3 papers
cs.CV2025
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…
cs.CV2023
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…
cs.LG2021
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…