429 citations · 825 across the 14 of their papers we have counts for
15 papers
Segmenting, Fast and Slow: Real-Time Open-Vocabulary Video Instance Segmentation with Dual-Path Processing
Luca Barsellotti, Martin Sundermeyer, Mattia Segu +5
Object-centric models inspired by DETR have become the dominant paradigm for open-vocabulary video instance segmentation (OV-VIS). While recent efforts have reduced the computation…
Revisiting Evaluation Metrics for Semantic Segmentation: Optimization and Evaluation of Fine-grained Intersection over Union
Zifu Wang, Maxim Berman, Amal Rannen-Triki +6
Semantic segmentation datasets often exhibit two types of imbalance: \textit{class imbalance}, where some classes appear more frequently than others and \textit{size imbalance}, wh…
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…
Optimization for Medical Image Segmentation: Theory and Practice when evaluating with Dice Score or Jaccard Index
Tom Eelbode, Jeroen Bertels, Maxim Berman +4
In many medical imaging and classical computer vision tasks, the Dice score and Jaccard index are used to evaluate the segmentation performance. Despite the existence and great emp…
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…
Discriminative training of conditional random fields with probably submodular constraints
Maxim Berman, Matthew B. Blaschko
Problems of segmentation, denoising, registration and 3D reconstruction are often addressed with the graph cut algorithm. However, solving an unconstrained graph cut problem is NP-…
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…
Yes, IoU loss is submodular - as a function of the mispredictions
Maxim Berman, Matthew B. Blaschko, Amal Rannen Triki +1
This note is a response to [7] in which it is claimed that [13, Proposition 11] is false. We demonstrate here that this assertion in [7] is false, and is based on a misreading of t…
Supermodular Locality Sensitive Hashes
Maxim Berman, Matthew B. Blaschko
In this work, we show deep connections between Locality Sensitive Hashability and submodular analysis. We show that the LSHablility of the most commonly analyzed set similarities i…
Efficient semantic image segmentation with superpixel pooling
Mathijs Schuurmans, Maxim Berman, Matthew B. Blaschko
In this work, we evaluate the use of superpixel pooling layers in deep network architectures for semantic segmentation. Superpixel pooling is a flexible and efficient replacement f…
Function Norms and Regularization in Deep Networks
Amal Rannen Triki, Maxim Berman, Matthew B. Blaschko
Deep neural networks (DNNs) have become increasingly important due to their excellent empirical performance on a wide range of problems. However, regularization is generally achiev…
The Lovász-Softmax loss: A tractable surrogate for the optimization of the intersection-over-union measure in neural networks
Maxim Berman, Amal Rannen Triki, Matthew B. Blaschko
The Jaccard index, also referred to as the intersection-over-union score, is commonly employed in the evaluation of image segmentation results given its perceptual qualities, scale…