research
∙
07/08/2022
Beyond Transfer Learning: Co-finetuning for Action Localisation
Transfer learning is the predominant paradigm for training deep networks...
share
research
∙
08/07/2021
Impact of Aliasing on Generalization in Deep Convolutional Networks
We investigate the impact of aliasing on generalization in Deep Convolut...
research
∙
06/15/2021
Revisiting the Calibration of Modern Neural Networks
Accurate estimation of predictive uncertainty (model calibration) is ess...
research
∙
04/09/2021
SI-Score: An image dataset for fine-grained analysis of robustness to object location, rotation and size
Before deploying machine learning models it is critical to assess their ...
research
∙
10/06/2020
Representation learning from videos in-the-wild: An object-centric approach
We propose a method to learn image representations from uncurated videos...
research
∙
07/16/2020
On Robustness and Transferability of Convolutional Neural Networks
Modern deep convolutional networks (CNNs) are often criticized for not g...
research
∙
07/16/2019
Data Selection for training Semantic Segmentation CNNs with cross-dataset weak supervision
Training convolutional networks for semantic segmentation with strong (p...
research
∙
09/14/2018
A Domain Agnostic Normalization Layer for Unsupervised Adversarial Domain Adaptation
We propose a normalization layer for unsupervised domain adaption in sem...
research
∙
08/19/2017
Applying Deep Bidirectional LSTM and Mixture Density Network for Basketball Trajectory Prediction
Data analytics helps basketball teams to create tactics. However, manual...
research
∙
08/12/2016