|
I am a teaching professor in the Department of Computer Science at Princeton University, where I teach intro and AIML CS courses and conduct research in computer vision and machine learning with a focus on explainable AI. At Princeton, I lead the Looking Glass Lab and frequently collaborate with Professor Olga Russakovsky and the Visual AI Lab. I completed my PhD in the Visual Geometry Group at the University of Oxford, where I was advised by Andrea Vedaldi and funded by the Rhodes Trust and Open Philanthropy. Also at Oxford, I earned a Masters in Neuroscience, where I worked with Rafal Bogacz, Ben Willmore, and Nicol Harper. I received a Bachelors in Computer Science at Harvard University, where I worked with David Cox and Walter Scheirer. Funding acknowledgements: Looking Glass Lab is grateful to Princeton SEAS and Open Philanthropy for generous support of our research.
Email | CV | Bio | Google Scholar | GitHub |
|
|
On leave in Spring 2026. I'm on leave this semester; below are few pointers to common questions I get. COS324. Please see course website for the best ways to reach the current course staff (it should be updated by late January 2026). Research/IW/thesis advising. I am excited to work with Princeton students! I am not accepting students for Spring 2026 but will be accepting students starting Fall 2027. If you are a...
Other Princeton things. Engaging with students is one of my favorite parts of the job. If you'd like to reach me about other Princeton-related things (e.g. participating in a student event, grabbing a meal), shoot me an email! I won't be able to do things in Spring 2026 but may be available in the Fall. Non-Princeton asks. Unfortunately, I am not accepting most non-Princeton requests in Spring 2026 while I am on leave. |
|
|
Members
Collaborators
Awards
Alumni
|
|
My research interests are in computer vision, machine learning (ML), and human-computer interaction (HCI), with a particular focus on explainable AI and ML fairness. Most of my work focuses on developing novel techniques for understanding AI models post-hoc, designing new AI models that are interpretable-by-design, and/or introducing paradigms for finding and correcting existing failure points in AI models. See Google Scholar for the most updated list of papers. * denotes equal contribution; ^ denotes peer-reviewed, non-archival work (e.g. accepted to non-archival workshop). |
Rawand Aziz
Matthew Barrett
Emilio Chan
Anha Khan
Ben Wachspress
Indu Panigrahi
Sunnie S. Y. Kim
Prof. Parastoo Abtahi
Prof. Andrés Monroy-Hernández
Prof. Vikram V. Ramaswamy
Prof. Olga Russakovsky
|
Anha Khan, Romina Mahinpei, Maryam Hedayati, Victoria Dean, Ruth Fong
SIGCSE TS (ACM Student Research Competition [SRC]), 2026 (1st Place at SRC 🏆)
paper | LinkedIn post | bibtex
We design and study a custom LLM chatbot used by students in an introductory machine learning course to evaluate the effect of generative AI on student behavior and learning outcomes.
Indu Panigrahi, Sunnie S. Y. Kim*, Amna Liaqat*, Rohan Jinturkar, Olga Russakovsky, Ruth Fong, Parastoo Abtahi
CHI Extended Abstracts (Late-Breaking Work), 2025
paper | project page | bibtex
We study how end-users leverage and perceive interactive computer vision explanations.
Devon Ulrich and Ruth Fong
CVPR Workshop on Computer Vision for XAI (CV4XAI), 2024
arXiv | code | bibtex
We present an interactive visualization tool that allows you to perform a reverse image search for similar image regions using intermediate activations.
Sunnie S. Y. Kim, Elizabeth Anne Watkins, Olga Russakovsky, Ruth Fong, Andrés Monroy-Hernández
FAccT, 2023
arXiv | project page | bibtex
We study how end-users trust AI in a real-world context. Concretely, we describe multiple aspects of trust in AI and how human, AI, and context-related factors influence each.
Vikram V. Ramaswamy, Sunnie S. Y. Kim, Ruth Fong, Olga Russakovsky
arXiv, 2023
arXiv | bibtex
We introduce a novel concept-based explanation framework for CNNs: UFO, which is a method for controlling the understandability and faithfulness of concept-based explanations using well-defined objective functions for the two qualities.
Indu Panigrahi, Ryan Manzuk, Adam Maloof, Ruth Fong
CVPR Workshop on Learning with Limited Labelled Data for Image and Video Understanding, 2023
arXiv | bibtex
We explore how to improve a model for segmenting coral reef fossils by first understanding its systematic failures and second ``editing'' the model to mitigate said failures.
Sunnie S. Y. Kim, Elizabeth Anne Watkins, Olga Russakovsky, Ruth Fong, Andrés Monroy-Hernández
CHI, 2023 (Honorable Mention award 🏆)
arXiv | supp | 30-sec video | 10-min video | bibtex
We explore how explainability can support human-AI interaction by interviewing 20 end-users of a real-world AI application. Specifically, we study (1) what XAI needs people have, (2) how people intend to use XAI explanations, and (3) how people perceive existing XAI methods.
Vikram V. Ramaswamy, Sunnie S. Y. Kim, Ruth Fong, Olga Russakovsky
CVPR, 2023
arXiv | bibtex
We analyze three commonly overlooked factors in concept-based explanations, (1) the choice of the probe dataset, (2) the saliency of concepts in the probe dataset, (3) the number of concepts used in explanations, and make suggestions for future development and analysis of concept-based interpretability methods.
Nicole Meister*, Dora Zhao*, Angelina Wang, Vikram V. Ramaswamy, Ruth Fong, Olga Russakovsky
ICCV, 2023
arXiv | project page | bibtex
We demonstrate the pervasive-ness of gender artifacts in popular computer vision datasets (e.g. COCO and OpenImages). We find that all of the following (and more) are gender artifacts: the mean value of color channels (i.e. mean RGB), the pose and location of people, and most co-located objects.
