Supplementary archive for VDLF-Net: code, datasets, model checkpoints, and experimental results
Supplementary archive for VDLF-Net: code, datasets, model checkpoints, and experimental results
Complete supplementary package for: "VDLF-Net: Variational Feature Fusion for Adaptive and Few-Shot Visual Learning" Author: Jiawei Yan, Department of Statistics, School of Mathematical Sciences, Shanghai Jiao Tong University, Shanghai 200240, ChinaContact: yjw1998@sjtu.edu.cn ----------------------------------------------------------------Contents (vdlf_net.zip)----------------------------------------------------------------Unpack to folder vdlf_net/ with five parts: • exp1codes/ — Main Experiment 1 code, notebooks, CSV results, and notes (start here).• experiment_1/ — Earlier Experiment 1 tree (CIFAR-100; legacy copy).• experiment_2/ — Few-shot experiments on Mini-ImageNet (code, logs, figures, data/, checkpoints).• experiment_ablation/ — Ablation studies (scripts, CSV, notebooks, checkpoints).• tSNE/ — t-SNE scripts and figure outputs. Also includes Markdown guides, shell scripts, and result files (CSV/JSON/TXT) where applicable. ----------------------------------------------------------------Reproduction----------------------------------------------------------------Python 3.10+; PyTorch/torchvision (CUDA as appropriate). See README and guides inside each folder. ----------------------------------------------------------------Version----------------------------------------------------------------This deposit (June 2026) supersedes the Zenodo record "Supplementary archive: VDLF-Net (code, data, and results)" (April 2026, v1). Please use this DOI for the current manuscript. License: CC BY 4.0. Please cite this Zenodo DOI together with the journal article when published.
- Shanghai Jiao Tong University China (People's Republic of)
Mini-ImageNet, feature fusion, deep learning, few-shot learning, reproducibility, VDLF-Net, variational inference
Mini-ImageNet, feature fusion, deep learning, few-shot learning, reproducibility, VDLF-Net, variational inference
selected citations These citations are derived from selected sources.This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).0 popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.Average influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).Average impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.Average
Citations provided by BIP!Popularity provided by BIP!