2022/11/23 by Thomas M. Hehn, Hehn, Thomas M., Julian F. P. Kooij +3
Computer Science · #Advanced Vision and Imaging #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Multimodal Machine Learning Applications
paper · pdf · doi:10.48550/arxiv.2211.13309
openalex publication_date 2022/11/23 · openalex created_date 2022/11/30 · openalex updated_date 2026/07/28
Various state-of-the-art self-supervised visual representation learning approaches take advantage of data from multiple sensors by aligning the feature representations across views and/or modalities. In this work, we investigate how aligning representations affects the visual features obtained from cross-view and cross-modal contrastive learning on images and point clouds. On five real-world datasets and on five tasks, we train and evaluate 108 models based on four pretraining variations. We find that cross-modal representation alignment discards complementary visual information, such as color and texture, and instead emphasizes redundant depth cues. The depth cues obtained from pretraining improve downstream depth prediction performance. Also overall, cross-modal alignment leads to more robust encoders than pre-training by cross-view alignment, especially on depth prediction, instance segmentation, and object detection.