提出循环训练框架，提升移动端场景识别准确率与实时性。
Cycle Training with Semi-Supervised Domain Adaptation: Bridging Accuracy and Efficiency for Real-Time Mobile Scene Detection
- 三阶段循环训练，交替探索与稳定，优化模型性能
- 结合半监督域适应，利用大量无标签数据提升精度
- 在移动端实现94%准确率，推理仅需1.61ms
如今智能手机普及，深度学习在图像分类中的应用日益广泛。然而，移动设备资源有限，如何平衡准确性与计算效率仍是挑战。本文提出一种名为循环训练（Cycle Training）的新框架，采用三阶段交替的探索-稳定训练过程以优化模型表现，并引入半监督域适应（SSDA）利用大模型和无标签数据，有效扩充训练集。在CamSSD数据集上的实验证明，该框架显著提升分类准确率并保证实时推理。具体而言，方法达到Top-1准确率94.00%，Top-3准确率99.17%，在CPU上推理仅需1.61ms，适合真实移动端部署。
原文摘要 · Abstract (English)
Nowadays, smartphones are ubiquitous, and almost everyone owns one. At the same time, the rapid development of AI has spurred extensive research on applying deep learning techniques to image classification. However, due to the limited resources available on mobile devices, significant challenges remain in balancing accuracy with computational efficiency. In this paper, we propose a novel training framework called Cycle Training, which adopts a three-stage training process that alternates between exploration and stabilization phases to optimize model performance. Additionally, we incorporate Semi-Supervised Domain Adaptation (SSDA) to leverage the power of large models and unlabeled data, thereby effectively expanding the training dataset. Comprehensive experiments on the CamSSD dataset for mobile scene detection demonstrate that our framework not only significantly improves classification accuracy but also ensures real-time inference efficiency. Specifically, our method achieves a 94.00% in Top-1 accuracy and a 99.17% in Top-3 accuracy and runs inference in just 1.61ms using CPU, demonstrating its suitability for real-world mobile deployment.
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。