3 citations · 8 across the 8 of their papers we have counts for
6 papers · 1 filter
On Explaining Knowledge Distillation: Measuring and Visualising the Knowledge Transfer Process
Gereziher Adhane, Mohammad Mahdi Dehshibi, Dennis Vetter +2
Knowledge distillation (KD) remains challenging due to the opaque nature of the knowledge transfer process from a Teacher to a Student, making it difficult to address certain issue…
Learning Object Semantic Similarity with Self-Supervision
Arthur Aubret, Timothy Schaumlöffel, Gemma Roig +1
Humans judge the similarity of two objects not just based on their visual appearance but also based on their semantic relatedness. However, it remains unclear how humans learn abou…
Caregiver Talk Shapes Toddler Vision: A Computational Study of Dyadic Play
Timothy Schaumlöffel, Arthur Aubret, Gemma Roig +1
Infants' ability to recognize and categorize objects develops gradually. The second year of life is marked by both the emergence of more semantic visual representations and a bette…
Learning Class and Domain Augmentations for Single-Source Open-Domain Generalization
Prathmesh Bele, Valay Bundele, Avigyan Bhattacharya +3
Single-source open-domain generalization (SS-ODG) addresses the challenge of labeled source domains with supervision during training and unlabeled novel target domains during testi…
Herding Generalizes Diverse M -Best Solutions
Ece Ozkan, Gemma Roig, Orcun Goksel +1
We show that the algorithm to extract diverse M -solutions from a Conditional Random Field (called divMbest [1]) takes exactly the form of a Herding procedure [2], i.e. a determini…
Comment on "Ensemble Projection for Semi-supervised Image Classification"
Xavier Boix, Gemma Roig, Luc Van Gool
In a series of papers by Dai and colleagues [1,2], a feature map (or kernel) was introduced for semi- and unsupervised learning. This feature map is build from the output of an ens…