Search Results for author: Brady Zhou

Found 5 papers, 3 papers with code

Cross-view Transformers for real-time Map-view Semantic Segmentation

2 code implementations CVPR 2022 Brady Zhou, Philipp Krähenbühl

The architecture consists of a convolutional image encoder for each view and cross-view transformer layers to infer a map-view semantic segmentation.

Bird's-Eye View Semantic Segmentation Segmentation

Domain Adaptation Through Task Distillation

1 code implementation27 Aug 2020 Brady Zhou, Nimit Kalra, Philipp Krähenbühl

We use these recognition datasets to link up a source and target domain to transfer models between them in a task distillation framework.

Autonomous Driving Domain Adaptation

Does computer vision matter for action?

no code implementations30 May 2019 Brady Zhou, Philipp Krähenbühl, Vladlen Koltun

Thus the central question of our work: Does computer vision matter for action?

Don't let your Discriminator be fooled

no code implementations ICLR 2019 Brady Zhou, Philipp Krähenbühl

We experimentally show that any GAN objective, including Wasserstein GANs, benefit from adversarial robustness both quantitatively and qualitatively.

Adversarial Robustness

Cannot find the paper you are looking for? You can Submit a new open access paper.