69 citations · 120 across the 12 of their papers we have counts for
12 papers
Neural Architecture Search by Learning a Hierarchical Search Space
Mehraveh Javan Roshtkhari, Matthew Toews, Marco Pedersoli
Monte-Carlo Tree Search (MCTS) is a powerful tool for many non-differentiable search related problems such as adversarial games. However, the performance of such approach highly de…
Balanced Mixture of SuperNets for Learning the CNN Pooling Architecture
Mehraveh Javan, Matthew Toews, Marco Pedersoli
Downsampling layers, including pooling and strided convolutions, are crucial components of the convolutional neural network architecture that determine both the granularity/scale o…
Boundary-aware Information Maximization for Self-supervised Medical Image Segmentation
Jizong Peng, Ping Wang, Marco Pedersoli +1
Unsupervised pre-training has been proven as an effective approach to boost various downstream tasks given limited labeled data. Among various methods, contrastive learning learns…
Diversified Multi-prototype Representation for Semi-supervised Segmentation
Jizong Peng, Christian Desrosiers, Marco Pedersoli
This work considers semi-supervised segmentation as a dense prediction problem based on prototype vector correlation and proposes a simple way to represent each segmentation class…
Self-Paced Contrastive Learning for Semi-supervised Medical Image Segmentation with Meta-labels
Jizong Peng, Ping Wang, Chrisitian Desrosiers +1
Pre-training a recognition model with contrastive learning on a large dataset of unlabeled data has shown great potential to boost the performance of a downstream task, e.g., image…
Context-aware virtual adversarial training for anatomically-plausible segmentation
Ping Wang, Jizong Peng, Marco Pedersoli +3
Despite their outstanding accuracy, semi-supervised segmentation methods based on deep neural networks can still yield predictions that are considered anatomically impossible by cl…
Boosting Semi-supervised Image Segmentation with Global and Local Mutual Information Regularization
Jizong Peng, Marco Pedersoli, Christian Desrosiers
The scarcity of labeled data often impedes the application of deep learning to the segmentation of medical images. Semi-supervised learning seeks to overcome this limitation by exp…
Self-paced and self-consistent co-training for semi-supervised image segmentation
Ping Wang, Jizong Peng, Marco Pedersoli +3
Deep co-training has recently been proposed as an effective approach for image segmentation when annotated data is scarce. In this paper, we improve existing approaches for semi-su…
Information based Deep Clustering: An experimental study
Jizong Peng, Christian Desrosiers, Marco Pedersoli
Recently, two methods have shown outstanding performance for clustering images and jointly learning the feature representation. The first, called Information Maximiz-ing Self-Augme…
Discretely-constrained deep network for weakly supervised segmentation
Jizong Peng, Hoel Kervadec, Jose Dolz +3
An efficient strategy for weakly-supervised segmentation is to impose constraints or regularization priors on target regions. Recent efforts have focused on incorporating such cons…
Deep Co-Training for Semi-Supervised Image Segmentation
Jizong Peng, Guillermo Estrada, Marco Pedersoli +1
In this paper, we aim to improve the performance of semantic image segmentation in a semi-supervised setting in which training is effectuated with a reduced set of annotated images…
Modeling Information Flow Through Deep Neural Networks
Ahmad Chaddad, Behnaz Naisiri, Marco Pedersoli +3
This paper proposes a principled information theoretic analysis of classification for deep neural network structures, e.g. convolutional neural networks (CNN). The output of convol…