Prior work on fine-grained image recognition (FGIR) has established the importance of the backbone selection, but has neglected the accuracy-vs-cost trade-offs under different training and evaluation settings. In this work we conduct a large-scale study with over 2000 experiments across 6 training and evaluation settings, 9 pretrained backbones, and 17 datasets. Preliminary observations on the effectiveness of data augmentation for fine-grained training motivate us to extend Counterfactual Attention Learning (CAL), a state-of-the-art method based on data-aware cropping and masking augmentations, with cross-image discriminative region mixing augmentation. We also propose an efficient evaluation-only variant that maintains competitive accuracy while reducing inference costs by forfeiting the forward pass on discriminative crops that is normally used by CAL and similar FGIR methods. Our results show that data-aware augmentations during training only can enable a model to achieve excellent accuracy even without crops, significantly reducing inference costs. To support future research we share our code and checkpoints at: \url{https://github.com/arkel23/FGIR-Backbones}
@article{arxiv.2605.18700,
title = {A Large-Scale Study on the Accuracy vs Cost Trade-offs of Training and Evaluation Settings in Fine-Grained Image Recognition},
author = {Edwin Arkel Rios and Augusto Christian Surya and Oswin Gosal and Fernando Mikael and Mary Madeline Nicole and Kisoon Jang and Bo-Cheng Lai and Min-Chun Hu},
journal= {arXiv preprint arXiv:2605.18700},
year = {2026}
}
Comments
Accepted to The 13th Workshop on Fine-Grained Visual Categorization (FGVC13) @ CVPR 2026. Main: 6 pages, 4 figures