Test-Time Personalization with Meta Prompt for Gaze Estimation

arXiv:2401.01577v3 Announce Type: replace
Abstract: Despite the recent remarkable achievement in gaze estimation, efficient and accurate personalization of gaze estimation without labels is a practical problem but rarely touched on in the literature. To achieve efficient personalization, we take inspiration from the recent advances in Natural Language Processing (NLP) by updating a negligible number of parameters, "prompts", at the test time. Specifically, the prompt is additionally attached without perturbing original network and can contain less than 1% of a ResNet-18's …

arxiv cs.cv meta personalization prompt test type