activity
20172021
most citedUnderstanding when spatial transformer networks do not support invariance, and what to do about it

24 citations · 60 across the 5 of their papers we have counts for

collaborators

6 papers

cs.CV2021★ 20 cited

Scale-invariant scale-channel networks: Deep networks that generalise to previously unseen scales

Ylva Jansson, Tony Lindeberg

The ability to handle large scale variations is crucial for many real world visual tasks. A straightforward approach for handling scale in a deep network is to process an image at…

cs.CV2020★ 3 cited

Inability of spatial transformations of CNN feature maps to support invariant recognition

Ylva Jansson, Maksim Maydanskiy, Lukas Finnveden +1

A large number of deep learning architectures use spatial transformations of CNN feature maps or filters to better deal with variability in object appearance caused by natural imag…

cs.CV2020★ 24 cited

Understanding when spatial transformer networks do not support invariance, and what to do about it

Lukas Finnveden, Ylva Jansson, Tony Lindeberg

Spatial transformer networks (STNs) were designed to enable convolutional neural networks (CNNs) to learn invariance to image transformations. STNs were originally proposed to tran…

cs.CV2020★ 12 cited

Exploring the ability of CNNs to generalise to previously unseen scales over wide scale ranges

Ylva Jansson, Tony Lindeberg

The ability to handle large scale variations is crucial for many real world visual tasks. A straightforward approach for handling scale in a deep network is to process an image at…

cs.CV2020★ 1 cited

The problems with using STNs to align CNN feature maps

Lukas Finnveden, Ylva Jansson, Tony Lindeberg

Spatial transformer networks (STNs) were designed to enable CNNs to learn invariance to image transformations. STNs were originally proposed to transform CNN feature maps as well a…

cs.CV2017

Dynamic texture recognition using time-causal and time-recursive spatio-temporal receptive fields

Ylva Jansson, Tony Lindeberg

This work presents a first evaluation of using spatio-temporal receptive fields from a recently proposed time-causal spatio-temporal scale-space framework as primitives for video a…