# SegBlocks: Block-Based Dynamic Resolution Networks for Real-Time Segmentation

arXiv: https://arxiv.org/abs/2011.12025 · HTML: https://mlsanity.com/paper/2011.12025/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Nov 2020.

## Built on by (most cited first, 9 of 9)

- [ZeroFL: Efficient On-Device Training for Federated Learning with Local Sparsity](https://mlsanity.com/paper/2208.02507/) (2022)
- [TransKD: Transformer Knowledge Distillation for Efficient Semantic Segmentation](https://mlsanity.com/paper/2202.13393/) (2022)
- [Learning to Zoom and Unzoom](https://mlsanity.com/paper/2303.15390/) (2023)
- [Edge Video Analytics: A Survey on Applications, Systems and Enabling Techniques](https://mlsanity.com/paper/2211.15751/) (2022)
- [Adaptive Computation Modules: Granular Conditional Computation For Efficient Inference](https://mlsanity.com/paper/2312.10193/) (2023)
- [A Survey on Dynamic Neural Networks: from Computer Vision to Multi-modal Sensor Fusion](https://mlsanity.com/paper/2501.07451/) (2025)
- [Sparse Refinement for Efficient High-Resolution Semantic Segmentation](https://mlsanity.com/paper/2407.19014/) (2024)
- [Med-DANet V2: A Flexible Dynamic Architecture for Efficient Medical Volumetric Segmentation](https://mlsanity.com/paper/2310.18656/) (2023)
- [Efficient On-Board Processing of Oblique UAV Video for Rapid Flood Extent Mapping](https://mlsanity.com/paper/2601.11290/) (2026)

## Abstract (arXiv)

SegBlocks reduces the computational cost of existing neural networks, by dynamically adjusting the processing resolution of image regions based on their complexity. Our method splits an image into blocks and downsamples blocks of low complexity, reducing the number of operations and memory consumption. A lightweight policy network, selecting the complex regions, is trained using reinforcement learning. In addition, we introduce several modules implemented in CUDA to process images in blocks. Most important, our novel BlockPad module prevents the feature discontinuities at block borders of which existing methods suffer, while keeping memory consumption under control. Our experiments on Cityscapes, Camvid and Mapillary Vistas datasets for semantic segmentation show that dynamically processing images offers a better accuracy versus complexity trade-off compared to static baselines of similar complexity. For instance, our method reduces the number of floating-point operations of SwiftNet-RN18 by 60% and increases the inference speed by 50%, with only 0.3% decrease in mIoU accuracy on Cityscapes.