# Efficient Segmentation: Learning Downsampling Near Semantic Boundaries

arXiv: https://arxiv.org/abs/1907.07156 · HTML: https://mlsanity.com/paper/1907.07156/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Jul 2019.

## Built on by (most cited first, 30 of 33)

- [Dynamic Neural Networks: A Survey](https://mlsanity.com/paper/2102.04906/) (2021)
- [Boundary IoU: Improving Object-Centric Image Segmentation Evaluation](https://mlsanity.com/paper/2103.16562/) (2021)
- [AdaInt: Learning Adaptive Intervals for 3D Lookup Tables on Real-time Image Enhancement](https://mlsanity.com/paper/2204.13983/) (2022)
- [Token Pooling in Vision Transformers](https://mlsanity.com/paper/2110.03860/) (2021)
- [Contrastive Boundary Learning for Point Cloud Segmentation](https://mlsanity.com/paper/2203.05272/) (2022)
- [FOVEA: Foveated Image Magnification for Autonomous Navigation](https://mlsanity.com/paper/2108.12102/) (2021)
- [Resolution learning in deep convolutional networks using scale-space theory](https://mlsanity.com/paper/2106.03412/) (2021)
- [Variable-rate discrete representation learning](https://mlsanity.com/paper/2103.06089/) (2021)
- [Learning to Downsample for Segmentation of Ultra-High Resolution Images](https://mlsanity.com/paper/2109.11071/) (2021)
- [SALISA: Saliency-based Input Sampling for Efficient Video Object Detection](https://mlsanity.com/paper/2204.02397/) (2022)
- [Learning to Zoom and Unzoom](https://mlsanity.com/paper/2303.15390/) (2023)
- [Efficient High-Resolution Deep Learning: A Survey](https://mlsanity.com/paper/2207.13050/) (2022)
- [Contour-Aware Equipotential Learning for Semantic Segmentation](https://mlsanity.com/paper/2210.00223/) (2022)
- [Differentiable Sensor Layouts for End-to-End Learning of Task-Specific Camera Parameters](https://mlsanity.com/paper/2304.14736/) (2023)
- [Soft labelling for semantic segmentation: Bringing coherence to label down-sampling](https://mlsanity.com/paper/2302.13961/) (2023)
- [Content-Adaptive Downsampling in Convolutional Neural Networks](https://mlsanity.com/paper/2305.09504/) (2023)
- [BFANet: Revisiting 3D Semantic Segmentation with Boundary Feature Analysis](https://mlsanity.com/paper/2503.12539/) (2025)
- [Efficient Deep Learning Pipelines for Accurate Cost Estimations Over Large Scale Query Workload](https://mlsanity.com/paper/2103.12465/) (2021)
- [Spatial Frequency Modulation for Semantic Segmentation](https://mlsanity.com/paper/2507.11893/) (2025)
- [The Ikshana Hypothesis of Human Scene Understanding](https://mlsanity.com/paper/2101.10837/) (2021)
- [Robust Trust Region for Weakly Supervised Segmentation](https://mlsanity.com/paper/2104.01948/) (2021)
- [Heterogeneous Grid Convolution for Adaptive, Efficient, and Controllable Computation](https://mlsanity.com/paper/2104.11176/) (2021)
- [Foveated Instance Segmentation](https://mlsanity.com/paper/2503.21854/) (2025)
- [Ink Detection from Surface Topography of the Herculaneum Papyri](https://mlsanity.com/paper/2603.27698/) (2026)
- [CatSIM: A Categorical Image Similarity Metric](https://mlsanity.com/paper/2004.09073/) (2020)
- [DANCE: DAta-Network Co-optimization for Efficient Segmentation Model Training and Inference](https://mlsanity.com/paper/2107.07706/) (2021)
- [PDFNet: Pointwise Dense Flow Network for Urban-Scene Segmentation](https://mlsanity.com/paper/2109.10083/) (2021)
- [Polyline Generative Navigable Space Segmentation for Autonomous Visual Navigation](https://mlsanity.com/paper/2111.00063/) (2021)
- [Joint Hierarchical Priors and Adaptive Spatial Resolution for Efficient Neural Image Compression](https://mlsanity.com/paper/2307.02273/) (2023)
- [DBF-Net: A Dual-Branch Network with Feature Fusion for Ultrasound Image Segmentation](https://mlsanity.com/paper/2411.11116/) (2024)

## Abstract (arXiv)

Many automated processes such as auto-piloting rely on a good semantic segmentation as a critical component. To speed up performance, it is common to downsample the input frame. However, this comes at the cost of missed small objects and reduced accuracy at semantic boundaries. To address this problem, we propose a new content-adaptive downsampling technique that learns to favor sampling locations near semantic boundaries of target classes. Cost-performance analysis shows that our method consistently outperforms the uniform sampling improving balance between accuracy and computational efficiency. Our adaptive sampling gives segmentation with better quality of boundaries and more reliable support for smaller-size objects.