have counts for
6 papers
Occlusion-Ordered Semantic Instance Segmentation
Soroosh Baselizadeh, Cheuk-To Yu, Olga Veksler +1
Standard semantic instance segmentation provides useful, but inherently 2D information from a single image. To enable 3D analysis, one usually integrates absolute monocular depth e…
Towards Semantic Interpretation of Thoracic Disease and COVID-19 Diagnosis Models
Ashkan Khakzar, Sabrina Musatian, Jonas Buchberger +5
Convolutional neural networks are showing promise in the automatic diagnosis of thoracic pathologies on chest x-rays. Their black-box nature has sparked many recent works to explai…
Neural Response Interpretation through the Lens of Critical Pathways
Ashkan Khakzar, Soroosh Baselizadeh, Saurabh Khanduja +3
Is critical input information encoded in specific sparse pathways within the neural network? In this work, we discuss the problem of identifying these critical pathways and subsequ…
Rethinking Positive Aggregation and Propagation of Gradients in Gradient-based Saliency Methods
Ashkan Khakzar, Soroosh Baselizadeh, Nassir Navab
Saliency methods interpret the prediction of a neural network by showing the importance of input elements for that prediction. A popular family of saliency methods utilize gradient…
Multiresolution Knowledge Distillation for Anomaly Detection
Mohammadreza Salehi, Niousha Sadjadi, Soroosh Baselizadeh +2
Unsupervised representation learning has proved to be a critical component of anomaly detection/localization in images. The challenges to learn such a representation are two-fold.…
Improving Feature Attribution through Input-specific Network Pruning
Ashkan Khakzar, Soroosh Baselizadeh, Saurabh Khanduja +3
Attributing the output of a neural network to the contribution of given input elements is a way of shedding light on the black-box nature of neural networks. Due to the complexity…