Papers › MultiNet: Real-time Joint Semantic Reasoning for Autonomous Driving

MultiNet: Real-time Joint Semantic Reasoning for Autonomous Driving

22 Dec 2016arXiv:1612.07695archive 2025-07-28

Marvin Teichmann, Michael Weber, Marius Zoellner, Roberto Cipolla, Raquel Urtasun

While most approaches to semantic reasoning have focused on improving performance, in this paper we argue that computational times are very important in order to enable real time applications such as autonomous driving. Towards this goal, we present an approach to joint classification, detection and semantic segmentation via a unified architecture where the encoder is shared amongst the three tasks. Our approach is very simple, can be trained end-to-end and performs extremely well in the challenging KITTI dataset, outperforming the state-of-the-art in the road segmentation task. Our approach is also very efficient, taking less than 100 ms to perform all tasks.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 42 code samples harvested from 6 repositories linked to this paper: 18 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 2 honoured, 0 violated, 12 with no contract checked; 4 where Syntology's instrument failed) · 24 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 3 samples from 1 repository, 1 ran (1 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 39 samples from 5 repositories, 17 ran (13 with no instrument failure; 4 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 18 samples that ran has no recorded date.

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

MarvinTeichmann/MultiNet officialmentioned on GitHubtfMITSyntology: 3 samples, 1 ran (0 instrument-failed) · 2 unverified report
MarvinTeichmann/KittiBox mentioned on GitHubtfMITSyntology: 10 samples, 4 ran (2 instrument-failed) · 6 unverified report
MarvinTeichmann/KittiSeg mentioned on GitHubtfMITSyntology: 18 samples, 6 ran (0 instrument-failed) · 12 unverified report
MrHongweiDu/Road_detection mentioned on GitHubtfMITSyntology: not harvested report
XRONHH/text_1 mentioned on GitHubtfMITSyntology: not harvested report
ahmadelsallab/MultiCheXNet mentioned on GitHubtfGPL-3.0Syntology: not harvested report
hustvl/YOLOP mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to YOLOP: You Only Look Once for Panoptic Driving Perception (arXiv:2108.11250; that paper's own run record: 13 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
hustvl/yolop mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to YOLOP: You Only Look Once for Panoptic Driving Perception (arXiv:2108.11250; that paper's own run record: 13 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
iac-team/semseg mentioned on GitHubtfMITSyntology: not harvested report
jiayuanwang-jw/yolov8-multi-task mentioned on GitHubpytorchAGPL-3.0Syntology: not harvested report
kinglintianxia/KittiSeg mentioned on GitHubtfMITSyntology: not harvested report
kinglintianxia/MultiNet mentioned on GitHubtfMITSyntology: 2 samples, 0 ran · 2 unverified report
linxi159/KittiSeg mentioned on GitHubtfMITSyntology: not harvested report
lrxiao/free-space mentioned on GitHubtfMITSyntology: 6 samples, 6 ran (2 instrument-failed) · 0 unverified report
ziyuan400/video_segmentation mentioned on GitHubtfMITSyntology: 3 samples, 1 ran (0 instrument-failed) · 2 unverified 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

42 samples harvested: 18 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 2 honoured, 0 violated, 12 with no contract checked; 4 where Syntology's instrument failed) · 24 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · honoured contract
2ran · our draft was wrong
2ran; the contract check could not run
12ran
24unverified

Licence: 1 of the 42 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 6 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

