# HR-NAS: Searching Efficient High-Resolution Neural Architectures with Lightweight Transformers Source: [HR-NAS: Searching Efficient High-Resolution Neural Architectures with Lightweight Transformers]() Collection index: [llms.txt]() Data updated: 2026-01-04T05:07:32.902Z Authors: Mingyu Ding, Xiaochen Lian, Linjie Yang, Peng Wang, Xiaojie Jin, Zhiwu Lu, Ping Luo Published: 2021-06-11T18:11:36.000Z ## Abstract High-resolution representations (HR) are essential for dense prediction tasks such as segmentation, detection, and pose estimation. Learning HR representations is typically ignored in previous Neural Architecture Search (NAS) methods that focus on image classification. This work proposes a novel NAS method, called HR-NAS, which is able to find efficient and accurate networks for different tasks, by effectively encoding multiscale contextual information while maintaining high-resolution representations. In HR-NAS, we renovate the NAS search space as well as its searching strategy. To better encode multiscale image contexts in the search space of HR-NAS, we first carefully design a lightweight transformer, whose computational complexity can be dynamically changed with respect to different objective functions and computation budgets. To maintain high-resolution representations of the learned networks, HR-NAS adopts a multi-branch architecture that provides convolutional encoding of multiple feature resolutions, inspired by HRNet. Last, we proposed an efficient fine-grained search strategy to train HR-NAS, which effectively explores the search space, and finds optimal architectures given various tasks and computation resources. HR-NAS is capable of achieving state-of-the-art trade-offs between performance and FLOPs for three dense prediction tasks and an image classification task, given only small computational budgets. For example, HR-NAS surpasses SqueezeNAS that is specially designed for semantic segmentation while improving efficiency by 45.9%. Code is available at https://github.com/dingmyu/HR-NAS ## 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. - [Human Pose Estimation on COCO keypoint (val)](): Human Pose Estimation; COCO keypoint (val); AP: 75.5. - [3D Vehicle Detection on KITTI (val split 1)](): Vehicle 3D Detection; KITTI (val split 1); AP (Moderate): 78.49. - [Image Classification on ImageNet 1k (val) (Top-1 Accuracy)](): Image Classification; ImageNet-1k (val); Top-1 Acc: 77.3. - [Semantic Segmentation on ADE20K (val)](): Semantic segmentation; ADE20K (val); mIoU: 34.92. - [Semantic Segmentation on Cityscapes (val) (mIoU only)](): Semantic segmentation; Cityscapes (val); mIoU: not recorded. ## Original sources and implementation [Original paper]() [PDF]() [Implementation]()