Continual Facial Expression Recognition: A benchmark

We introduce ConFER, a continual-learning benchmark for facial expression recognition that evaluates how well popular CL methods adapt to real-world, incremental data without catastrophic forgetting, demonstrating state-of-the-art performance across multiple FER datasets and highlighting the benefits of CL for robust affective computing.

May 2023 · Nikhil Churamani, Tolga Dimlioglu, German I Parisi, Hatice Gunes