Papers › Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
Liang-Chieh Chen, Yukun Zhu, George Papandreou, Florian Schroff, Hartwig Adam
Spatial pyramid pooling module or encode-decoder structure are used in deep neural networks for semantic segmentation task. The former networks are able to encode multi-scale contextual information by probing the incoming features with filters or pooling operations at multiple rates and multiple effective fields-of-view, while the latter networks can capture sharper object boundaries by gradually recovering the spatial information. In this work, we propose to combine the advantages from both methods. Specifically, our proposed model, DeepLabv3+, extends DeepLabv3 by adding a simple yet effective decoder module to refine the segmentation results especially along object boundaries. We further explore the Xception model and apply the depthwise separable convolution to both Atrous Spatial Pyramid Pooling and decoder modules, resulting in a faster and stronger encoder-decoder network. We demonstrate the effectiveness of the proposed model on PASCAL VOC 2012 and Cityscapes datasets, achieving the test set performance of 89.0\% and 82.1\% without any post-processing. Our paper is accompanied with a publicly available reference implementation of the proposed models in Tensorflow at \url{https://github.com/tensorflow/models/tree/master/research/deeplab}.
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="1802.02611")
Code
Syntology Ran 43 of 72 code samples harvested from 17 repositories linked to this paper; 29 have no recorded run. Of those that ran: 2 ran · honoured contract; 8 ran · our draft was wrong; 5 ran · fixture could not drive it; 28 ran with no contract checked.
By repository: community (archive-listed): 72 samples from 17 repositories, 43 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.
78 repositories listed; official and paper-mentioned ones first.
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
72 samples harvested; 43 ran; 2 honoured the contract we drafted; 29 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.
Licence: 40 of the 72 samples are 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 17 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.
9a5496117125b307 · report
0f94e0514fb25366 · report
eaa0ac6ed86c450b · report
0633b0a6570b756e · report
cb6b44750325dc1e · report
a4f0a021c8fd4295 · report
03d31a466787b052 · report
a2f1b4aadd626233 · report
4a9a634b49dda7a4 · report
1e87570d52719052 · report
682f6d56a1c45f69 · report
df2ed20fe3290ced · report
43562ef9d87c54e7 · report
692e7f2e56fbd23e · report
3326d9cd4c357d28 · report
303dec08f3ebd517 · report
fc4e40cedd008787 · report
c10a37b7673d30e0 · report
d99dfd9a3f26d56b · report
42610493d6f82abe · report
8e495c6bb6122711 · report
5b3058ed46740fef · report
b293f1d81655c5e6 · report
e6cccdb5cc9404d7 · report
414adf534687df82 · report
ebedb218ce19918d · report
3274a200ef8fa29a · report
d5caae9d47ff2394 · report
a5651a6111de513f · report
9c74246baf89e0d2 · report
3ebb19f692e505f6 · report
1096e5ba9c24632c · report
1eac80b6e2cee7b2 · report
5776a2cbccc2bd40 · report
76185251accca7d2 · report
398cd429c73d683e · report
68330450cf875f58 · report
3f8ff8379eaf97df · report
6d5672a93099e8b5 · report
b387bf7cf1bc8ced · report
e7a210769e38826c · report
90c8dc399d2c6b51 · report
4976637b084e5281 · report
26047a3c90df0a36 · report
a9f549942de7d30b · report
edf673cbd75a7027 · report
4ac4bc7c6f72419c · report
6e6115c04c3f121d · report
9ac514a69bb5bb62 · report
