TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Papers/KGTN-ens: Few-Shot Image Classification with Knowledge Gra...

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

Dominik Filipiak, Anna Fensel, Agata Filipowska

2022-11-06Image ClassificationKnowledge Graph EmbeddingsFew-Shot Image Classification
PaperPDFCode(official)

Abstract

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.

Results

TaskDatasetMetricValueModel
Image ClassificationImageNet-FS (10-shot, all)Top-5 Accuracy (%)83.46KGTN-ens (ResNet-50, h+g, max)
Image ClassificationImageNet-FS (5-shot, novel)Top-5 Accuracy (%)78.9KGTN-ens (ResNet-50, h+g, mean)
Image ClassificationImageNet-FS (2-shot, all)Top-5 Accuracy (%)75.45KGTN-ens (ResNet-50, h+g, max)
Image ClassificationImageNet-FS (5-shot, all)Top-5 Accuracy (%)81.12KGTN-ens (ResNet-50, h+g, max)
Image ClassificationImageNet-FS (1-shot, novel)Top-5 Accuracy (%)62.73KGTN-ens (ResNet-50, h+g, max)
Image ClassificationImageNet-FS (1-shot, all)Top-5 Accuracy (%)68.58KGTN-ens (ResNet-50, h+g, max)
Image ClassificationImageNet-FS (2-shot, novel)Top-5 Accuracy (%)71.48KGTN-ens (ResNet-50, h+g, max)
Image ClassificationImageNet-FS (10-shot, novel)Top-5 Accuracy (%)82.56KGTN-ens (ResNet-50, h+g, max)
Few-Shot Image ClassificationImageNet-FS (10-shot, all)Top-5 Accuracy (%)83.46KGTN-ens (ResNet-50, h+g, max)
Few-Shot Image ClassificationImageNet-FS (5-shot, novel)Top-5 Accuracy (%)78.9KGTN-ens (ResNet-50, h+g, mean)
Few-Shot Image ClassificationImageNet-FS (2-shot, all)Top-5 Accuracy (%)75.45KGTN-ens (ResNet-50, h+g, max)
Few-Shot Image ClassificationImageNet-FS (5-shot, all)Top-5 Accuracy (%)81.12KGTN-ens (ResNet-50, h+g, max)
Few-Shot Image ClassificationImageNet-FS (1-shot, novel)Top-5 Accuracy (%)62.73KGTN-ens (ResNet-50, h+g, max)
Few-Shot Image ClassificationImageNet-FS (1-shot, all)Top-5 Accuracy (%)68.58KGTN-ens (ResNet-50, h+g, max)
Few-Shot Image ClassificationImageNet-FS (2-shot, novel)Top-5 Accuracy (%)71.48KGTN-ens (ResNet-50, h+g, max)
Few-Shot Image ClassificationImageNet-FS (10-shot, novel)Top-5 Accuracy (%)82.56KGTN-ens (ResNet-50, h+g, max)

Related Papers

Automatic Classification and Segmentation of Tunnel Cracks Based on Deep Learning and Visual Explanations2025-07-18Adversarial attacks to image classification systems using evolutionary algorithms2025-07-17Efficient Adaptation of Pre-trained Vision Transformer underpinned by Approximately Orthogonal Fine-Tuning Strategy2025-07-17Federated Learning for Commercial Image Sources2025-07-17MUPAX: Multidimensional Problem Agnostic eXplainable AI2025-07-17Hashed Watermark as a Filter: Defeating Forging and Overwriting Attacks in Weight-based Neural Network Watermarking2025-07-15Transferring Styles for Reduced Texture Bias and Improved Robustness in Semantic Segmentation Networks2025-07-14FedGSCA: Medical Federated Learning with Global Sample Selector and Client Adaptive Adjuster under Label Noise2025-07-13