Vikram V. Ramaswamy, Sunnie S. Y. Kim, Nicole Meister, Ruth Fong, Olga Russakovsky
arXiv, 2022
arXiv | bibtex
We present ELUDE, a novel explanation framework that decomposes a model's prediction into two components: 1. using labelled, semantic attributes (e.g. fur, paw, etc.) and 2. using an unlabelled, low-rank feature space.
Sunnie S. Y. Kim, Nicole Meister, Vikram V. Ramaswamy, Ruth Fong, Olga Russakovsky
ECCV, 2022
arXiv | project page | extended abstract | code | 2-min video | bibtex
We introduce HIVE, a novel human evaluation framework for diverse interpretability methods in computer vision, and develop metrics that measure achievement on two desiderata for explanations used to assist human decision making: (1) Explanations should allow users to distinguish between correct and incorrect predictions. (2) Explanations should be understandable to users.
Ruth Fong, Alexander Mordvintsev, Andrea Vedaldi, Chris Olah
VISxAI, 2021
interactive article | code | bibtex
We introduce a novel interactive visualization that allows machine learning practitioners and researchers to easily observe, explore, and compare how a neural network perceives different image regions.
Mandela Patrick*, Yuki M. Asano*, Polina Kuznetsova, Ruth Fong, João F. Henriques, Geoffrey Zweig, and Andrea Vedaldi
ICCV, 2021
arXiv | code | bibtex
We give transformations the prominence they deserve by introducing a systematic framework suitable for contrastive learning. SOTA video representation learning by learning (in)variances systematically.
Iro Laina, Ruth Fong, and Andrea Vedaldi
NeurIPS, 2020
arxiv | supp | bibtex
We introduce two novel human evaluation metrics for quantifying for evaluating the interpretability of clusters discovered via self-supervised methods. We also outline how to partially approximate one of the metrics using a group captioning model.
Kurtis Evan David, Qiang Liu, and Ruth Fong
NeurIPS Workshop on Algorithmic Fairness through the Lens of Causality and Interpretability (AFCI), 2020
arxiv | supp | poster | bibtex
We introduce a novel paradigm for debiasing CNNs by encouraging salient concept vectors to orthogonal to class vectors in the activation space of an intermediate CNN layer (e.g., orthogonalizing gender and oven concepts in conv5).
Diego Marcos, Ruth Fong, Sylvain Lobry, Rémi Flamary, Nicolas Courty, and Devis Tuia
ACCV, 2020
arxiv | supp | code | bibtex
We introduce an interpretable-by-design machine vision model that learns to sparse groupings of interpretable concepts and demonstrate the utility of our novel architecture on scenicness prediction.
Sylvestre-Alvise Rebuffi*, Ruth Fong*, Xu Ji*, and Andrea Vedaldi
CVPR, 2020
arxiv | code | bibtex
We outline a novel framework that unifies many backpropagation saliency methods. Furthermore, we introduce NormGrad, a saliency method that considers the spatial contribution of the gradients of convolutional weights. We also systematically study the effects of combining saliency maps at different layers. Finally, we introduce a class-sensitivity metric and a meta-learning inspired technique that can be applied to any saliency method to improve class sensitivity.
Miles Brundage*, Shahar Avin*, Jasmine Wang*, Haydn Belfield*, Gretchen Krueger*, … ,
Ruth Fong, et al.
arXiv, 2020
arxiv | project page | bibtex
This report suggests various steps that different stakeholders can take to make it easier to verify claims made about AI systems and their associated development processes. The authors believe the implementation of such mechanisms can help make progress on one component of the multifaceted problem of ensuring that AI development is conducted in a trustworthy fashion.
Ruth Fong*, Mandela Patrick*, and Andrea Vedaldi
ICCV, 2019 (Oral)
arxiv | supp | poster | code (TorchRay) | 4-min video | bibtex
We introduce extremal perturbations, an novel attribution method that highlights "where" a model is "looking." We improve upon Fong and Vedaldi, 2017 by separating out regularization on the size and smoothness of a perturbation mask from the attribution objective of learning a mask that maximally affects a model's output; we also extend our work to intermediate channel representations.
Ruth Fong and Andrea Vedaldi
ICCV Workshop on Interpreting and Explaining Visual Artificial Intelligence Models, 2019
paper | bibtex | code (coming soon)
We introduce a simple paradigm based on batch augmentation for leveraging input-level occlusions (both stochastic and saliency-based) to improve ImageNet image classification. We also demonstrate the necessary of batch augmentation and quantify the robustness of different CNN architectures to occlusion via ablation studies.
Ruth Fong and Andrea Vedaldi
CVPR, 2018 (Spotlight)
arxiv | supp | bibtex | code | 4-min video | slides
Investigating how human-interpretable visual concepts (i.e., textures, objects, etc.) are encoded across hidden units of a convolutional neural network (CNN) layer as well as across CNN layers.
Ruth Fong, Walter Scheirer, and David Cox
Scientific Reports, 2018
arxiv |
supp |
Harvard thesis |
bibtex
We introduce a biologically-informed machine learning paradigm for object classification that biases models to better match the learned, internal representations of the visual cortex.
Ruth Fong and Andrea Vedaldi
ICCV, 2017
arxiv | supp | bibtex | code | book chapter (extended) | chapter bibtex
We developed a theoretical framework for learning "explanations" of black box functions like CNNs as well as saliency methods for identifying "where" a computer vision algorithm is looking.
