Search Results for author:
Found 6 papers, 1 papers with code
Scale-invariant scale-channel networks: Deep networks that generalise to previously unseen scales
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
Inability of spatial transformations of CNN feature maps to support invariant recognition
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.
Understanding when spatial transformer networks do not support invariance, and what to do about it
This enables the use of more complex features when predicting transformation parameters.
Exploring the ability of CNNs to generalise to previously unseen scales over wide scale ranges
The ability to handle large scale variations is crucial for many real world visual tasks.
The problems with using STNs to align CNN feature maps
Spatial transformer networks (STNs) were designed to enable CNNs to learn invariance to image transformations.
Dynamic texture recognition using time-causal and time-recursive spatio-temporal receptive fields
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.
