论文标题
强大的DNN推断的部分重量适应
Partial Weight Adaptation for Robust DNN Inference
论文作者
论文摘要
主流视频分析使用预先训练的DNN模型，假设推论输入和训练数据遵循相同的概率分布。但是，这种假设并不总是在野外存在：自动驾驶汽车可能会以不同的亮度捕获视频。不稳定的无线带宽需要视频的自适应比特率流；并且，推理服务器可以提供异质IoT设备/相机的输入。在这种情况下，输入失真的水平迅速变化，从而重塑了输入的概率分布。 我们提出齿轮，这是一种适合异质DNN输入的自适应推理结构。 Gearnn采用优化算法来确定一小部分“失真敏感” DNN参数，给定记忆预算。基于输入的失真级别，Gearnn然后仅适应失真敏感的参数，同时重用所有输入质量的恒定参数的其余部分。在我们评估DNN推断的动态输入扭曲时，Gearnn在接受未经段的数据集的DNN中平均提高了准确性（MIOU），平均提高了18.12％，而从Google进行的稳定性培训中，其稳定性培训为4.84％，只有1.8％的额外存储器额外头顶。
Mainstream video analytics uses a pre-trained DNN model with an assumption that inference input and training data follow the same probability distribution. However, this assumption does not always hold in the wild: autonomous vehicles may capture video with varying brightness; unstable wireless bandwidth calls for adaptive bitrate streaming of video; and, inference servers may serve inputs from heterogeneous IoT devices/cameras. In such situations, the level of input distortion changes rapidly, thus reshaping the probability distribution of the input. We present GearNN, an adaptive inference architecture that accommodates heterogeneous DNN inputs. GearNN employs an optimization algorithm to identify a small set of "distortion-sensitive" DNN parameters, given a memory budget. Based on the distortion level of the input, GearNN then adapts only the distortion-sensitive parameters, while reusing the rest of constant parameters across all input qualities. In our evaluation of DNN inference with dynamic input distortions, GearNN improves the accuracy (mIoU) by an average of 18.12% over a DNN trained with the undistorted dataset and 4.84% over stability training from Google, with only 1.8% extra memory overhead.
