Amending Facial Expression Representation via De-albino
Jiawei Shi, Songhao Zhu, Zhiwei Liang
Abstract
This paper is the first to investigate the flawed nature of padding in the convolutional layer. We find that the accumulation of padding in convolutional networks has an erosive effect on features, resulting in a partial loss of recognition performance. We block the detrimental impacts of padding to some extent at the extraction stage of the representation by secondary processing of the high-dimensional features at the network's back end, despite the fact that no solution for total padding replacement has been established. Our proposed module named Amend Representation Module (ARM) weakens the weights of degraded feature pixels and obtains more discriminative representations from eroded features. Experiments on public benchmarks prove that our ARM based on ResNet-18 boosts the performance of FER remarkably.