General object-based features account for letter perception D Janini, C Hamblin, A Deza, T Konkle PLoS computational biology 18 (9), e1010522, 2022 | 9 | 2022 |
Pruning for interpretable, feature-preserving circuits in cnns C Hamblin, T Konkle, G Alvarez arXiv preprint arXiv:2206.01627, 2022 | 5 | 2022 |
Controlled assessment of CLIP-style language-aligned vision models in prediction of brain & behavioral data C Conwell, JS Prince, CJ Hamblin, GA Alvarez ICLR 2023 Workshop on Mathematical and Empirical Understanding of Foundation …, 2023 | 4 | 2023 |
Towards Disentangling the Roles of Vision & Language in Aesthetic Experience with Multimodal DNNs C Conwell, CJ Hamblin SVRHM 2022 Workshop@ NeurIPS, 2022 | 2 | 2022 |
Feature Accentuation: Revealing'What'Features Respond to in Natural Images C Hamblin, T Fel, S Saha, T Konkle, G Alvarez arXiv preprint arXiv:2402.10039, 2024 | 1 | 2024 |
Understanding Inhibition Through Maximally Tense Images C Hamblin, S Saha, T Konkle, G Alvarez arXiv preprint arXiv:2406.05598, 2024 | | 2024 |
Uncovering the hidden computations of deep neural networks by tracing the trajectory manifold from images to feature activations C Hamblin, T Konkle, G Alvarez Journal of Vision 23 (9), 5671-5671, 2023 | | 2023 |
Understanding the invariances of visual features with separable subnetworks C Hamblin, T Konkle, G Alvarez Journal of Vision 22 (14), 4237-4237, 2022 | | 2022 |
Pruning for Feature-Preserving Circuits in CNNs C Hamblin, T Konkle, G Alvarez arXiv preprint arXiv:2206.01627, 2022 | | 2022 |
VISCNN: A Tool for Visualizing Interpretable Subgraphs in CNNs C Hamblin, G Alvarez Journal of Vision 21 (9), 2674-2674, 2021 | | 2021 |
Feature Accentuation: Explaining'what'features respond to in natural images CJ Hamblin, FEL Thomas, S Saha, T Konkle, GA Alvarez | | |