{"ID":2875820,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.01275","arxiv_id":"2509.01275","title":"Novel Category Discovery with X-Agent Attention for Open-Vocabulary Semantic Segmentation","abstract":"Open-vocabulary semantic segmentation (OVSS) conducts pixel-level classification via text-driven alignment, where the domain discrepancy between base category training and open-vocabulary inference poses challenges in discriminative modeling of latent unseen category. To address this challenge, existing vision-language model (VLM)-based approaches demonstrate commendable performance through pre-trained multi-modal representations. However, the fundamental mechanisms of latent semantic comprehension remain underexplored, making the bottleneck for OVSS. In this work, we initiate a probing experiment to explore distribution patterns and dynamics of latent semantics in VLMs under inductive learning paradigms. Building on these insights, we propose X-Agent, an innovative OVSS framework employing latent semantic-aware ``agent'' to orchestrate cross-modal attention mechanisms, simultaneously optimizing latent semantic dynamic and amplifying its perceptibility. Extensive benchmark evaluations demonstrate that X-Agent achieves state-of-the-art performance while effectively enhancing the latent semantic saliency.","short_abstract":"Open-vocabulary semantic segmentation (OVSS) conducts pixel-level classification via text-driven alignment, where the domain discrepancy between base category training and open-vocabulary inference poses challenges in discriminative modeling of latent unseen category. To address this challenge, existing vision-language...","url_abs":"https://arxiv.org/abs/2509.01275","url_pdf":"https://arxiv.org/pdf/2509.01275v2","authors":"[\"Jiahao Li\",\"Yang Lu\",\"Yachao Zhang\",\"Fangyong Wang\",\"Yuan Xie\",\"Yanyun Qu\"]","published":"2025-09-01T09:01:58Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Language Model\"]","has_code":false}