1 citations · 1 across the 7 of their papers we have counts for
8 papers
Making Better Mistakes in CLIP-Based Zero-Shot Classification with Hierarchy-Aware Language Prompts
Tong Liang, Jim Davis
Recent studies are leveraging advancements in large language models (LLMs) trained on extensive internet-crawled text data to generate textual descriptions of downstream classes in…
Inducing Neural Collapse to a Fixed Hierarchy-Aware Frame for Reducing Mistake Severity
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 penult…
Enhancing Self-Training Methods
Aswathnarayan Radhakrishnan, Jim Davis, Zachary Rabin +3
Semi-supervised learning approaches train on small sets of labeled data along with large sets of unlabeled data. Self-training is a semi-supervised teacher-student approach that of…
Learning When to Say "I Don't Know"
Nicholas Kashani Motlagh, Jim Davis, Tim Anderson +1
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. Such existing…
Confident AI
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 pre…
Bottom-up Hierarchical Classification Using Confusion-based Logit Compression
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 infer…
Revisiting Batch Norm Initialization
Jim Davis, Logan Frank
Batch normalization (BN) is comprised of a normalization component followed by an affine transformation and has become essential for training deep neural networks. Standard initial…
Posterior Adaptation With New Priors
Jim Davis
Classification approaches based on the direct estimation and analysis of posterior probabilities will degrade if the original class priors begin to change. We prove that a unique (…