24 citations · 27 across the 4 of their papers we have counts for
4 papers
Self-Supervised Learning with a Multi-Task Latent Space Objective
Pierre-François De Plaen, Abhishek Jha, Luc Van Gool +2
We propose a multi-task formulation of self-predictive Siamese SSL in which each spatial transformation defines a distinct latent-space alignment task, solved by a dedicated predic…
Adversarial Dependence Minimization
Pierre-François De Plaen, Tinne Tuytelaars, Marc Proesmans +1
Minimally redundant representations are typically learned by minimizing feature covariance. However, covariance-based methods fail to eliminate all dependencies/redundancies, as li…
Contrastive Learning for Multi-Object Tracking with Transformers
Pierre-François De Plaen, Nicola Marinello, Marc Proesmans +2
The DEtection TRansformer (DETR) opened new possibilities for object detection by modeling it as a translation task: converting image features into object-level representations. Pr…
Unbalanced Optimal Transport: A Unified Framework for Object Detection
Henri De Plaen, Pierre-François De Plaen, Johan A. K. Suykens +3
During training, supervised object detection tries to correctly match the predicted bounding boxes and associated classification scores to the ground truth. This is essential to de…