# MaskAttn-UNet: A Mask Attention-Driven Framework for Universal Low-Resolution Image Segmentation

Source: [MaskAttn-UNet: A Mask Attention-Driven Framework for Universal Low-Resolution Image Segmentation](<https://www.sota2.com/research/paper/68fa78771e209131cea7881a>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T04:39:15.781Z

Authors: Anzhe Cheng, Chenzhong Yin, Yu Chang, Heng Ping, Shixuan Li, Shahin Nazarian, Paul Bogdan

Published: 2025-03-11T22:43:26.000Z

## Abstract

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.

## 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](<https://arxiv.org/abs/2503.10686>)

[PDF](<https://arxiv.org/pdf/2503.10686.pdf>)
