LLDif: Diffusion Models for Low-light Emotion Recognition
This work addresses emotion recognition challenges in low-light conditions, which is an incremental improvement for applications like surveillance or human-computer interaction.
The paper tackles facial expression recognition in extremely low-light environments by proposing LLDif, a diffusion-based framework that uses a two-stage training process with label-aware embeddings and a transformer network, achieving competitive performance on low-light FER datasets.
This paper introduces LLDif, a novel diffusion-based facial expression recognition (FER) framework tailored for extremely low-light (LL) environments. Images captured under such conditions often suffer from low brightness and significantly reduced contrast, presenting challenges to conventional methods. These challenges include poor image quality that can significantly reduce the accuracy of emotion recognition. LLDif addresses these issues with a novel two-stage training process that combines a Label-aware CLIP (LA-CLIP), an embedding prior network (PNET), and a transformer-based network adept at handling the noise of low-light images. The first stage involves LA-CLIP generating a joint embedding prior distribution (EPD) to guide the LLformer in label recovery. In the second stage, the diffusion model (DM) refines the EPD inference, ultilising the compactness of EPD for precise predictions. Experimental evaluations on various LL-FER datasets have shown that LLDif achieves competitive performance, underscoring its potential to enhance FER applications in challenging lighting conditions.