Papers › ScaleNAS: One-Shot Learning of Scale-Aware Representations for Visual Recognition

ScaleNAS: One-Shot Learning of Scale-Aware Representations for Visual Recognition

30 Nov 2020arXiv:2011.14584archive 2025-07-28

Hsin-Pai Cheng, Feng Liang, Meng Li, Bowen Cheng, Feng Yan, Hai Li, Vikas Chandra, Yiran Chen

Scale variance among different sizes of body parts and objects is a challenging problem for visual recognition tasks. Existing works usually design dedicated backbone or apply Neural architecture Search(NAS) for each task to tackle this challenge. However, existing works impose significant limitations on the design or search space. To solve these problems, we present ScaleNAS, a one-shot learning method for exploring scale-aware representations. ScaleNAS solves multiple tasks at a time by searching multi-scale feature aggregation. ScaleNAS adopts a flexible search space that allows an arbitrary number of blocks and cross-scale feature fusions. To cope with the high search cost incurred by the flexible space, ScaleNAS employs one-shot learning for multi-scale supernet driven by grouped sampling and evolutionary search. Without further retraining, ScaleNet can be directly deployed for different visual recognition tasks with superior performance. We use ScaleNAS to create high-resolution models for two different tasks, ScaleNet-P for human pose estimation and ScaleNet-S for semantic segmentation. ScaleNet-P and ScaleNet-S outperform existing manually crafted and NAS-based methods in both tasks. When applying ScaleNet-P to bottom-up human pose estimation, it surpasses the state-of-the-art HigherHRNet. In particular, ScaleNet-P4 achieves 71.6% AP on COCO test-dev, achieving new state-of-the-art result.

PaperPDF

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Multi-Person Pose EstimationNeural Architecture SearchOne-Shot LearningPose EstimationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Multi-Person Pose Estimation COCO test-dev HigherHRNet (ScaleNet_P4) AP 71.6 #5 of 15 Archive leaderboard report
Multi-Person Pose Estimation COCO test-dev HigherHRNet (ScaleNet_P4) AP50 90.3 #5 of 15 Archive leaderboard report
Multi-Person Pose Estimation COCO test-dev HigherHRNet (ScaleNet_P4) AP75 78.2 #5 of 15 Archive leaderboard report
Multi-Person Pose Estimation COCO test-dev HigherHRNet (ScaleNet_P4) APL 77.2 #5 of 15 Archive leaderboard report
Multi-Person Pose Estimation COCO test-dev HigherHRNet (ScaleNet_P4) APM 67.5 #5 of 15 Archive leaderboard report
Multi-Person Pose Estimation COCO test-dev HigherHRNet (ScaleNet_P4) AR 76.0 #5 of 15 Archive leaderboard report
Multi-Person Pose Estimation COCO test-dev HigherHRNet (ScaleNet_P4) AR50 92.3 #5 of 15 Archive leaderboard report
Multi-Person Pose Estimation CrowdPose HigherHRNet (ScaleNet_P4) mAP @0.5:0.95 71.3 #12 of 28 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionDense ConnectionsGlobal Average PoolingMax PoolingReLUResidual ConnectionScale Aggregation BlockScaleNetSoftmax

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections