Most of the wins under the "deep learning" umbrella come from extracting meaning from homogenous features like "the pixel at x-2,y+1 has red=123" or "the word at n+1 is 'king'". That's why we see latent variable embeddings like word2vec come from the DL world even though they're not deep.
When you want to include highly informative features in a deep network, it's often better to feed them into a separate logistic model, as shown in the Tensorflow wide-deep tutorials.
State of the art performance on MNIST is held by a 6 layer convnet (4 layers convolutional, 2 layers FC). MNIST is just 28 x 28 grayscale images, so 768 dimensions. There are many more datasets on the same order of dimensionality. CIFAR 10/100 (32 x 32 pixel images) is also dominated by DL convnets, AFAIK.
Data augmentation is also a thing.