Papers › KGTN-ens: Few-Shot Image Classification with Knowledge Graph Ensembles

KGTN-ens: Few-Shot Image Classification with Knowledge Graph Ensembles

6 Nov 2022arXiv:2211.03199archive 2025-07-28

Dominik Filipiak, Anna Fensel, Agata Filipowska

We propose KGTN-ens, a framework extending the recent Knowledge Graph Transfer Network (KGTN) in order to incorporate multiple knowledge graph embeddings at a small cost. We evaluate it with different combinations of embeddings in a few-shot image classification task. We also construct a new knowledge source - Wikidata embeddings - and evaluate it with KGTN and KGTN-ens. Our approach outperforms KGTN in terms of the top-5 accuracy on the ImageNet-FS dataset for the majority of tested settings.

PaperPDFCode

Code

DominikFilipiak/KGTN-ens officialmentioned on GitHubpytorch 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 ClassificationImage ClassificationKnowledge Graph Embeddingsimage-classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Few-Shot Image Classification ImageNet-FS (1-shot, all) KGTN-ens (ResNet-50, h+g, max) Top-5 Accuracy (%) 68.58 #1 of 2 Archive leaderboard report
Few-Shot Image Classification ImageNet-FS (1-shot, novel) KGTN-ens (ResNet-50, h+g, max) Top-5 Accuracy (%) 62.73 #1 of 7 Archive leaderboard report
Few-Shot Image Classification ImageNet-FS (10-shot, all) KGTN-ens (ResNet-50, h+g, max) Top-5 Accuracy (%) 83.46 #2 of 2 Archive leaderboard report
Few-Shot Image Classification ImageNet-FS (10-shot, novel) KGTN-ens (ResNet-50, h+g, max) Top-5 Accuracy (%) 82.56 #1 of 2 Archive leaderboard report
Few-Shot Image Classification ImageNet-FS (2-shot, all) KGTN-ens (ResNet-50, h+g, max) Top-5 Accuracy (%) 75.45 #1 of 2 Archive leaderboard report
Few-Shot Image Classification ImageNet-FS (2-shot, novel) KGTN-ens (ResNet-50, h+g, max) Top-5 Accuracy (%) 71.48 #1 of 8 Archive leaderboard report
Few-Shot Image Classification ImageNet-FS (5-shot, all) KGTN-ens (ResNet-50, h+g, max) Top-5 Accuracy (%) 81.12 #1 of 8 Archive leaderboard report
Few-Shot Image Classification ImageNet-FS (5-shot, novel) KGTN-ens (ResNet-50, h+g, mean) Top-5 Accuracy (%) 78.90 #1 of 3 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