Papers › Numerical Coordinate Regression with Convolutional Neural Networks

Numerical Coordinate Regression with Convolutional Neural Networks

23 Jan 2018arXiv:1801.07372archive 2025-07-28

Aiden Nibali, Zhen He, Stuart Morgan, Luke Prendergast

We study deep learning approaches to inferring numerical coordinates for points of interest in an input image. Existing convolutional neural network-based solutions to this problem either take a heatmap matching approach or regress to coordinates with a fully connected output layer. Neither of these approaches is ideal, since the former is not entirely differentiable, and the latter lacks inherent spatial generalization. We propose our differentiable spatial to numerical transform (DSNT) to fill this gap. The DSNT layer adds no trainable parameters, is fully differentiable, and exhibits good spatial generalization. Unlike heatmap matching, DSNT works well with low heatmap resolutions, so it can be dropped in as an output layer for a wide range of existing fully convolutional architectures. Consequently, DSNT offers a better trade-off between inference speed and prediction accuracy compared to existing techniques. When used to replace the popular heatmap matching approach used in almost all state-of-the-art methods for pose estimation, DSNT gives better prediction accuracy for all model architectures tested.

PaperPDFCode

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

Code

anibali/dsntnn officialmentioned in paperpytorch report
mansimane/WormML mentioned on GitHubtf report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

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

Tasks

Pose Estimationregression

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Pose Estimation MPII Human Pose DSNTr ResNet-50@28px PCKh-0.5 89.5 #29 of 46 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 BlockConvolutionGlobal Average PoolingHeatmapKaiming InitializationMax PoolingReLUResidual BlockResidual ConnectionSPEED

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