1.7k citations · 1.9k across the 16 of their papers we have counts for
11 papers · 1 filter
Sit Back and Relax: Learning to Drive Incrementally in All Weather Conditions
Stefan Leitner, M. Jehanzeb Mirza, Wei Lin +5
In autonomous driving scenarios, current object detection models show strong performance when tested in clear weather. However, their performance deteriorates significantly when te…
An Efficient Domain-Incremental Learning Approach to Drive in All Weather Conditions
M. Jehanzeb Mirza, Marc Masana, Horst Possegger +1
Although deep neural networks enable impressive visual perception performance for autonomous driving, their robustness to varying weather conditions still requires attention. When…
Disentanglement of Color and Shape Representations for Continual Learning
David Berga, Marc Masana, Joost Van de Weijer
We hypothesize that disentangled feature representations suffer less from catastrophic forgetting. As a case study we perform explicit disentanglement of color and shape, by adjust…
On Class Orderings for Incremental Learning
Marc Masana, Bartłomiej Twardowski, Joost van de Weijer
The influence of class orderings in the evaluation of incremental learning has received very little attention. In this paper, we investigate the impact of class orderings for incre…
Ternary Feature Masks: zero-forgetting for task-incremental learning
Marc Masana, Tinne Tuytelaars, Joost van de Weijer
We propose an approach without any forgetting to continual learning for the task-aware regime, where at inference the task-label is known. By using ternary masks we can upgrade a m…
A continual learning survey: Defying forgetting in classification tasks
Matthias De Lange, Rahaf Aljundi, Marc Masana +5
Artificial neural networks thrive in solving the classification problem for a particular rigid task, acquiring knowledge through generalized learning behaviour from a distinct trai…
Metric Learning for Novelty and Anomaly Detection
Marc Masana, Idoia Ruiz, Joan Serrat +2
When neural networks process images which do not resemble the distribution seen during training, so called out-of-distribution images, they often make wrong predictions, and do so…
Context Proposals for Saliency Detection
Aymen Azaza, Joost van de Weijer, Ali Douik +1
One of the fundamental properties of a salient object region is its contrast with the immediate context. The problem is that numerous object regions exist which potentially can all…
Rotate your Networks: Better Weight Consolidation and Less Catastrophic Forgetting
Xialei Liu, Marc Masana, Luis Herranz +3
In this paper we propose an approach to avoiding catastrophic forgetting in sequential task learning scenarios. Our technique is based on a network reparameterization that approxim…
Domain-adaptive deep network compression
Marc Masana, Joost van de Weijer, Luis Herranz +2
Deep Neural Networks trained on large datasets can be easily transferred to new domains with far fewer labeled examples by a process called fine-tuning. This has the advantage that…
On-the-fly Network Pruning for Object Detection
Marc Masana, Joost van de Weijer, Andrew D. Bagdanov
Object detection with deep neural networks is often performed by passing a few thousand candidate bounding boxes through a deep neural network for each image. These bounding boxes…