1 code implementation • CVPR 2021 • Vikram V. Ramaswamy, Sunnie S. Y. Kim, Olga Russakovsky
Fairness in visual recognition is becoming a prominent and critical topic of discussion as recognition systems are deployed at scale in the real world.
1 code implementation • 6 Dec 2021 • Sunnie S. Y. Kim, Nicole Meister, Vikram V. Ramaswamy, Ruth Fong, Olga Russakovsky
As AI technology is increasingly applied to high-impact, high-risk domains, there have been a number of new methods aimed at making AI models more human interpretable.
1 code implementation • 10 May 2022 • Angelina Wang, Vikram V. Ramaswamy, Olga Russakovsky
In this work, we grapple with questions that arise along three stages of the machine learning pipeline when incorporating intersectionality as multiple demographic attributes: (1) which demographic attributes to include as dataset labels, (2) how to handle the progressively smaller size of subgroups during model training, and (3) how to move beyond existing evaluation metrics when benchmarking model fairness for more subgroups.
no code implementations • 15 Jun 2022 • Vikram V. Ramaswamy, Sunnie S. Y. Kim, Nicole Meister, Ruth Fong, Olga Russakovsky
Specifically, we develop a novel explanation framework ELUDE (Explanation via Labelled and Unlabelled DEcomposition) that decomposes a model's prediction into two parts: one that is explainable through a linear combination of the semantic attributes, and another that is dependent on the set of uninterpretable features.
no code implementations • ICCV 2023 • Nicole Meister, Dora Zhao, Angelina Wang, Vikram V. Ramaswamy, Ruth Fong, Olga Russakovsky
Gender biases are known to exist within large-scale visual datasets and can be reflected or even amplified in downstream models.
1 code implementation • CVPR 2023 • Vikram V. Ramaswamy, Sunnie S. Y. Kim, Ruth Fong, Olga Russakovsky
Second, we find that concepts in the probe dataset are often less salient and harder to learn than the classes they claim to explain, calling into question the correctness of the explanations.
no code implementations • 27 Mar 2023 • Vikram V. Ramaswamy, Sunnie S. Y. Kim, Ruth Fong, Olga Russakovsky
In this work, we propose UFO, a unified method for controlling Understandability and Faithfulness Objectives in concept-based explanations.