429 citations · 467 across the 6 of their papers we have counts for
7 papers · 1 filter
Spatial Consistency Loss for Training Multi-Label Classifiers from Single-Label Annotations
Thomas Verelst, Paul K. Rubenstein, Marcin Eichner +2
As natural images usually contain multiple objects, multi-label image classification is more applicable "in the wild" than single-label classification. However, exhaustively annota…
AOWS: Adaptive and optimal network width search with latency constraints
Maxim Berman, Leonid Pishchulin, Ning Xu +2
Neural architecture search (NAS) approaches aim at automatically finding novel CNN architectures that fit computational constraints while maintaining a good performance on the targ…
Optimizing the Dice Score and Jaccard Index for Medical Image Segmentation: Theory & Practice
Jeroen Bertels, Tom Eelbode, Maxim Berman +4
The Dice score and Jaccard index are commonly used metrics for the evaluation of segmentation tasks in medical imaging. Convolutional neural networks trained for image segmentation…
Adaptive Compression-based Lifelong Learning
Shivangi Srivastava, Maxim Berman, Matthew B. Blaschko +1
The problem of a deep learning model losing performance on a previously learned task when fine-tuned to a new one is a phenomenon known as Catastrophic forgetting. There are two ma…
MultiGrain: a unified image embedding for classes and instances
Maxim Berman, Hervé Jégou, Andrea Vedaldi +2
MultiGrain is a network architecture producing compact vector representations that are suited both for image classification and particular object retrieval. It builds on a standard…
Generating superpixels using deep image representations
Thomas Verelst, Matthew Blaschko, Maxim Berman
Superpixel algorithms are a common pre-processing step for computer vision algorithms such as segmentation, object tracking and localization. Many superpixel methods only rely on c…