A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is
Partial Weight Adaptation for Robust DNN Inference
2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
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,doi:10.1109/cvpr42600.2020.00959 dblp:conf/cvpr/XieK20 fatcat:2t4ag565bnhffkrxu3ef6aw66q