# Small Objects Matters in Weakly-supervised Semantic Segmentation Source: [Small Objects Matters in Weakly-supervised Semantic Segmentation]() Collection index: [llms.txt]() Data updated: 2025-10-27T06:26:19.104Z Authors: Cheolhyun Mun, Sanghuk Lee, Youngjung Uh, Junsuk Choe, Hyeran Byun Published: 2023-09-25T13:15:57.000Z ## Abstract Weakly-supervised semantic segmentation (WSSS) performs pixel-wise classification given only image-level labels for training. Despite the difficulty of this task, the research community has achieved promising results over the last five years. Still, current WSSS literature misses the detailed sense of how well the methods perform on different sizes of objects. Thus we propose a novel evaluation metric to provide a comprehensive assessment across different object sizes and collect a size-balanced evaluation set to complement PASCAL VOC. With these two gadgets, we reveal that the existing WSSS methods struggle in capturing small objects. Furthermore, we propose a size-balanced cross-entropy loss coupled with a proper training strategy. It generally improves existing WSSS methods as validated upon ten baselines on three different datasets. ## 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]()