</> Code with Papers by Syntology

Papers › Light-Weight RefineNet for Real-Time Semantic Segmentation

Light-Weight RefineNet for Real-Time Semantic Segmentation

8 Oct 2018arXiv:1810.03272archive 2025-07-28

Vladimir Nekrasov, Chunhua Shen, Ian Reid

We consider an important task of effective and efficient semantic image segmentation. In particular, we adapt a powerful semantic segmentation architecture, called RefineNet, into the more compact one, suitable even for tasks requiring real-time performance on high-resolution inputs. To this end, we identify computationally expensive blocks in the original setup, and propose two modifications aimed to decrease the number of parameters and floating point operations. By doing that, we achieve more than twofold model reduction, while keeping the performance levels almost intact. Our fastest model undergoes a significant speed-up boost from 20 FPS to 55 FPS on a generic GPU card on 512x512 inputs with solid 81.1% mean iou performance on the test set of PASCAL VOC, while our slowest model with 32 FPS (from original 17 FPS) shows 82.7% mean iou on the same dataset. Alternatively, we showcase that our approach is easily mixable with light-weight classification networks: we attain 79.2% mean iou on PASCAL VOC using a model that contains only 3.3M parameters and performs only 9.3B floating point operations.

PaperPDFCode

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

Code

AleksBanbur/EE8204---Real-Time-Multi-Task-Learning mentioned on GitHubpytorch report
DrSleep/light-weight-refinenet pytorch 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

Image SegmentationReal-Time Semantic SegmentationSegmentationSemantic Segmentation

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Real-Time Semantic Segmentation NYU Depth v2 Light-Weight-RefineNet-152 Speed(ms/f) 36 #2 of 10 Archive leaderboard report
Real-Time Semantic Segmentation NYU Depth v2 Light-Weight-RefineNet-152 mIoU 44.4 #2 of 10 Archive leaderboard report
Real-Time Semantic Segmentation NYU Depth v2 Light-Weight-RefineNet-101 Speed(ms/f) 27 #3 of 10 Archive leaderboard report
Real-Time Semantic Segmentation NYU Depth v2 Light-Weight-RefineNet-101 mIoU 43.6 #3 of 10 Archive leaderboard report
Real-Time Semantic Segmentation NYU Depth v2 Light-Weight-RefineNet-50 Speed(ms/f) 20 #8 of 10 Archive leaderboard report
Real-Time Semantic Segmentation NYU Depth v2 Light-Weight-RefineNet-50 mIoU 41.7 #8 of 10 Archive leaderboard report
Semantic Segmentation NYU Depth v2 Light-Weight-RefineNet-152 Mean IoU 44.4% #97 of 121 Archive leaderboard report
Semantic Segmentation NYU Depth v2 Light-Weight-RefineNet-101 Mean IoU 43.6% #99 of 121 Archive leaderboard report
Semantic Segmentation NYU Depth v2 Light-Weight-RefineNet-50 Mean IoU 41.7% #105 of 121 Archive leaderboard report
Semantic Segmentation PASCAL VOC 2012 test Light-Weight-RefineNet-152 Mean IoU 82.7% #24 of 51 Archive leaderboard report
Semantic Segmentation PASCAL VOC 2012 test Light-Weight-RefineNet-101 Mean IoU 82.0% #27 of 51 Archive leaderboard report
Semantic Segmentation PASCAL VOC 2012 test Light-Weight-RefineNet-50 Mean IoU 81.1% #28 of 51 Archive leaderboard report
Semantic Segmentation PASCAL VOC 2012 test Light-Weight-RefineNet-MobileNet-v2 Mean IoU 79.2% #33 of 51 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