3 papers
cs.CV2020
Spatial Attention as an Interface for Image Captioning Models
Philipp Sadler
The internal workings of modern deep learning models stay often unclear to an external observer, although spatial attention mechanisms are involved. The idea of this work is to tra…
cs.CL2019
Can Neural Image Captioning be Controlled via Forced Attention?
Philipp Sadler, Tatjana Scheffler, David Schlangen
Learned dynamic weighting of the conditioning signal (attention) has been shown to improve neural language generation in a variety of settings. The weights applied when generating…
cs.CV2018
Detecting cities in aerial night-time images by learning structural invariants using single reference augmentation
Philipp Sadler
This paper examines, if it is possible to learn structural invariants of city images by using only a single reference picture when producing transformations along the variants in t…