Papers › A Comprehensive Study on Torchvision Pre-trained Models for Fine-grained Inter-species...

A Comprehensive Study on Torchvision Pre-trained Models for Fine-grained Inter-species Classification

14 Oct 2021arXiv:2110.07097archive 2025-07-28

Feras Albardi, H M Dipu Kabir, Md Mahbub Islam Bhuiyan, Parham M. Kebria, Abbas Khosravi, Saeid Nahavandi

This study aims to explore different pre-trained models offered in the Torchvision package which is available in the PyTorch library. And investigate their effectiveness on fine-grained images classification. Transfer Learning is an effective method of achieving extremely good performance with insufficient training data. In many real-world situations, people cannot collect sufficient data required to train a deep neural network model efficiently. Transfer Learning models are pre-trained on a large data set, and can bring a good performance on smaller datasets with significantly lower training time. Torchvision package offers us many models to apply the Transfer Learning on smaller datasets. Therefore, researchers may need a guideline for the selection of a good model. We investigate Torchvision pre-trained models on four different data sets: 10 Monkey Species, 225 Bird Species, Fruits 360, and Oxford 102 Flowers. These data sets have images of different resolutions, class numbers, and different achievable accuracies. We also apply their usual fully-connected layer and the Spinal fully-connected layer to investigate the effectiveness of SpinalNet. The Spinal fully-connected layer brings better performance in most situations. We apply the same augmentation for different models for the same data set for a fair comparison. This paper may help future Computer Vision researchers in choosing a proper Transfer Learning model.

PaperPDFCode

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.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Fine-Grained Image ClassificationTransfer Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Fine-Grained Image Classification 10 Monkey Species Inception-v3 (Spinal FC) Accuracy 99.26 #1 of 4 Archive leaderboard report
Fine-Grained Image Classification 10 Monkey Species WideResNet-101(Spinal FC) Accuracy 99.26 #2 of 4 Archive leaderboard report
Fine-Grained Image Classification 10 Monkey Species VGG-19_bn Accuracy 98.90 #3 of 4 Archive leaderboard report
Fine-Grained Image Classification Bird-225 WideResNet-101 (Spinal FC) Accuracy 99.56 #1 of 5 Archive leaderboard report
Fine-Grained Image Classification Bird-225 WideResNet-101 Accuracy 99.38 #3 of 5 Archive leaderboard report
Fine-Grained Image Classification Fruits-360 ResNeXt-101 Accuracy (%) 99.98 #1 of 3 Archive leaderboard report
Fine-Grained Image Classification Oxford 102 Flowers DenseNet-201(Spinal FC) Accuracy 98.36 #11 of 25 Archive leaderboard report
Fine-Grained Image Classification Oxford 102 Flowers DenseNet-201 Accuracy 98.29 #13 of 25 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