no code implementations • 4 Jun 2023 • Deepan Chakravarthi Padmanabhan, Paul G. Plöger, Octavio Arriaga, Matias Valdenegro-Toro
Adebayo et al.'s work on evaluating saliency methods for classification models illustrate certain explanation methods fail the model and data randomization tests.
no code implementations • 13 Apr 2023 • Deepan Chakravarthi Padmanabhan, Shruthi Gowda, Elahe Arani, Bahram Zonooz
Few-shot learning (FSL) techniques seek to learn the underlying patterns in data using fewer samples, analogous to how humans learn from limited experience.
1 code implementation • 21 Dec 2022 • Deepan Chakravarthi Padmanabhan, Paul G. Plöger, Octavio Arriaga, Matias Valdenegro-Toro
State-of-the-art object detectors are treated as black boxes due to their highly non-linear internal computations.