<ul><li>This paper presents a comprehensive evaluation of instance segmentation models with respect to real-world image corruptions and out-of-domain image collections.</li><li>The evaluation shows the generalization capability of models, an essential aspect of real-world applications and domain adaptation.</li><li>The study includes analysis of network architectures, normalization layers, pretrained networks, and the effect of multi-task training on robustness and generalization.</li><li>Insights from the study indicate the impact of group normalization, batch normalization, and image resolution on the performance of instance segmentation models.</li></ul>

Benchmarking the Robustness of Instance Segmentation Models

Discover more