Thank you very much for your detailed survey of the work on CLIP in Medical Imaging. We recognize the complexity of this work and are very grateful for your efforts.
We would also like to recommend our paper accepted by NeurIPS 2023, Text Promptable Surgical Instrument Segmentation with Vision-Language Models (paper: https://arxiv.org/abs/2306.09244, code: https://github.com/franciszzj/TP-SIS). This paper utilizes a CLIP model to construct a text-promptable surgical instrument segmentation model. We believe this fits well with the CLIP-driven Application/Dense Prediction section of the review.
Thank you in advance for considering our suggestion.
Thank you very much for your detailed survey of the work on CLIP in Medical Imaging. We recognize the complexity of this work and are very grateful for your efforts. We would also like to recommend our paper accepted by NeurIPS 2023, Text Promptable Surgical Instrument Segmentation with Vision-Language Models (paper: https://arxiv.org/abs/2306.09244, code: https://github.com/franciszzj/TP-SIS). This paper utilizes a CLIP model to construct a text-promptable surgical instrument segmentation model. We believe this fits well with the CLIP-driven Application/Dense Prediction section of the review. Thank you in advance for considering our suggestion.