Papers › Image Deformation Meta-Networks for One-Shot Learning

Image Deformation Meta-Networks for One-Shot Learning

28 May 2019CVPR 2019 6arXiv:1905.11641archive 2025-07-28

Zitian Chen, Yanwei Fu, Yu-Xiong Wang, Lin Ma, Wei Liu, Martial Hebert

Humans can robustly learn novel visual concepts even when images undergo various deformations and lose certain information. Mimicking the same behavior and synthesizing deformed instances of new concepts may help visual recognition systems perform better one-shot learning, i.e., learning concepts from one or few examples. Our key insight is that, while the deformed images may not be visually realistic, they still maintain critical semantic information and contribute significantly to formulating classifier decision boundaries. Inspired by the recent progress of meta-learning, we combine a meta-learner with an image deformation sub-network that produces additional training examples, and optimize both models in an end-to-end manner. The deformation sub-network learns to deform images by fusing a pair of images --- a probe image that keeps the visual content and a gallery image that diversifies the deformations. We demonstrate results on the widely used one-shot learning benchmarks (miniImageNet and ImageNet 1K Challenge datasets), which significantly outperform state-of-the-art approaches. Code is available at https://github.com/tankche1/IDeMe-Net.

PaperPDFConference PDFCode

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

Code

tankche1/IDeMe-Net officialmentioned in papermentioned on GitHubpytorchMIT 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

Few-Shot Image ClassificationMeta-LearningOne-Shot Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Few-Shot Image Classification ImageNet-FS (1-shot, novel) IDeMe-Net (ResNet-50) Top-5 Accuracy (%) 60.1 #4 of 7 Archive leaderboard report
Few-Shot Image Classification ImageNet-FS (2-shot, novel) IDeMe-Net (ResNet-50) Top-5 Accuracy (%) 69.6 #4 of 8 Archive leaderboard report
Few-Shot Image Classification ImageNet-FS (5-shot, all) IdeMe-Net (ResNet-50) Top-5 Accuracy (%) 77.4 #6 of 8 Archive leaderboard report
Few-Shot Image Classification Mini-Imagenet 5-way (1-shot) IDeMe-Net Accuracy 59.14 #77 of 105 Archive leaderboard report
Few-Shot Image Classification Mini-Imagenet 5-way (5-shot) IDeMe-Net Accuracy 74.63 #71 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