Picture for Marissa Connor

Marissa Connor

The SaTML '24 CNN Interpretability Competition: New Innovations for Concept-Level Interpretability

Add code
Apr 03, 2024
Viaarxiv icon

Learning Internal Representations of 3D Transformations from 2D Projected Inputs

Add code
Mar 31, 2023
Viaarxiv icon

Rethinking Backdoor Data Poisoning Attacks in the Context of Semi-Supervised Learning

Add code
Dec 05, 2022
Viaarxiv icon

Learning Identity-Preserving Transformations on Data Manifolds

Add code
Jun 22, 2021
Figure 1 for Learning Identity-Preserving Transformations on Data Manifolds
Figure 2 for Learning Identity-Preserving Transformations on Data Manifolds
Figure 3 for Learning Identity-Preserving Transformations on Data Manifolds
Figure 4 for Learning Identity-Preserving Transformations on Data Manifolds
Viaarxiv icon

Generative causal explanations of black-box classifiers

Add code
Jun 24, 2020
Figure 1 for Generative causal explanations of black-box classifiers
Figure 2 for Generative causal explanations of black-box classifiers
Figure 3 for Generative causal explanations of black-box classifiers
Figure 4 for Generative causal explanations of black-box classifiers
Viaarxiv icon

Representing Closed Transformation Paths in Encoded Network Latent Space

Add code
Dec 05, 2019
Figure 1 for Representing Closed Transformation Paths in Encoded Network Latent Space
Figure 2 for Representing Closed Transformation Paths in Encoded Network Latent Space
Figure 3 for Representing Closed Transformation Paths in Encoded Network Latent Space
Figure 4 for Representing Closed Transformation Paths in Encoded Network Latent Space
Viaarxiv icon