Search Results for author:
Found 5 papers, 2 papers with code
MedCycle: Unpaired Medical Report Generation via Cycle-Consistency
This approach is based on cycle-consistent mapping functions that transform image embeddings into report embeddings, coupled with report auto-encoding for medical report generation.
Asymmetric Image Retrieval with Cross Model Compatible Ensembles
In this setting, a large model is used for indexing the gallery while a lightweight model is used for querying.
LIMITR: Leveraging Local Information for Medical Image-Text Representation
Furthermore, the model integrates domain-specific information of two types -- lateral images and the consistent visual structure of chest images.
CLID: Controlled-Length Image Descriptions with Limited Data
Controllable image captioning models generate human-like image descriptions, enabling some kind of control over the generated captions.
Color Visual Illusions: A Statistics-based Computational Model
Visual illusions may be explained by the likelihood of patches in real-world images, as argued by input-driven paradigms in Neuro-Science.
