Papers › Multi-task Self-Supervised Visual Learning

Multi-task Self-Supervised Visual Learning

25 Aug 2017ICCV 2017 10arXiv:1708.07860archive 2025-07-28

Carl Doersch, Andrew Zisserman

We investigate methods for combining multiple self-supervised tasks--i.e., supervised tasks where data can be collected without manual labeling--in order to train a single visual representation. First, we provide an apples-to-apples comparison of four different self-supervised tasks using the very deep ResNet-101 architecture. We then combine tasks to jointly train a network. We also explore lasso regularization to encourage the network to factorize the information in its representation, and methods for "harmonizing" network inputs in order to learn a more unified representation. We evaluate all methods on ImageNet classification, PASCAL VOC detection, and NYU depth prediction. Our results show that deeper networks work better, and that combining tasks--even via a naive multi-head architecture--always improves performance. Our best joint network nearly matches the PASCAL performance of a model pre-trained on ImageNet classification, and matches the ImageNet network on NYU depth prediction.

PaperPDFConference PDF

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

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

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

Tasks

Depth EstimationDepth PredictionGeneral ClassificationSelf-Supervised Image Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Self-Supervised Image Classification ImageNet Colorisation (improved) (ResNet-101) Number of Params 44M #139 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet Colorisation (improved) (ResNet-101) Top 1 Accuracy 39.6 #139 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet Colorisation (improved) (ResNet-101) Top 5 Accuracy 62.5 #139 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet Multi-task SSL (ResNet-101) Number of Params 44M #144 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet Multi-task SSL (ResNet-101) Top 5 Accuracy 70.2 #144 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