arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2103.15136cs.CV
收藏

基于ImponnestrandNet的人脸表情识别

Imponderous Net for Facial Expression Recognition in the Wild

SSSIHL(斯里萨蒂亚赛人类卓越研究所)

Darshan Gera, S. Balasubramanian

摘要:

自深度学习(DL)复兴以来,面部表情识别(FER)受到了极大的关注,其性能不断提高。与业绩携手,新的挑战也随之而来。现代FER系统处理在不受控制的条件下(也称为野外场景)捕获的面部图像,包括遮挡和姿态变化。他们使用深度网络成功地处理了这些情况,这些网络具有各种组件,如迁移学习,注意力机制和局部-全局上下文提取器。然而,这些深度网络非常复杂,具有大量参数,使其不适合在实际场景中部署。是否有可能构建一个轻量级网络,在野外场景下仍然可以在FER上显示出显着的良好性能?在这项工作中,我们有条不紊地构建了这样一个网络,并将其称为ImponetransNet。我们利用FER的深度网络的上述组件,并分析,仔细选择和调整它们以达到Imponetrant Net。我们的Imponetrable Net是一个低卡路里的网络,只有145万个参数,比最先进的(SOTA)架构少了近50倍。此外,在推理过程中,它可以在intel-i7 cpu中以每秒40帧(fps)的实时的速率进行处理。虽然它是低热量的,但它的性能仍然强大,压倒了其他轻量级架构,甚至是少数高容量架构。具体来说,ImponnestNet在野外数据集RAFDB,FERPlus和AffectNet上的准确率分别为87.09%,88.17%和62.06%。与文献中的其他轻量级架构相比,它在遮挡和姿态变化下也具有出色的鲁棒性。

英文摘要:

Since the renaissance of deep learning (DL), facial expression recognition (FER) has received a lot of interest, with continual improvement in the performance. Hand-in-hand with performance, new challenges have come up. Modern FER systems deal with face images captured under uncontrolled conditions (also called in-the-wild scenario) including occlusions and pose variations. They successfully handle such conditions using deep networks that come with various components like transfer learning, attention mechanism and local-global context extractor. However, these deep networks are highly complex with large number of parameters, making them unfit to be deployed in real scenarios. Is it possible to build a light-weight network that can still show significantly good performance on FER under in-the-wild scenario? In this work, we methodically build such a network and call it as Imponderous Net. We leverage on the aforementioned components of deep networks for FER, and analyse, carefully choose and fit them to arrive at Imponderous Net. Our Imponderous Net is a low calorie net with only 1.45M parameters, which is almost 50x less than that of a state-of-the-art (SOTA) architecture. Further, during inference, it can process at the real time rate of 40 frames per second (fps) in an intel-i7 cpu. Though it is low calorie, it is still power packed in its performance, overpowering other light-weight architectures and even few high capacity architectures. Specifically, Imponderous Net reports 87.09\%, 88.17\% and 62.06\% accuracies on in-the-wild datasets RAFDB, FERPlus and AffectNet respectively. It also exhibits superior robustness under occlusions and pose variations in comparison to other light-weight architectures from the literature.

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。

↑