Papers › ReSeg: A Recurrent Neural Network-based Model for Semantic Segmentation

ReSeg: A Recurrent Neural Network-based Model for Semantic Segmentation

22 Nov 2015arXiv:1511.07053archive 2025-07-28

Francesco Visin, Marco Ciccone, Adriana Romero, Kyle Kastner, Kyunghyun Cho, Yoshua Bengio, Matteo Matteucci, Aaron Courville

We propose a structured prediction architecture, which exploits the local generic features extracted by Convolutional Neural Networks and the capacity of Recurrent Neural Networks (RNN) to retrieve distant dependencies. The proposed architecture, called ReSeg, is based on the recently introduced ReNet model for image classification. We modify and extend it to perform the more challenging task of semantic segmentation. Each ReNet layer is composed of four RNN that sweep the image horizontally and vertically in both directions, encoding patches or activations, and providing relevant global information. Moreover, ReNet layers are stacked on top of pre-trained convolutional layers, benefiting from generic local features. Upsampling layers follow ReNet layers to recover the original image resolution in the final predictions. The proposed ReSeg architecture is efficient, flexible and suitable for a variety of semantic segmentation tasks. We evaluate ReSeg on several widely-used semantic segmentation datasets: Weizmann Horse, Oxford Flower, and CamVid; achieving state-of-the-art performance. Results show that ReSeg can act as a suitable architecture for semantic segmentation tasks, and may have further applications in other structured prediction problems. The source code and model hyperparameters are available on https://github.com/fvisin/reseg.

PaperPDFCode

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

Code

fvisin/reseg officialmentioned in papermentioned on GitHubGPL-3.0 report
SConsul/ReSeg mentioned on GitHubpytorch 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

SegmentationSemantic SegmentationStructured Predictionimage-classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semantic Segmentation CamVid ReSeg Global Accuracy 88.7% #20 of 21 Archive leaderboard report
Semantic Segmentation CamVid ReSeg Mean IoU 58.8% #20 of 21 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