InFER++: Real-World Indian Facial Expression Dataset
Open Access
- 14 August 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of the Computer Society
- Vol. 5, 406-417
Abstract
Detecting facial expressions is a challenging task in the field of computer vision. Several datasets and algorithms have been proposed over the past two decades; however, deploying them in real-world, in-the-wild scenarios hampers the overall performance. This is because the training data does not completely represent socio-cultural and ethnic diversity; the majority of the datasets consist of American and Caucasian populations. On the contrary, in a diverse and heterogeneous population distribution like the Indian subcontinent, the need for a significantly large enough dataset representing all the ethnic groups is even more critical. To address this, we present InFER++, an India-specific, multi-ethnic, real-world, in-the-wild facial expression dataset consisting of seven basic expressions. To the best of our knowledge, this is the largest India-specific facial expression dataset. Our cross-dataset analysis of RAF-DB vs InFER++ shows that models trained on RAF-DB were not generalizable to ethnic datasets like InFER++. This is because the facial expressions change with respect to ethnic and socio-cultural factors. We also present LiteXpressionNet, a lightweight deep facial expression network that outperforms many existing lightweight models with considerably fewer FLOPs and parameters. The proposed model is inspired by MobileViTv2 architecture, which utilizes GhostNetv2 blocks to increase parametrization while reducing latency and FLOP requirements. The model is trained with a novel objective function that combines early learning regularization and symmetric cross-entropy loss to mitigate human uncertainties and annotation bias in most real-world facial expression datasets.Keywords
Funding Information
- Kwikpic AI Solutions
This publication has 57 references indexed in Scilit:
- FGENet: a lightweight facial expression recognition algorithm based on FasterNetSignal, Image and Video Processing, 2024
- Learn from All: Erasing Attention Consistency for Noisy Label Facial Expression Recognition2022
- Ad-Corre: Adaptive Correlation-Based Loss for Facial Expression Recognition in the WildIEEE Access, 2022
- Landmark guidance independent spatio-channel attention and complementary context information based facial expression recognitionPattern Recognition Letters, 2021
- Hybrid deep neural networks for face emotion recognitionPattern Recognition Letters, 2018
- ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design2018
- From Facial Expression Recognition to Interpersonal Relation PredictionInternational Journal of Computer Vision, 2017
- Facial expression recognition from near-infrared videosImage and Vision Computing, 2011
- Multi-PIEImage and Vision Computing, 2010
- Facial expression recognition based on Local Binary Patterns: A comprehensive studyImage and Vision Computing, 2009