Skip to Main content Skip to Navigation
Preprints, Working Papers, ...

Cross-modal Learning for Domain Adaptation in 3D Semantic Segmentation

Abstract : Domain adaptation is an important task to enable learning when labels are scarce. While most works focus only on the image modality, there are many important multi-modal datasets. In order to leverage multi-modality for domain adaptation, we propose cross-modal learning, where we enforce consistency between the predictions of two modalities via mutual mimicking. We constrain our network to make correct predictions on labeled data and consistent predictions across modalities on unlabeled target-domain data. Experiments in unsupervised and semi-supervised domain adaptation settings prove the effectiveness of this novel domain adaptation strategy. Specifically, we evaluate on the task of 3D semantic segmentation using the image and point cloud modality. We leverage recent autonomous driving datasets to produce a wide variety of domain adaptation scenarios including changes in scene layout, lighting, sensor setup and weather, as well as the synthetic-to-real setup. Our method significantly improves over previous uni-modal adaptation baselines on all adaption scenarios. Code will be made available.
Complete list of metadata

https://hal.inria.fr/hal-03140938
Contributor : Raoul de Charette Connect in order to contact the contributor
Submitted on : Sunday, February 14, 2021 - 4:15:34 PM
Last modification on : Friday, January 21, 2022 - 3:16:33 AM

Links full text

Identifiers

  • HAL Id : hal-03140938, version 1
  • ARXIV : 2101.07253

Collections

Citation

Maximilian Jaritz, Tuan-Hung Vu, Raoul de Charette, Émilie Wirbel, Patrick Pérez. Cross-modal Learning for Domain Adaptation in 3D Semantic Segmentation. 2021. ⟨hal-03140938⟩

Share

Metrics

Les métriques sont temporairement indisponibles