no code implementations • 20 Oct 2023 • Logan Frank, Jim Davis
Knowledge distillation (KD) has been a popular and effective method for model compression.
1 code implementation • ICCV 2023 • TONG LIANG, Jim Davis
There is a recently discovered and intriguing phenomenon called Neural Collapse: at the terminal phase of training a deep neural network for classification, the within-class penultimate feature means and the associated classifier vectors of all flat classes collapse to the vertices of a simplex Equiangular Tight Frame (ETF).
no code implementations • 18 Jan 2023 • Aswathnarayan Radhakrishnan, Jim Davis, Zachary Rabin, Benjamin Lewis, Matthew Scherreik, Roman Ilin
Semi-supervised learning approaches train on small sets of labeled data along with large sets of unlabeled data.
1 code implementation • 11 Sep 2022 • Nicholas Kashani Motlagh, Jim Davis, Tim Anderson, Jeremy Gwinnup
We propose a new Reject Option Classification technique to identify and remove regions of uncertainty in the decision space for a given neural classifier and dataset.
no code implementations • 12 Feb 2022 • Jim Davis
In this paper, we propose "Confident AI" as a means to designing Artificial Intelligence (AI) and Machine Learning (ML) systems with both algorithm and user confidence in model predictions and reported results.
2 code implementations • 26 Oct 2021 • Jim Davis, Logan Frank
Standard initialization of each BN in a network sets the affine transformation scale and shift to 1 and 0, respectively.
no code implementations • 5 Oct 2021 • TONG LIANG, Jim Davis, Roman Ilin
In this work, we propose a method to efficiently compute label posteriors of a base flat classifier in the presence of few validation examples within a bottom-up hierarchical inference framework.
no code implementations • 2 Jul 2020 • Jim Davis
Classification approaches based on the direct estimation and analysis of posterior probabilities will degrade if the original class priors begin to change.