# Object Segmentation using Pixel-wise Adversarial Loss Source: [Object Segmentation using Pixel-wise Adversarial Loss]() Collection index: [llms.txt]() Data updated: 2025-10-25T21:48:29.028Z Authors: Ricard Durall, Franz-Josef Pfreundt, Ullrich K\\"othe, Janis Keuper Published: 2019-09-23T12:52:54.000Z ## Abstract Recent deep learning based approaches have shown remarkable success on object segmentation tasks. However, there is still room for further improvement. Inspired by generative adversarial networks, we present a generic end-to-end adversarial approach, which can be combined with a wide range of existing semantic segmentation networks to improve their segmentation performance. The key element of our method is to replace the commonly used binary adversarial loss with a high resolution pixel-wise loss. In addition, we train our generator employing stochastic weight averaging fashion, which further enhances the predicted output label maps leading to state-of-the-art results. We show, that this combination of pixel-wise adversarial training and weight averaging leads to significant and consistent gains in segmentation performance, compared to the baseline models. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()