Context Autoencoder for Self-Supervised Representation Learning. (arXiv:2202.03026v3 [cs.CV] UPDATED)

We present a novel masked image modeling (MIM) approach, context autoencoder
(CAE), for self-supervised representation pretraining. We pretrain an encoder
by making predictions in the encoded representation space. The pretraining
tasks include two tasks: masked representation prediction - predict the
representations for the masked patches, and masked patch reconstruction -
reconstruct the masked patches. The network is an encoder-regressor-decoder
architecture: the encoder takes the visible patches as input; the regressor
predicts the representations of the masked patches, which are expected …

arxiv autoencoder cae context encoder image making modeling novel prediction predictions representation representation learning space