Papers › RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation

RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation

20 Nov 2016CVPR 2017 7arXiv:1611.06612archive 2025-07-28

Guosheng Lin, Anton Milan, Chunhua Shen, Ian Reid

Recently, very deep convolutional neural networks (CNNs) have shown outstanding performance in object recognition and have also been the first choice for dense classification problems such as semantic segmentation. However, repeated subsampling operations like pooling or convolution striding in deep CNNs lead to a significant decrease in the initial image resolution. Here, we present RefineNet, a generic multi-path refinement network that explicitly exploits all the information available along the down-sampling process to enable high-resolution prediction using long-range residual connections. In this way, the deeper layers that capture high-level semantic features can be directly refined using fine-grained features from earlier convolutions. The individual components of RefineNet employ residual connections following the identity mapping mindset, which allows for effective end-to-end training. Further, we introduce chained residual pooling, which captures rich background context in an efficient manner. We carry out comprehensive experiments and set new state-of-the-art results on seven public datasets. In particular, we achieve an intersection-over-union score of 83.4 on the challenging PASCAL VOC 2012 dataset, which is the best reported result to date.

PaperPDFConference PDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1611.06612")

Code

Syntology Ran 1 of 7 code samples harvested from 2 repositories linked to this paper; 6 have no recorded run. Of those that ran: 1 ran · honoured contract.

By repository: community (archive-listed): 7 samples from 2 repositories, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

13 repositories listed; official and paper-mentioned ones first.

guosheng/refinenet officialmentioned in papermentioned on GitHubpytorchNOASSERTION report
alililia/ascend_RefineNet mentioned on GitHubmindsporeApache-2.0 report
hiyaroy12/multitask_learning mentioned on GitHubtf report
hugozanini/realtime-semantic-segmentation mentioned on GitHubtfApache-2.0 report
kingcong/RefineNet mentioned on GitHubmindsporenot reachable when probed 2026-09-18 — repositories for recent papers often appear after camera-ready report
kingcong/gpu_RefineNet mentioned on GitHubmindsporenot reachable when probed 2026-09-18 — repositories for recent papers often appear after camera-ready report
yangyucheng000/RefineNet mentioned on GitHubmindspore 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

7 samples harvested; 1 ran; 1 honoured the contract we drafted; 6 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · honoured contract
6unverified

Licence: 1 of the 7 samples is pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; each sample names its own and says which. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

process_seg hiyaroy12/multitask_learning/refinenet-image-segmentation/RefineNet/test_captioning.py community (archive-listed) ran · honoured contract fingerprinted no licence file found · pointer only · 26490223efed770e · report
cal_hist alililia/ascend_RefineNet/postprocess.py community (archive-listed) unverified Apache-2.0 (permissive) · 5e57042613d98374 · report
get_img_size alililia/ascend_RefineNet/postprocess.py community (archive-listed) unverified Apache-2.0 (permissive) · b13acc0922dade5c · report
get_lr alililia/ascend_RefineNet/src/learning_rates.py community (archive-listed) unverified Apache-2.0 (permissive) · ca5006a85f504b0d · report
get_resized_size alililia/ascend_RefineNet/postprocess.py community (archive-listed) unverified Apache-2.0 (permissive) · 874e384c8b2bd6bf · report
linear_warmup_lr alililia/ascend_RefineNet/src/learning_rates.py community (archive-listed) unverified Apache-2.0 (permissive) · 9da7260d717664f9 · report
warmup_cosine_annealing_lr alililia/ascend_RefineNet/src/learning_rates.py community (archive-listed) unverified Apache-2.0 (permissive) · d4a0bdf1190319c4 · report

Tasks

3D Absolute Human Pose EstimationSemantic SegmentationVocal Bursts Intensity Prediction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semantic Segmentation ADE20K RefineNet Validation mIoU 40.7 #217 of 235 Archive leaderboard report
Semantic Segmentation ADE20K val RefineNet (ResNet-152) mIoU 40.70 #94 of 95 Archive leaderboard report
Semantic Segmentation ADE20K val RefineNet (ResNet-101) mIoU 40.20 #95 of 95 Archive leaderboard report
Semantic Segmentation COCO-Stuff test RefineNet (ResNet-101) mIoU 33.6% #19 of 21 Archive leaderboard report
Semantic Segmentation Cityscapes test RefineNet (ResNet-101) Mean IoU (class) 73.6% #67 of 105 Archive leaderboard report
Semantic Segmentation NYU Depth v2 RefineNet (ResNet-101) Mean IoU 46.5% #89 of 121 Archive leaderboard report
Semantic Segmentation PASCAL Context RefineNet mIoU 47.3 #54 of 66 Archive leaderboard report
Semantic Segmentation PASCAL VOC 2012 test Multipath-RefineNet Mean IoU 84.2% #14 of 51 Archive leaderboard report
Semantic Segmentation Trans10K RefineNet GFLOPs 44.56 #13 of 15 Archive leaderboard report
Semantic Segmentation Trans10K RefineNet mIoU 58.18% #13 of 15 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.

Methods

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionGlobal Average PoolingKaiming InitializationMax PoolingReLUResidual BlockResidual Connection

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