通过掩码注意力提升低分辨率图像分割精度
MaskAttn-UNet: A Mask Attention-Driven Framework for Universal Low-Resolution Image Segmentation
- 引入掩码注意力机制，聚焦重要区域并抑制背景
- 在128x128输入下达到与顶尖方法相当的准确率
- 计算成本远低于基于Transformer的模型，适合资源受限场景
低分辨率图像分割在机器人、增强现实和大规模场景理解等实际应用中至关重要，因计算限制常无法获取高分辨率数据。为此，我们提出MaskAttn-UNet，一种通过掩码注意力机制增强传统U-Net架构的新分割框架。该模型能选择性强化关键区域，抑制无关背景，在复杂杂乱场景中提升分割精度。不同于常规U-Net变体，MaskAttn-UNet有效平衡局部特征提取与全局上下文感知，尤其适用于低分辨率输入。我们在三个基准数据集上对128x128输入进行评估，结果表明其在语义、实例和全景分割任务中表现优异，性能接近当前最优方法，且计算开销显著低于基于Transformer的模型，为资源受限场景下的低分辨率分割提供了高效可扩展的解决方案。
原文摘要 · Abstract (English)
Low-resolution image segmentation is crucial in real-world applications such as robotics, augmented reality, and large-scale scene understanding, where high-resolution data is often unavailable due to computational constraints. To address this challenge, we propose MaskAttn-UNet, a novel segmentation framework that enhances the traditional U-Net architecture via a mask attention mechanism. Our model selectively emphasizes important regions while suppressing irrelevant backgrounds, thereby improving segmentation accuracy in cluttered and complex scenes. Unlike conventional U-Net variants, MaskAttn-UNet effectively balances local feature extraction with broader contextual awareness, making it particularly well-suited for low-resolution inputs. We evaluate our approach on three benchmark datasets with input images rescaled to 128x128 and demonstrate competitive performance across semantic, instance, and panoptic segmentation tasks. Our results show that MaskAttn-UNet achieves accuracy comparable to state-of-the-art methods at significantly lower computational cost than transformer-based models, making it an efficient and scalable solution for low-resolution segmentation in resource-constrained scenarios.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。