Showing 2024Show all
2 papers · 1 filter
cs.AI2024
Interpreting Global Perturbation Robustness of Image Models using Axiomatic Spectral Importance Decomposition
Róisín Luo, James McDermott, Colm O'Riordan
Perturbation robustness evaluates the vulnerabilities of models, arising from a variety of perturbations, such as data corruptions and adversarial attacks. Understanding the mechan…
cs.CV2024
Reclaiming Residual Knowledge: A Novel Paradigm to Low-Bit Quantization
Róisín Luo, Alexandru Drimbarean, James McDermott +1
This paper explores a novel paradigm in low-bit (i.e. 4-bits or lower) quantization, differing from existing state-of-the-art methods, by framing optimal quantization as an archite…