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

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

24 Nov 2020arXiv:2011.12025archive 2025-07-28

Thomas Verelst, Tinne Tuytelaars

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.

PaperPDFCode

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

Code

thomasverelst/segblocks-segmentation-pytorch officialmentioned in paperpytorch 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

Real-Time Semantic SegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Real-Time Semantic Segmentation Cityscapes test SegBlocks-RN18 (t=0.4) Frame (fps) 48.6 (1080Ti) #21 of 39 Archive leaderboard report
Real-Time Semantic Segmentation Cityscapes test SegBlocks-RN18 (t=0.4) mIoU 73.8% #21 of 39 Archive leaderboard report
Semantic Segmentation Mapillary val SegBlocks-RN50 (t=0.4) mIoU 39.7 #7 of 8 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.

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