大规模实验揭示细粒度图像识别中训练与推理成本的权衡关系。
A Large-Scale Study on the Accuracy vs Cost Trade-offs of Training and Evaluation Settings in Fine-Grained Image Recognition
- 通过数据感知增强训练，无需依赖裁剪即可达到高精度。
- 提出新方法在保持精度同时降低推理开销超过50%。
- 适合关注模型效率与实用性的研究者参考。
细粒度图像识别（FGIR）研究虽重视骨干网络选择，却忽视了不同训练与评估设置下的准确率-成本权衡。本文在6种训练与评估设置、9个预训练骨干网络、17个数据集上开展了超过2000次实验。初步发现数据增强对细粒度训练有效后，我们扩展了先进方法Counterfactual Attention Learning（CAL），引入跨图像判别区域混合增强。同时提出一种高效的仅评估变体，通过放弃判别区域的前向传播，显著降低推理成本而保持竞争力。结果表明，仅在训练阶段使用数据感知增强，即可使模型在无需裁剪的情况下实现优异准确率，大幅减少推理开销。为支持后续研究，代码与模型权重已开源： https://github.com/arkel23/FGIR-Backbones。
原文摘要 · Abstract (English)
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}
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。