Efficient Image Pre-Training with Siamese Cropped Masked Autoencoders

1 code implementation • 26 Mar 2024 • Alexandre Eymaël, Renaud Vandeghen, Anthony Cioppa, Silvio Giancola, Bernard Ghanem, Marc Van Droogenbroeck

In particular, SiamMAE recently introduced a Siamese network, training a shared-weight encoder from two frames of a video with a high asymmetric masking ratio (95%).

Self-Supervised Learning

Adaptive Self-Training for Object Detection

1 code implementation • 7 Dec 2022 • Renaud Vandeghen, Gilles Louppe, Marc Van Droogenbroeck

In this work, we introduce our method Adaptive Self-Training for Object Detection (ASTOD), which is a simple yet effective teacher-student method.

Object Object Detection +2

Mixture Domain Adaptation to Improve Semantic Segmentation in Real-World Surveillance

1 code implementation • 18 Nov 2022 • Sébastien Piérard, Anthony Cioppa, Anaïs Halin, Renaud Vandeghen, Maxime Zanella, Benoît Macq, Saïd Mahmoudi, Marc Van Droogenbroeck

In this paper, we define a probabilistic framework and present a formal proof of an algorithm for the unsupervised many-to-infinity domain adaptation of posteriors.

Bayesian Inference Domain Adaptation +1

Semi-Supervised Training to Improve Player and Ball Detection in Soccer

1 code implementation • 14 Apr 2022 • Renaud Vandeghen, Anthony Cioppa, Marc Van Droogenbroeck

More precisely, we design a teacher-student approach in which the teacher produces surrogate annotations on the unlabeled data to be used later for training a student which has the same architecture as the teacher.