Papers › Task Augmentation by Rotating for Meta-Learning

Task Augmentation by Rotating for Meta-Learning

8 Feb 2020arXiv 2020 2arXiv:2003.00804archive 2025-07-28

Jialin Liu, Fei Chao, Chih-Min Lin

Data augmentation is one of the most effective approaches for improving the accuracy of modern machine learning models, and it is also indispensable to train a deep model for meta-learning. In this paper, we introduce a task augmentation method by rotating, which increases the number of classes by rotating the original images 90, 180 and 270 degrees, different from traditional augmentation methods which increase the number of images. With a larger amount of classes, we can sample more diverse task instances during training. Therefore, task augmentation by rotating allows us to train a deep network by meta-learning methods with little over-fitting. Experimental results show that our approach is better than the rotation for increasing the number of images and achieves state-of-the-art performance on miniImageNet, CIFAR-FS, and FC100 few-shot learning benchmarks. The code is available on \url{www.github.com/AceChuse/TaskLevelAug}.

PaperPDFCode

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

Code

AceChuse/TaskLevelAug officialmentioned in paperpytorch 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

Data AugmentationFew-Shot LearningMeta-Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Few-Shot Image Classification CIFAR-FS 5-way (1-shot) R2-D2+Task Aug Accuracy 77.66 #18 of 38 Archive leaderboard report
Few-Shot Image Classification CIFAR-FS 5-way (1-shot) MetaOptNet-SVM+Task Aug Accuracy 76.75 #20 of 38 Archive leaderboard report
Few-Shot Image Classification CIFAR-FS 5-way (5-shot) MetaOptNet-SVM+Task Aug Accuracy 88.38 #20 of 39 Archive leaderboard report
Few-Shot Image Classification CIFAR-FS 5-way (5-shot) R2-D2+Task Aug Accuracy 88.33 #22 of 39 Archive leaderboard report
Few-Shot Image Classification FC100 5-way (1-shot) R2-D2+Task Aug Accuracy 51.35 #4 of 22 Archive leaderboard report
Few-Shot Image Classification FC100 5-way (1-shot) MetaOptNet-SVM+Task Aug Accuracy 49.77 #6 of 22 Archive leaderboard report
Few-Shot Image Classification FC100 5-way (5-shot) R2-D2+Task Aug Accuracy 67.66 #2 of 22 Archive leaderboard report
Few-Shot Image Classification FC100 5-way (5-shot) MetaOptNet-SVM+Task Aug Accuracy 67.17 #3 of 22 Archive leaderboard report
Few-Shot Image Classification Mini-ImageNet - 1-Shot Learning R2-D2+Task Aug Accuracy 65.95% #10 of 16 Archive leaderboard report
Few-Shot Image Classification Mini-ImageNet - 1-Shot Learning MetaOptNet-SVM+Task Aug Accuracy 65.38% #11 of 16 Archive leaderboard report
Few-Shot Image Classification Mini-Imagenet 5-way (1-shot) R2-D2+Task Aug Accuracy 65.95 #52 of 105 Archive leaderboard report
Few-Shot Image Classification Mini-Imagenet 5-way (1-shot) MetaOptNet-SVM+Task Aug Accuracy 65.38 #56 of 105 Archive leaderboard report
Few-Shot Image Classification Mini-Imagenet 5-way (5-shot) MetaOptNet-SVM+Task Aug Accuracy 82.13 #43 of 95 Archive leaderboard report
Few-Shot Image Classification Mini-Imagenet 5-way (5-shot) R2-D2+Task Aug Accuracy 81.96 #44 of 95 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