平衡检测和跟踪的专业化、泛化和压缩
Balancing Specialization, Generalization, and Compression for Detection and Tracking
摘要：
我们提出了一种专门的深度检测器和跟踪器的限制设置的方法。我们的方法设计考虑到以下目标：（a）提高精度的限制域;（b）防止过度拟合到新的域和忘记的广义功能;（c）积极的模型压缩和加速。为此，我们提出了一种新的损失，它平衡了深度学习模型的压缩和加速与泛化能力的损失。我们将我们的方法应用到现有的跟踪器和检测器模型。我们报告的VIRAT和CAVIAR数据集的检测结果。这些结果表明，我们的方法提供了前所未有的压缩率以及改进的检测。我们在测试时将损失应用于跟踪器压缩，因为它处理每个视频。我们在OTB 2015基准上的测试表明，在测试期间应用压缩实际上提高了跟踪性能。
英文摘要：
We propose a method for specializing deep detectors and trackers to restricted settings. Our approach is designed with the following goals in mind: (a) Improving accuracy in restricted domains; (b) preventing overfitting to new domains and forgetting of generalized capabilities; (c) aggressive model compression and acceleration. To this end, we propose a novel loss that balances compression and acceleration of a deep learning model vs. loss of generalization capabilities. We apply our method to the existing tracker and detector models. We report detection results on the VIRAT and CAVIAR data sets. These results show our method to offer unprecedented compression rates along with improved detection. We apply our loss for tracker compression at test time, as it processes each video. Our tests on the OTB2015 benchmark show that applying compression during test time actually improves tracking performance.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
