mlsanityData to 7 Oct 2026

HyperSeg: Patch-wise Hypernetwork for Real-time Semantic Segmentation

arXiv 2012.11582 ↗First posted 21 Dec 2020cs.CVcited by 66

Not on the map. Why?

Abstract (arXiv)

We present a novel, real-time, semantic segmentation network in which the encoder both encodes and generates the parameters (weights) of the decoder. Furthermore, to allow maximal adaptivity, the weights at each decoder block vary spatially. For this purpose, we design a new type of hypernetwork, composed of a nested U-Net for drawing higher level context features, a multi-headed weight generating module which generates the weights of each block in the decoder immediately before they are consumed, for efficient memory utilization, and a primary network that is composed of novel dynamic patch-wise convolutions. Despite the usage of less-conventional blocks, our architecture obtains real-time performance. In terms of the runtime vs. accuracy trade-off, we surpass state of the art (SotA) results on popular semantic segmentation benchmarks: PASCAL VOC 2012 (val. set) and real-time semantic segmentation on Cityscapes, and CamVid. The code is available: https://nirkin.com/hyperseg.

Key facts. Cited by 66 papers in the map (data through 7 Oct 2026). First posted on arXiv 21 Dec 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 12; 2022: 16; 2023: 15; 2024: 10; 2025: 7; 2026: 6.

66 papers.

Sort:

By area:

  1. 2021Neural Fields in Visual Computing and Beyondcited by 539
  2. 2021SegDiff: Image Segmentation with Diffusion Probabilistic Modelscited by 279
  3. 2021HyperStyle: StyleGAN Inversion with HyperNetworks for Real Image Editingcited by 208
  4. 2022Highly Accurate Dichotomous Image Segmentationcited by 110
  5. 2023A Brief Review of Hypernetworks in Deep Learningcited by 102
  6. 2021HyperInverter: Improving StyleGAN Inversion via Hypernetworkcited by 85
  7. 2022PIDNet: A Real-time Semantic Segmentation Network Inspired by PID Controllerscited by 84
  8. 2024What Matters When Repurposing Diffusion Models for General Dense Perception Tasks?cited by 74
  9. 2022Representation Compensation Networks for Continual Semantic Segmentationcited by 72
  10. 2022Wireless Deep Video Semantic Transmissioncited by 49
  11. 2023HyperE2VID: Improving Event-Based Video Reconstruction via Hypernetworkscited by 37
  12. 2023Time Does Tell: Self-Supervised Time-Tuning of Dense Image Representationscited by 35
38 more
  1. 2024Frequency-Adaptive Dilated Convolution for Semantic Segmentationcited by 34
  2. 2022Learning Local and Global Temporal Contexts for Video Semantic Segmentationcited by 24
  3. 2022DynaGAN: Dynamic Few-shot Adaptation of GANs to Multiple Domainscited by 15
  4. 2022HyperDet3D: Learning a Scene-conditioned 3D Object Detectorcited by 14
  5. 2024HAIR: Hypernetworks-based All-in-One Image Restorationcited by 12
  6. 2021Rethinking Dilated Convolution for Real-time Semantic Segmentationcited by 11
  7. 2023Turbulence in Focus: Benchmarking Scaling Behavior of 3D Volumetric Super-Resolution with BLASTNet 2.0 Datacited by 11
  8. 2021Hyper-Convolution Networks for Biomedical Image Segmentationcited by 10
  9. 2021MFNet: Multi-class Few-shot Segmentation Network with Pixel-wise Metric Learningcited by 10
  10. 2022SFNet: Faster and Accurate Semantic Segmentation via Semantic Flowcited by 10
  11. 2023Efficient Semantic Segmentation by Altering Resolutions for Compressed Videoscited by 8
  12. 2021Semantic Scene Segmentation for Robotics Applicationscited by 7
  13. 2022On Efficient Real-Time Semantic Segmentation: A Surveycited by 7
  14. 2022Deep Learning based Computer Vision Methods for Complex Traffic Environments Perception: A Reviewcited by 7
  15. 2023Generalizable Neural Fields as Partially Observed Neural Processescited by 7
  16. 2021Leveraging Human Selective Attention for Medical Image Analysis with Limited Training Datacited by 5
  17. 2021Hypernet-Ensemble Learning of Segmentation Probability for Medical Image Segmentation with Ambiguous Labelscited by 4
  18. 2022Lightweight and Progressively-Scalable Networks for Semantic Segmentationcited by 4
  19. 2025Learning to Learn Weight Generation via Local Consistency Diffusioncited by 4
  20. 2025Golden Cudgel Network for Real-Time Semantic Segmentationcited by 4
  21. 2026HyperAlign: Hypernetwork for Efficient Test-Time Alignment of Diffusion Modelscited by 4
  22. 2023INFAMOUS-NeRF: ImproviNg FAce MOdeling Using Semantically-Aligned Hypernetworks with Neural Radiance Fieldscited by 3
  23. 2023LAPP: Layer Adaptive Progressive Pruning for Compressing CNNs from Scratchcited by 2
  24. 2024Reparameterizable Dual-Resolution Network for Real-time Semantic Segmentationcited by 2
  25. 2024PNeRV: A Polynomial Neural Representation for Videoscited by 2
  26. 2024DFREC: DeepFake Identity Recovery Based on Identity-aware Masked Autoencodercited by 2
  27. 2021Object Pursuit: Building a Space of Objects via Discriminative Weight Generationcited by 1
  28. 2022Hyper-Convolutions via Implicit Kernels for Medical Imagingcited by 1
  29. 2022TriangleNet: Edge Prior Augmented Network for Semantic Segmentation through Cross-Task Consistencycited by 1
  30. 2023HyperPose: Hypernetwork-Infused Camera Pose Localization and an Extended Cambridge Landmarks Datasetcited by 1
  31. 2023HyperEditor: Achieving Both Authenticity and Cross-Domain Capability in Image Editing via Hypernetworkscited by 1
  32. 2024Uncertainty Driven Active Learning for Image Segmentation in Underwater Inspectioncited by 1
  33. 2024Hyper-Transformer for Amodal Completioncited by 1
  34. 2025Hypernetworks for Model-Heterogeneous Personalized Federated Learningcited by 1
  35. 2025TSLA: A Task-Specific Learning Adaptation for Semantic Segmentation on Autonomous Vehicles Platformcited by 1
  36. 2026TraceVision: Trajectory-Aware Vision-Language Model for Human-Like Spatial Understandingcited by 1
  37. 2021DRBANET: A Lightweight Dual-Resolution Network for Semantic Segmentation with Boundary Auxiliarycited by 0
  38. 2022Borrowing from yourself: Faster future video segmentation with partial channel updatecited by 0

50 most cited of 66 All 66 (JSON)