CERN: Compact facial expression recognition net

•Build CERN, a low-calorie power-packed architecture for FER in the wild.•It has only 1.45M parameters, requires only 17MB and processes at real time 40 fps.•Superior performance over other light-weight architectures.•Comparable or superior performance over some of the heavy SOTA architectures.•Robust to occlusions and pose variations. 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 Compact Expression Recognition Net (CERN). We leverage on the aforementioned components of deep networks for FER, and analyse, and appropriately fit them to arrive at CERN. Our CERN 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. It requires only 17MB of storage. 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, CERN 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. Codes are publicly available at https://github.com/1980x/CFERNet.