MarvinTeichmann/MultiNet official repository 3 samples, 1 ran (0 instrument-failed) · 2 unverified
download in 53 papers download_data.py ran MIT (permissive) · 2f54556acaaaa4eb · report fixture: signature url:str/0/str, dest_directory:str/0/str · returned str · level recorded 2026-09-25
eval_runtime predict_joint.py unverified MIT (permissive) · 73a138ca8514b82f · report
road_draw predict_joint.py unverified MIT (permissive) · c4752a51f8ca2379 · report
MarvinTeichmann/KittiBox community (archive-listed) 10 samples, 4 ran (2 instrument-failed) · 6 unverified
checkpoint_fn encoder/resnet.py ran fingerprinted MIT (permissive) · 0fb1e9b87874ccf9 · report fixture: signature layers:int/0/int · returned str · level recorded 2026-09-26
get_learning_rate in 19 papers optimizer/generic_optimizer.py ran MIT (permissive) · c1079c98e7fd20cf · report fixture: signature hypes:dict/0/?, step:int/0/int · returned float · level recorded 2026-09-26
make_img_dir evals/kitti_eval.py ran · our draft was wrong MIT (permissive) · 11f62180c1d254d1 · report fixture: signature hypes:dict/0/? · returned str · level recorded 2026-09-22
make_val_dir evals/kitti_eval.py ran · our draft was wrong MIT (permissive) · 8f66730ce77f9c73 · report fixture: signature hypes:dict/0/?, validation:bool/0/bool · returned str · level recorded 2026-09-22
annotation_jitter submodules/utils/data_utils.py unverified MIT (permissive) · 3120b13eb44ef9b4 · report
create_queues inputs/kitti_input.py unverified MIT (permissive) · a49c2b6b1b3d9630 · report
download in 53 papers download_data.py unverified MIT (permissive) · e699268eb4620c35 · report
init in 55 papers submodules/utils/googlenet_load.py unverified MIT (permissive) · 0380022ecb697fdf · report
model in 13 papers submodules/utils/googlenet_load.py unverified MIT (permissive) · 665442a0da999129 · report
training in 9 papers optimizer/generic_optimizer.py unverified MIT (permissive) · b0b9089925308ff8 · report
MarvinTeichmann/KittiSeg community (archive-listed) 18 samples, 6 ran (0 instrument-failed) · 12 unverified
decoder in 19 papers decoder/kitti_multiloss.py ran MIT (permissive) · f2a6283192e3a5f8 · report fixture: signature hypes:dict/0/?, logits:dict/0/?, train:bool/0/bool · returned dict · level recorded 2026-09-26
overlayImageWithConfidence submodules/evaluation/kitti_devkit/helper.py ran MIT (permissive) · f34c9ee2e46909bb · report fixture: signature in_image:ndarray/3/int, conf:ndarray/2/float, vis_channel:int/0/int, threshold:float/0/float · returned ndarray · level recorded 2026-09-26
overlayImageWithConfidence submodules/evaluation/kitti_devkit/seg_utils.py ran MIT (permissive) · 6e12dc2a14ed2373 · report fixture: signature in_image:ndarray/3/int, conf:ndarray/2/float, vis_channel:int/0/int, threshold:float/0/float · returned ndarray · level recorded 2026-09-26
random_crop in 59 papers inputs/kitti_seg_input.py ran MIT (permissive) · e8eae01d93336c85 · report fixture: signature image:ndarray/3/float, gt_image:ndarray/3/float, height:int/0/int, width:int/0/int · returned tuple · level recorded 2026-09-26
random_crop_soft inputs/kitti_seg_input.py ran MIT (permissive) · a1e4b024187ff727 · report fixture: signature image:ndarray/3/int, gt_image:ndarray/3/int, max_crop:int/0/int · returned tuple · level recorded 2026-09-26
upsample_initilizer decoder/fcn.py ran MIT (permissive) · 7ddd48e200f540e1 · report fixture: signature dtype:DType/0/? · returned function · level recorded 2026-09-26
decoder in 19 papers decoder/fcn.py unverified MIT (permissive) · 6fbefb7857e241c5 · report
evalExp submodules/evaluation/kitti_devkit/helper.py unverified MIT (permissive) · dcee0d4be9444cc8 · report
evalExp submodules/evaluation/kitti_devkit/seg_utils.py unverified MIT (permissive) · dbe61b335391da9f · report
evaluation in 57 papers decoder/kitti_multiloss.py unverified MIT (permissive) · 9897841211ca8e31 · report
getGroundTruth submodules/evaluation/kitti_devkit/helper.py unverified MIT (permissive) · 9371cb2fed46f3fa · report
jitter_input inputs/kitti_seg_input.py unverified MIT (permissive) · 953123fb9050c56c · report
make_overlay submodules/evaluation/kitti_devkit/seg_utils.py unverified MIT (permissive) · 685529fb4fab3fb4 · report
overlay_segmentation submodules/evaluation/overlay_utils.py unverified MIT (permissive) · b03f0d16f3cb39fe · report
replace_colors submodules/evaluation/overlay_utils.py unverified MIT (permissive) · 8db8a9f07f5b6969 · report
resize_label_image evals/kitti_eval.py unverified MIT (permissive) · 6843b5f4caa59fd8 · report
training in 9 papers optimizer/generic_optimizer.py unverified MIT (permissive) · f612b914061fe0f8 · report
kinglintianxia/MultiNet community (archive-listed) 2 samples, 0 ran · 2 unverified
build_training_graph train_mult_gpus.py unverified MIT (permissive) · 9ef4cce374ca90b3 · report
eval_runtime demo_seg&obj.py unverified MIT (permissive) · e7f1800d0e5ffc40 · report
lrxiao/free-space community (archive-listed) 6 samples, 6 ran (2 instrument-failed) · 0 unverified
in_hull in 13 papers prepare_data.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic MIT (permissive) here; the stored copy is pointer only · aab935d4b7b55c2c · report fixture: signature p:ndarray/2/float, hull:Delaunay/0/? · returned ndarray · level recorded, date not recorded
extract_pc_in_box2d prepare_data.py ran MIT (permissive) · c1c81b9614b5c990 · report fixture: signature pc:ndarray/2/float, box2d:ndarray/1/float · returned tuple · level recorded 2026-09-26
extract_pc_in_box3d in 7 papers prepare_data.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · 50bdbf961c28b4b2 · report fixture: signature pc:ndarray/2/float, box3d:ndarray/2/float · returned tuple · level recorded 2026-09-24
rotx in 15 papers kitti_util.py ran · honoured contract fingerprinted MIT (permissive) · 8843d80ab666c4e9 · report fixture: signature t:float/0/float · returned ndarray · level recorded 2026-09-24
roty in 19 papers kitti_util.py ran · honoured contract fingerprinted MIT (permissive) · ae86074e10e1dfd7 · report fixture: signature t:float/0/float · returned ndarray · level recorded 2026-09-24
rotz in 12 papers kitti_util.py ran fingerprinted MIT (permissive) · 082920adf6e29c94 · report fixture: signature t:float/0/float · returned ndarray · level recorded 2026-09-25
ziyuan400/video_segmentation community (archive-listed) 3 samples, 1 ran (0 instrument-failed) · 2 unverified
jitter_input inputs/kitti_seg_input.py ran MIT (permissive) · a368e5f40eda4322 · report fixture: signature hypes:dict/0/?, image:ndarray/3/int, gt_image:ndarray/3/int · returned tuple · level recorded 2026-09-26
evaluation in 57 papers decoder/kitti_multiloss.py unverified MIT (permissive) · 64d216d65449fe96 · report

Tasks

Autonomous DrivingGeneral ClassificationRoad SegmentationSegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

1D CNN

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