Biased Mixtures of Experts: Enabling Computer Vision Inference Under Data Transfer Limitations
Biased Mixtures of Experts: Enabling Computer Vision Inference Under Data Transfer Limitations
复制标题
DOI：
10.1109/tip.2020.3005508
复制
发表时间：
2020-07
影响因子：
10.6
通讯作者：
Alhabib Abbas;Y. Andreopoulos
中科院分区：
文献类型：
--
作者：
Alhabib Abbas;Y. Andreopoulos
我们提出了一种新颖的专家混合类，用于根据测试时的数据传输限制来优化计算机视觉模型。我们的方法假设，允许高精度结果的最小可接受数据量可能因不同的输入空间分区而异。因此，我们考虑专家需要不同数量数据的混合，并训练稀疏门函数来划分每个专家的输入空间。通过适当的超参数选择，我们的方法能够使专家组合偏向于选择特定专家而不是其他专家。通过这种方式，我们表明视觉传感和处理之间的数据传输优化可以作为凸优化问题来解决。为了证明数据可用性和性能之间的关系，我们评估了一系列主流计算机视觉问题的有偏差混合物，即：（i）单镜头检测，（ii）图像超分辨率，以及（iii）实时视频动作分类。对于所有情况，当专家构建修改基线以满足允许的数据效用的不同限制时，有偏差的混合物显着优于之前为满足可用数据的相同限制而优化的工作。
We propose a novel mixture-of-experts class to optimize computer vision models in accordance with data transfer limitations at test time. Our approach postulates that the minimum acceptable amount of data allowing for highly-accurate results can vary for different input space partitions. Therefore, we consider mixtures where experts require different amounts of data, and train a sparse gating function to divide the input space for each expert. By appropriate hyperparameter selection, our approach is able to bias mixtures of experts towards selecting specific experts over others. In this way, we show that the data transfer optimization between visual sensing and processing can be solved as a convex optimization problem. To demonstrate the relation between data availability and performance, we evaluate biased mixtures on a range of mainstream computer vision problems, namely: (i) single shot detection, (ii) image super resolution, and (iii) realtime video action classification. For all cases, and when experts constitute modified baselines to meet different limits on allowed data utility, biased mixtures significantly outperform previous work optimized to meet the same constraints on available data.