Papers › Context Autoencoder for Self-Supervised Representation Learning

Context Autoencoder for Self-Supervised Representation Learning

7 Feb 2022arXiv:2202.03026archive 2025-07-28

Xiaokang Chen, Mingyu Ding, Xiaodi Wang, Ying Xin, Shentong Mo, Yunhao Wang, Shumin Han, Ping Luo, Gang Zeng, Jingdong Wang

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.

PaperPDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

atten4vis/cae officialmentioned in papermentioned on GitHubpytorchSyntology: not harvested report
lxtGH/CAE mentioned on GitHubpytorchSyntology: not harvested report
open-mmlab/mmselfsup mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to PixMIM: Rethinking Pixel Reconstruction in Masked Image Modeling (arXiv:2303.02416; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
PaddlePaddle/PLSC paddleSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Token Merging: Your ViT But Faster (arXiv:2210.09461; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
PaddlePaddle/PaddleFL paddleApache-2.0Syntology: not harvested report
PaddlePaddle/VIMER paddleSyntology: not harvested report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

DecoderInstance SegmentationObject DetectionRepresentation LearningSelf-Supervised Image ClassificationSelf-Supervised LearningSemantic Segmentationobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Object Detection COCO minival CAE (ViT-L, Mask R-CNN, 1x schedule) box AP 54.5 #56 of 220 Archive leaderboard report
Self-Supervised Image Classification ImageNet (finetuned) CAE (ViT-L/16) Number of Params 307M #15 of 65 Archive leaderboard report
Self-Supervised Image Classification ImageNet (finetuned) CAE (ViT-L/16) Top 1 Accuracy 86.3% #15 of 65 Archive leaderboard report
Semantic Segmentation ADE20K CAE (ViT-L, UperNet) Validation mIoU 54.7 #57 of 235 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections