mlsanityData to 7 Oct 2026

Efficient Segmentation: Learning Downsampling Near Semantic Boundaries

arXiv 1907.07156 ↗First posted 16 Jul 2019cs.CV cs.LGcited by 33

Not on the map. Why?

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.

Key facts. Cited by 33 papers in the map (data through 7 Oct 2026). First posted on arXiv 16 Jul 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2020: 1; 2021: 14; 2022: 5; 2023: 5; 2024: 1; 2025: 6; 2026: 1.

33 papers.

Sort:

  1. 2021Dynamic Neural Networks: A Surveycited by 405
  2. 2021Boundary IoU: Improving Object-Centric Image Segmentation Evaluationcited by 186
  3. 2022AdaInt: Learning Adaptive Intervals for 3D Lookup Tables on Real-time Image Enhancementcited by 70
  4. 2021Token Pooling in Vision Transformerscited by 68
  5. 2022Contrastive Boundary Learning for Point Cloud Segmentationcited by 56
  6. 2021FOVEA: Foveated Image Magnification for Autonomous Navigationcited by 31
  7. 2021Resolution learning in deep convolutional networks using scale-space theorycited by 26
  8. 2021Variable-rate discrete representation learningcited by 24
  9. 2021Learning to Downsample for Segmentation of Ultra-High Resolution Imagescited by 19
  10. 2022SALISA: Saliency-based Input Sampling for Efficient Video Object Detectioncited by 12
  11. 2023Learning to Zoom and Unzoomcited by 11
  12. 2022Efficient High-Resolution Deep Learning: A Surveycited by 9
21 more
  1. 2022Contour-Aware Equipotential Learning for Semantic Segmentationcited by 6
  2. 2023Differentiable Sensor Layouts for End-to-End Learning of Task-Specific Camera Parameterscited by 6
  3. 2023Soft labelling for semantic segmentation: Bringing coherence to label down-samplingcited by 5
  4. 2023Content-Adaptive Downsampling in Convolutional Neural Networkscited by 5
  5. 2025BFANet: Revisiting 3D Semantic Segmentation with Boundary Feature Analysiscited by 5
  6. 2021Efficient Deep Learning Pipelines for Accurate Cost Estimations Over Large Scale Query Workloadcited by 4
  7. 2025Spatial Frequency Modulation for Semantic Segmentationcited by 3
  8. 2021The Ikshana Hypothesis of Human Scene Understandingcited by 1
  9. 2021Robust Trust Region for Weakly Supervised Segmentationcited by 1
  10. 2021Heterogeneous Grid Convolution for Adaptive, Efficient, and Controllable Computationcited by 1
  11. 2025Foveated Instance Segmentationcited by 1
  12. 2026Ink Detection from Surface Topography of the Herculaneum Papyricited by 1
  13. 2020CatSIM: A Categorical Image Similarity Metriccited by 0
  14. 2021DANCE: DAta-Network Co-optimization for Efficient Segmentation Model Training and Inferencecited by 0
  15. 2021PDFNet: Pointwise Dense Flow Network for Urban-Scene Segmentationcited by 0
  16. 2021Polyline Generative Navigable Space Segmentation for Autonomous Visual Navigationcited by 0
  17. 2023Joint Hierarchical Priors and Adaptive Spatial Resolution for Efficient Neural Image Compressioncited by 0
  18. 2024DBF-Net: A Dual-Branch Network with Feature Fusion for Ultrasound Image Segmentationcited by 0
  19. 2025Microsurgical Instrument Segmentation for Robot-Assisted Surgerycited by 0
  20. 2025Modulo Video Recovery via Selective Spatiotemporal Vision Transformercited by 0
  21. 2025HyGE-Occ: Hybrid View-Transformation with 3D Gaussian and Edge Priors for 3D Panoptic Occupancy Predictioncited by 0