Rotated MNIST is a popular dataset for benchmarking models equivariant to rotations on $\mathbb{R}^2$, described by $SO(2)$ group or its discrete subgroups like $\mathbb{Z}^{n}$:

It consists of all digits from 0 to 9 rotated on an arbitrary angle from $[0, 2 \pi)$. However, what makes me a bit puzzled is that digits $6$ and $9$ seem to be confused by any learning algorithms, since from the view of human perception $6$ rotated by 180 degrees is equivalent to $9$ and vice versa.

The original paper in the description of Rotated MNIST doesn't comment on this point at all, which is strange, since it is a very natural question to ask.

enter image description here

In the paper Oriented Response Networks - authors plot embeddings of rotated digits projected via t-SNE on a 2d plane. There is a clear separation between all rotated versions of 6 and the rotated version of 9 for ORN.

enter image description here

I do not understand how it can be achieved? Probably, the networks understand much more in writing the digit, there are some subtle features, inaccessible to humans, but recognizable by powerful classifier?


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.