09a240d3865fee6c · report
609cfe0df52cf002 · report
9755f047bfec69ce · report
63a49a3c1dd4d263 · report
dfd28692d87464d1 · report
59849f10377fad5f · report
13a67fcfc1e4c1d7 · report
fabf7df16100c5bc · report
96875ada06fa67da · report
82f03ca51ba7dbc4 · report
350abbaf676488bc · report
f52f02f15632fc39 · report
c4e00178c12b2cf8 · report
d4f09015805919e2 · report
8be86acb174d9241 · report
66b9a9d2e9d2ca8d · report
83604720aed3cccf · report
c5fb690670bbe8da · report
7a0b3803f28d47fa · report
d9691f627c30dde9 · report
602a54842f95f3f0 · report
3222e50cba4be935 · report
b1992cb92fab6136 · report
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Lesion Segmentation | Anatomical Tracings of Lesions After Stroke (ATLAS) | DeepLab v3+ | Dice | 0.4609 | #3 of 5 | Archive leaderboard | report |
| Lesion Segmentation | Anatomical Tracings of Lesions After Stroke (ATLAS) | DeepLab v3+ | IoU | 0.3458 | #3 of 5 | Archive leaderboard | report |
| Lesion Segmentation | Anatomical Tracings of Lesions After Stroke (ATLAS) | DeepLab v3+ | Precision | 0.5831 | #3 of 5 | Archive leaderboard | report |
| Semantic Segmentation | AI-TOD | DeepLabV3+(ResNet-50) | Dice | 43.52 | #2 of 2 | Archive leaderboard | report |
| Semantic Segmentation | BDD100K val | Deeplabv3+ | mIoU | 63.6 | #4 of 24 | Archive leaderboard | report |
| Semantic Segmentation | BJRoad | DeepLabv3+ | IoU | 50.81 | #11 of 11 | Archive leaderboard | report |
| Semantic Segmentation | Cityscapes val | DeepLabv3+ (Dilated-Xception-71) | mIoU | 79.6 | #57 of 99 | Archive leaderboard | report |
| Semantic Segmentation | DADA-seg | DeepLabV3+ (ACDC) | mIoU | 26.8 | #12 of 28 | Archive leaderboard | report |
| Semantic Segmentation | DensePASS | DeepLabV3+ (ResNet-101) | mIoU | 32.5% | #21 of 36 | Archive leaderboard | report |
| Semantic Segmentation | EventScape | DeepLabV3+ | mIoU | 53.65 | #6 of 12 | Archive leaderboard | report |
| Semantic Segmentation | Fine-Grained Grass Segmentation Dataset | DeepLabv3+ | mIoU | 47.95 | #7 of 10 | Archive leaderboard | report |
| Semantic Segmentation | MCubeS | DeepLabV3+ (RGB-A-D-N) | mIoU | 38.13% | #20 of 22 | Archive leaderboard | report |
| Semantic Segmentation | PASCAL VOC 2012 test | DeepLabv3+ (Xception-65-JFT) | Mean IoU | 89.0% | #1 of 51 | Archive leaderboard | report |
| Semantic Segmentation | PASCAL VOC 2012 test | DeepLabv3+ (Xception-JFT) | Mean IoU | 89.0% | #2 of 51 | Archive leaderboard | report |
| Semantic Segmentation | PASCAL VOC 2012 val | DeepLabV3+ (ResNet-101) | mIoU (Syn) | 75.39 | #29 of 29 | Archive leaderboard | report |
| Semantic Segmentation | Potsdam | DeepLabV3+ | mIoU | 83.67 | #3 of 3 | Archive leaderboard | report |
| Semantic Segmentation | SkyScapes-Dense | DeepLabv3+ | Mean IoU | 38.20 | #2 of 7 | Archive leaderboard | report |
| Semantic Segmentation | SynPASS | DeepLabv3+ | mIoU | 29.66% | #5 of 6 | Archive leaderboard | report |
| Semantic Segmentation | Trans10K | DeepLabV3+ | GFLOPs | 37.98 | #5 of 15 | Archive leaderboard | report |
| Semantic Segmentation | Trans10K | DeepLabV3+ | mIoU | 68.87% | #5 of 15 | Archive leaderboard | report |
| Semantic Segmentation | US3D | DeepLabV3+ | mIoU | 74.42 | #1 of 3 | Archive leaderboard | report |
| Semantic Segmentation | UrbanLF | DeepLabV3+ (ResNet-101) | mIoU (Real) | 76.27 | #14 of 14 | Archive leaderboard | report |
| Semantic Segmentation | Vaihingen | DeepLabV3+ | mIoU | 72.90 | #13 of 13 | 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
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