DOE OSTI · code-128865
CLIP Representation Enhanced Predicate Estimation
Abstract
This software provides functions to perform visual predicate estimation by leveraging the pre-trained vision-language model CLIP. In addition to training the prediction estimator with a labeled dataset, it also performs performance evaluation and visualization of results.
Keep this discovery
Explore connections, maps & timelines
Jayaraman Thiagarajan, Jayaraman. 2023-07-21. CLIP Representation Enhanced Predicate Estimation. https://doi.org/10.11578/dc.20240614.257
Cite the original work for its findings. Save a collection to share your selection of sources.