| Fine-Grained Visual Classification via Internal Ensemble Learning Transformer | ✓ Link | 99.64% | | | | | IELT | 2023-02-13 |
| Big Transfer (BiT): General Visual Representation Learning | ✓ Link | 99.63% | 0.37 | | | | BiT-L (ResNet) | 2019-12-24 |
| An Evolutionary Approach to Dynamic Introduction of Tasks in Large-scale Multitask Learning Systems | ✓ Link | 99.61% | | | | | µ2Net (ViT-L/16) | 2022-05-25 |
| Big Transfer (BiT): General Visual Representation Learning | ✓ Link | 99.30% | 0.70 | | | | BiT-M (ResNet) | 2019-12-24 |
| SpinalNet: Deep Neural Network with Gradual Input | ✓ Link | 99.30% | | | | | Wide-ResNet-101 (Spinal FC) | 2020-07-07 |
| TResNet: High Performance GPU-Dedicated Architecture | ✓ Link | 99.1% | | | | | TResNet-L | 2020-03-30 |
| Grafit: Learning fine-grained image representations with coarse labels | | 99.1% | | | | | Grafit (RegNet-8GF) | 2020-11-25 |
| Transformer in Transformer | ✓ Link | 99.0% | | | 65.6M | | TNT-B | 2021-02-27 |
| Compounding the Performance Improvements of Assembled Techniques in a Convolutional Neural Network | ✓ Link | 98.9% | | | | | Assemble-ResNet | 2020-01-17 |
| Training data-efficient image transformers & distillation through attention | ✓ Link | 98.8% | | | 86M | | DeiT-B | 2020-12-23 |
| A Comprehensive Study on Torchvision Pre-trained Models for Fine-grained Inter-species Classification | ✓ Link | 98.36 | | | | | DenseNet-201(Spinal FC) | 2021-10-14 |
| Neural Architecture Transfer | ✓ Link | 98.3% | | 400M | 4.2M | | NAT-M4 | 2020-05-12 |
| A Comprehensive Study on Torchvision Pre-trained Models for Fine-grained Inter-species Classification | ✓ Link | 98.29 | | | | | DenseNet-201 | 2021-10-14 |
| Neural Architecture Transfer | ✓ Link | 98.1% | | 250M | 3.7M | | NAT-M3 | 2020-05-12 |
| ResNet strikes back: An improved training procedure in timm | ✓ Link | 97.9% | | 4.1 | 24M | | ResNet50 (A1) | 2021-10-01 |
| SR-GNN: Spatial Relation-aware Graph Neural Network for Fine-Grained Image Categorization | ✓ Link | 97.9% | | 9.8 | 30.9 | | SR-GNN | 2022-09-05 |
| ResMLP: Feedforward networks for image classification with data-efficient training | ✓ Link | 97.9% | | | | | ResMLP-24 | 2021-05-07 |
| Neural Architecture Transfer | ✓ Link | 97.9% | | 195M | 3.4M | | NAT-M2 | 2020-05-12 |
| ResMLP: Feedforward networks for image classification with data-efficient training | ✓ Link | 97.4% | | | | | ResMLP-12 | 2021-05-07 |
| Fixing the train-test resolution discrepancy | ✓ Link | 95.7% | 4.3% | | | | FixInceptionResNet-V2 | 2019-06-14 |
| AutoAugment: Learning Augmentation Policies from Data | ✓ Link | 95.36% | 4.64% | | | | AutoAugment | 2018-05-24 |
| Pairwise Confusion for Fine-Grained Visual Classification | ✓ Link | 93.65% | | | | | PC Bilinear CNN | 2017-05-22 |
| AutoFormer: Searching Transformers for Visual Recognition | ✓ Link | | | | | 98.8 | AutoFormer-S | 384 | 2021-07-01 |
| Escaping the Big Data Paradigm with Compact Transformers | ✓ Link | | | 15G | 22.5M | | CCT-14/7x2 | 2021-04-12 |
| Neural Architecture Transfer | ✓ Link | | | 152M | 3.3M | | NAT-M1 | 2020-05-12 |