Papers › Split-Brain Autoencoders: Unsupervised Learning by Cross-Channel Prediction

Split-Brain Autoencoders: Unsupervised Learning by Cross-Channel Prediction

29 Nov 2016CVPR 2017 7arXiv:1611.09842archive 2025-07-28

Richard Zhang, Phillip Isola, Alexei A. Efros

We propose split-brain autoencoders, a straightforward modification of the traditional autoencoder architecture, for unsupervised representation learning. The method adds a split to the network, resulting in two disjoint sub-networks. Each sub-network is trained to perform a difficult task -- predicting one subset of the data channels from another. Together, the sub-networks extract features from the entire input signal. By forcing the network to solve cross-channel prediction tasks, we induce a representation within the network which transfers well to other, unseen tasks. This method achieves state-of-the-art performance on several large-scale transfer learning benchmarks.

PaperPDFConference PDFCode

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

Code

richzhang/splitbrainauto officialmentioned on GitHubMIT 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.

Code Syntology ran Syntology

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

Tasks

Representation LearningSelf-Supervised Image ClassificationTransfer Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Self-Supervised Image Classification ImageNet Split-Brain (AlexNet) Number of Params 61M #141 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet Split-Brain (AlexNet) Top 1 Accuracy 35.4% #141 of 144 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