Learns adaptive aggregation of intermediate features from SE-ResNeXt-50 to map images to multi-subject fMRI/MEG activity, ranking top-5 in Algonauts 2019 with later layers favored for both EVC and IT.
Seeing it all: Convolutional network layers map the function of the human visual system
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Learning to aggregate feature representations
Learns adaptive aggregation of intermediate features from SE-ResNeXt-50 to map images to multi-subject fMRI/MEG activity, ranking top-5 in Algonauts 2019 with later layers favored for both EVC and IT.