Sign in
AttEntropy: Segmenting Unknown Objects in Complex Scenes using the Spatial Attention Entropy of Semantic Segmentation Transformers.
Krzysztof Lis
Matthias Rottmann
Sina Honari
Pascal Fua
Mathieu Salzmann
Published in:
CoRR (2022)
Keyphrases
</>
complex scenes
semantic segmentation
street scenes
multiple objects
computer graphics
spatial information
computer vision
weakly supervised
conditional random fields
superpixels
object classes
scene classification
object recognition
spatial relations