XAI-Genre results
Baselines
Our baselines consist on random samples from the training set of the XAI-Genre and prototypes obtained with the APNet model.
class | dataset sample | APNet |
---|---|---|
afrobeat | ||
ambient | ||
bolero | ||
bop | ||
bossa nova | ||
contemporary jazz | ||
cumbia | ||
disco | ||
doo wop | ||
dub | ||
electro | ||
europop | ||
funk | ||
gospel | ||
heavy metal | ||
house | ||
indie rock | ||
punk | ||
techno | ||
trance | ||
salsa | ||
samba | ||
soul | ||
swing |
Our models
We show the results obtained with PECMAE-3 (3 prototypes per target class). For each class, we sonify two of the prototypes.
class | PECMAE-3 (prototype 0) | PECMAE-3 (prototype 1) |
---|---|---|
afrobeat | ||
ambient | ||
bolero | ||
bop | ||
bossa nova | ||
contemporary jazz | ||
cumbia | ||
disco | ||
doo wop | ||
dub | ||
electro | ||
europop | ||
funk | ||
gospel | ||
heavy metal | ||
house | ||
indie rock | ||
punk | ||
techno | ||
trance | ||
salsa | ||
samba | ||
soul | ||
swing |
Prototype-class connections
In PECMAE, prototypes are linearly connected to the classification layer.
The following plot shows the weights learned for these connections.
Note that certain prototypes may have a positive correlation with related classes.
For example, bob
and contemporary jazz
, cumbia
and salsa
, or punk
and heavy metal
.