Skip to content

Anh Totti Nguyen

Associate Professor of Computer Science, Auburn University

  • Current Page Parent Research
  • Lab
  • Press
  • Work with me
  • Teaching
    • Courses
    • K-6 AI club
  • About
  • CV
  • Current Page Parent Research
  • Lab
  • Press
  • Work with me
  • Teaching
    • Courses
    • K-6 AI club
  • About
  • CV

May 2024 0

PEEB classifies this Dogs-120 image into Alaskan Malamute (softmax: 0.199) due to the matching between the image regions and associated textual part descriptors. In contrast, the explanation shows that the input image is not classified into Cairn Terrier mostly because its ears and body regions do not match the text descriptors, i.e., dot products are 0.000 and 0.000, respectively. See Appendix G for more qualitative examples.

Share
  • Previous PEEB: Part-based Image Classifiers with an Explainable and Editable Language Bottleneck
Computer Vision

GlitchBench: Can large multimodal models detect video game glitches?

  • April 10, 2024
NLP

B-score: Detecting biases in large language models using response history

  • May 30, 2025
Computer Vision Explainable AI

gScoreCAM: What objects is CLIP looking at?

  • September 30, 2022
Computer Vision

Strike (with) a Pose: Neural networks are easily fooled by strange poses of familiar objects

  • November 30, 2019

Anh Totti Nguyen © 2026. All Rights Reserved.

Powered by WordPress. Theme by Alx.