Matthew Kowal

Pavel Tokmakov

CoRR, 2024

2023

SegMix: Co-occurrence Driven Mixup for Semantic Segmentation and Adversarial Robustness.

[BibT_eX]

[DOI]

Int. J. Comput. Vis., March, 2023

2022

Quantifying and Learning Static vs. Dynamic Information in Deep Spatiotemporal Networks.

[BibT_eX]

[DOI]

CoRR, 2022

A Deeper Dive Into What Deep Spatiotemporal Networks Encode: Quantifying Static vs. Dynamic Information.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

Maximizing Mutual Shape Information.

[BibT_eX]

[DOI]

Proceedings of the 33rd British Machine Vision Conference 2022, 2022

2021

Position, Padding and Predictions: A Deeper Look at Position Information in CNNs.

[BibT_eX]

[DOI]

Sen Jia

CoRR, 2021

Shape or Texture: Understanding Discriminative Features in CNNs.

[BibT_eX]

[DOI]

Proceedings of the 9th International Conference on Learning Representations, 2021

Global Pooling, More than Meets the Eye: Position Information is Encoded Channel-Wise in CNNs.

[BibT_eX]

[DOI]

Sen Jia

Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021

Simpler Does It: Generating Semantic Labels with Objectness Guidance.

[BibT_eX]

[DOI]

Sen Jia

Proceedings of the 32nd British Machine Vision Conference 2021, 2021

2020

Feature Binding with Category-Dependant MixUp for Semantic Segmentation and Adversarial Robustness.

[BibT_eX]

[DOI]