# Recalling Holistic Information for Semantic Segmentation Source: [Recalling Holistic Information for Semantic Segmentation]() Collection index: [llms.txt]() Data updated: 2025-10-25T20:31:19.733Z Authors: Hexiang Hu, Zhiwei Deng, Guang-tong Zhou, Fei Sha, Greg Mori Published: 2016-11-24T03:46:37.000Z ## Abstract Semantic segmentation requires a detailed labeling of image pixels by object category. Information derived from local image patches is necessary to describe the detailed shape of individual objects. However, this information is ambiguous and can result in noisy labels. Global inference of image content can instead capture the general semantic concepts present. We advocate that high-recall holistic inference of image concepts provides valuable information for detailed pixel labeling. We build a two-stream neural network architecture that facilitates information flow from holistic information to local pixels, while keeping common image features shared among the low-level layers of both the holistic analysis and segmentation branches. We empirically evaluate our network on four standard semantic segmentation datasets. Our network obtains state-of-the-art performance on PASCAL-Context and NYUDv2, and ablation studies verify its effectiveness on ADE20K and SIFT-Flow. ## 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. - [Semantic Segmentation on NYU Depth V2 (test)](): Semantic segmentation; NYU Depth V2 (test); mIoU: 38.8. - [Semantic Segmentation on Pascal Context (test)](): Semantic segmentation; Pascal Context (test); mIoU: 45.8. - [Semantic Segmentation on ADE20K](): Semantic segmentation; ADE20K; mIoU: 37.93. ## Original sources and implementation [Original paper]() [PDF]()