13 citations · 13 across the 1 of their papers we have counts for
6 papers
FroDO: From Detections to 3D Objects
Kejie Li, Martin Rünz, Meng Tang +8
Object-oriented maps are important for scene understanding since they jointly capture geometry and semantics, allow individual instantiation and meaningful reasoning about objects.…
Beyond Gradient Descent for Regularized Segmentation Losses
Dmitrii Marin, Meng Tang, Ismail Ben Ayed +1
The simplicity of gradient descent (GD) made it the default method for training ever-deeper and complex neural networks. Both loss functions and architectures are often explicitly…
Constrained-CNN losses for weakly supervised segmentation
Hoel Kervadec, Jose Dolz, Meng Tang +3
Weakly-supervised learning based on, e.g., partially labelled images or image-tags, is currently attracting significant attention in CNN segmentation as it can mitigate the need fo…
On Regularized Losses for Weakly-supervised CNN Segmentation
Meng Tang, Federico Perazzi, Abdelaziz Djelouah +3
Minimization of regularized losses is a principled approach to weak supervision well-established in deep learning, in general. However, it is largely overlooked in semantic segment…
Normalized Cut Loss for Weakly-supervised CNN Segmentation
Meng Tang, Abdelaziz Djelouah, Federico Perazzi +2
Most recent semantic segmentation methods train deep convolutional neural networks with fully annotated masks requiring pixel-accuracy for good quality training. Common weakly-supe…
Kernel clustering: density biases and solutions
Dmitrii Marin, Meng Tang, Ismail Ben Ayed +1
Kernel methods are popular in clustering due to their generality and discriminating power. However, we show that many kernel clustering criteria have density biases theoretically e…