no code implementations • 11 Jun 2021 • Ylva Jansson, Tony Lindeberg
We then propose a new type of foveated scale channel architecture}, where the scale channels process increasingly larger parts of the image with decreasing resolution.
Ranked #1 on Scale Generalisation on MNIST Large Scale dataset
no code implementations • 30 Apr 2020 • Ylva Jansson, Maksim Maydanskiy, Lukas Finnveden, Tony Lindeberg
In this paper, we prove that spatial transformations of CNN feature maps cannot align the feature maps of a transformed image to match those of its original, for general affine transformations, unless the extracted features are themselves invariant.
1 code implementation • 24 Apr 2020 • Lukas Finnveden, Ylva Jansson, Tony Lindeberg
This enables the use of more complex features when predicting transformation parameters.
no code implementations • 3 Apr 2020 • Ylva Jansson, Tony Lindeberg
The ability to handle large scale variations is crucial for many real world visual tasks.
no code implementations • 14 Jan 2020 • Lukas Finnveden, Ylva Jansson, Tony Lindeberg
Spatial transformer networks (STNs) were designed to enable CNNs to learn invariance to image transformations.
no code implementations • 13 Oct 2017 • Ylva Jansson, Tony Lindeberg
We propose a new family of video descriptors based on regional statistics of spatio-temporal receptive field responses and evaluate this approach on the problem of dynamic texture recognition.