Papers › Constellation Nets for Few-Shot Learning
Constellation Nets for Few-Shot Learning
Weijian Xu, Yifan Xu, Huaijin Wang, Zhuowen Tu
The success of deep convolutional neural networks builds on top of the learning of effective convolution operations, capturing a hierarchy of structured features via filtering, activation, and pooling. However, the explicit structured features, e.g. object parts, are not expressive in the existing CNN frameworks. In this paper, we tackle the few-shot learning problem and make an effort to enhance structured features by expanding CNNs with a constellation model, which performs cell feature clustering and encoding with a dense part representation; the relationships among the cell features are further modeled by an attention mechanism. With the additional constellation branch to increase the awareness of object parts, our method is able to attain the advantages of the CNNs while making the overall internal representations more robust in the few-shot learning setting. Our approach attains a significant improvement over the existing methods in few-shot learning on the CIFAR-FS, FC100, and mini-ImageNet benchmarks.
Syntology This paper has no arXiv id in the archive, and this site joins papers to Syntology's graph by arXiv id, so this page does not say whether the graph holds it.
Code
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
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Few-Shot Image Classification | CIFAR-FS 5-way (1-shot) | ConstellationNets | Accuracy | 75.4 | #24 of 38 | Archive leaderboard | report |
| Few-Shot Image Classification | CIFAR-FS 5-way (5-shot) | ConstellationNets | Accuracy | 86.8 | #26 of 39 | Archive leaderboard | report |
| Few-Shot Image Classification | FC100 5-way (1-shot) | ConstellationNets | Accuracy | 43.8 | #16 of 22 | Archive leaderboard | report |
| Few-Shot Image Classification | FC100 5-way (5-shot) | ConstellationNets | Accuracy | 59.7 | #16 of 22 | Archive leaderboard | report |
| Few-Shot Image Classification | Mini-Imagenet 5-way (1-shot) | ConstellationNets | Accuracy | 64.89 | #60 of 105 | Archive leaderboard | report |
| Few-Shot Image Classification | Mini-Imagenet 5-way (5-shot) | ConstellationNets | Accuracy | 79.95 | #55 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.
Methods
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