Search Results for author:
Found 4 papers, 1 papers with code
Sanity Checks for Saliency Methods Explaining Object Detectors
Adebayo et al.'s work on evaluating saliency methods for classification models illustrate certain explanation methods fail the model and data randomization tests.
LSFSL: Leveraging Shape Information in Few-shot Learning
Few-shot learning (FSL) techniques seek to learn the underlying patterns in data using fewer samples, analogous to how humans learn from limited experience.
DExT: Detector Explanation Toolkit
State-of-the-art object detectors are treated as black boxes due to their highly non-linear internal computations.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
