{"ID":2895702,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.08554","arxiv_id":"2507.08554","title":"Image Translation with Kernel Prediction Networks for Semantic Segmentation","abstract":"Semantic segmentation relies on many dense pixel-wise annotations to achieve the best performance, but owing to the difficulty of obtaining accurate annotations for real world data, practitioners train on large-scale synthetic datasets. Unpaired image translation is one method used to address the ensuing domain gap by generating more realistic training data in low-data regimes. Current methods for unpaired image translation train generative adversarial networks (GANs) to perform the translation and enforce pixel-level semantic matching through cycle consistency. These methods do not guarantee that the semantic matching holds, posing a problem for semantic segmentation where performance is sensitive to noisy pixel labels. We propose a novel image translation method, Domain Adversarial Kernel Prediction Network (DA-KPN), that guarantees semantic matching between the synthetic label and translation. DA-KPN estimates pixel-wise input transformation parameters of a lightweight and simple translation function. To ensure the pixel-wise transformation is realistic, DA-KPN uses multi-scale discriminators to distinguish between translated and target samples. We show DA-KPN outperforms previous GAN-based methods on syn2real benchmarks for semantic segmentation with limited access to real image labels and achieves comparable performance on face parsing.","short_abstract":"Semantic segmentation relies on many dense pixel-wise annotations to achieve the best performance, but owing to the difficulty of obtaining accurate annotations for real world data, practitioners train on large-scale synthetic datasets. Unpaired image translation is one method used to address the ensuing domain gap by...","url_abs":"https://arxiv.org/abs/2507.08554","url_pdf":"https://arxiv.org/pdf/2507.08554v1","authors":"[\"Cristina Mata\",\"Michael S. Ryoo\",\"Henrik Turbell\"]","published":"2025-07-11T12:56:22Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Generative Adversarial Network\"]","has_code":false}