Classification via Segmented Attention
I spotted an interesting paper the other day that starts by detecting bird species.
It introduces an algorithm called
PDiscoNet that tries to detect specific categories based on predefined segments.
Detecting a specific species is tricky, but it becomes a lot easier if you know what to look for. Some species have a specific beak, while others have a more or less distinctive wing. So what if you try to detect interesting features first? Things like the head, neck, wing and belly? Then you might put all your attention there and then try to make your prediction based on these features.
It turns out that this won't just work for birds though. You could also do something similar when trying to detect specific people. In this case you'd go for facial features instead.
Pretty interesting read. And creative use of a bird dataset that I didn't know about.