We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
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 to be aligned with the representations computed from the encoder, using the representations of visible patches and the positions of visible and masked patches; the decoder reconstructs the masked patches from the predicted encoded representations. The CAE design encourages the separation of learning the encoder (representation) from completing the pertaining tasks: masked representation prediction and masked patch reconstruction tasks, and making predictions in the encoded representation space empirically shows the benefit to representation learning. We demonstrate the effectiveness of our CAE through superior transfer performance in downstream tasks: semantic segmentation, object detection and instance segmentation, and classification. The code will be available at https://github.com/Atten4Vis/CAE.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2202.03026")
get_code_for_paper("2202.03026")
have("2202.03026")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2202.03026.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2202.03026)
Connect an agent — have() is free.