Papers › MTP: Advancing Remote Sensing Foundation Model via Multi-Task Pretraining

MTP: Advancing Remote Sensing Foundation Model via Multi-Task Pretraining

20 Mar 2024arXiv:2403.13430archive 2025-07-28

Di Wang, Jing Zhang, Minqiang Xu, Lin Liu, Dongsheng Wang, Erzhong Gao, Chengxi Han, HaoNan Guo, Bo Du, DaCheng Tao, Liangpei Zhang

Foundation models have reshaped the landscape of Remote Sensing (RS) by enhancing various image interpretation tasks. Pretraining is an active research topic, encompassing supervised and self-supervised learning methods to initialize model weights effectively. However, transferring the pretrained models to downstream tasks may encounter task discrepancy due to their formulation of pretraining as image classification or object discrimination tasks. In this study, we explore the Multi-Task Pretraining (MTP) paradigm for RS foundation models to address this issue. Using a shared encoder and task-specific decoder architecture, we conduct multi-task supervised pretraining on the SAMRS dataset, encompassing semantic segmentation, instance segmentation, and rotated object detection. MTP supports both convolutional neural networks and vision transformer foundation models with over 300 million parameters. The pretrained models are finetuned on various RS downstream tasks, such as scene classification, horizontal and rotated object detection, semantic segmentation, and change detection. Extensive experiments across 14 datasets demonstrate the superiority of our models over existing ones of similar size and their competitive performance compared to larger state-of-the-art models, thus validating the effectiveness of MTP.

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 5 code samples harvested from 2 repositories linked to this paper: 5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 1 sample from 1 repository, 1 ran (1 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 4 samples from 1 repository, 4 ran (1 with no instrument failure; 3 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.

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 5 samples that ran has no recorded date.

vitae-transformer/mtp officialmentioned in papermentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
cuzyoung/crossearth mentioned on GitHubpytorchMITSyntology: 4 samples, 4 ran (3 instrument-failed) · 0 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.

Code Syntology ran Syntology

5 samples harvested: 5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · violated contract
2ran · our draft was wrong
1ran; the contract check could not run
1ran

Licence: 0 of the 5 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 2 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.

vitae-transformer/mtp official repository 1 sample, 1 ran (0 instrument-failed) · 0 unverified
main_process in 45 papers Multi-Task_Pretrain/main_pretrain.py ran · violated contract MIT (permissive) · e26853276bb3dd32 · report fixture: signature args:Args/0/? · returned bool · level recorded 2026-09-22
cuzyoung/crossearth community (archive-listed) 4 samples, 4 ran (3 instrument-failed) · 0 unverified
calc_rel_pos_spatial in 5 papers CrossEarth/models/backbones/vit_rvsa_mtp.py ran MIT (permissive) · 89b02b1673f5f567 · report fixture: signature attn:Tensor/4/float, q:Tensor/4/float, q_shape:tuple/1/int, k_shape:tuple/1/int, rel_pos_h:Tensor/2/float, rel_pos_w:Tensor/2/float · returned Tensor · level recorded 2026-09-24
named_apply in 32 papers CrossEarth/models/backbones/dino_v2.py ran · our draft was wrong MIT (permissive) · e7fcb6d9ac9deaf4 · report fixture: signature fn:callable/0/?, module:callable/0/?, name:str/0/str, depth_first:bool/0/bool, include_root:bool/0/bool · returned SimpleModel · level recorded, date not recorded
window_partition in 377 papers
census: 13 implementations from 17 papers, 5 distinct outputs across 3 buckets, one shared input per bucket
CrossEarth/models/backbones/vit_rvsa_mtp.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) · f9fd6241d935f07b · report fixture: signature x:Tensor/4/float, window_size:int/0/int · returned Tensor · level recorded 2026-09-22
window_reverse in 296 papers CrossEarth/models/backbones/vit_rvsa_mtp.py ran · our draft was wrong MIT (permissive) · fb32094c6dbece71 · report fixture: signature windows:Tensor/4/float, window_size:int/0/int, H:int/0/int, W:int/0/int · returned Tensor · level recorded 2026-09-22

Tasks

Aerial Scene ClassificationBuilding change detection for remote sensing imagesChange DetectionChange detection for remote sensing imagesDecoderImage ClassificationInstance SegmentationObjectObject DetectionObject Detection In Aerial ImagesOriented Object DetectionScene ClassificationSegmentationSelf-Supervised LearningSemantic Segmentationimage-classificationobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Building change detection for remote sensing images LEVIR-CD MAE+MTP(ViT-L+RVSA) F1 92.67 #1 of 37 Archive leaderboard report
Building change detection for remote sensing images LEVIR-CD MAE+MTP(ViT-L+RVSA) Params(M) 305 #1 of 37 Archive leaderboard report
Building change detection for remote sensing images LEVIR-CD IMP+MTP(InternImage-XL) F1 92.54 #2 of 37 Archive leaderboard report
Building change detection for remote sensing images LEVIR-CD IMP+MTP(InternImage-XL) Params(M) 335 #2 of 37 Archive leaderboard report
Building change detection for remote sensing images LEVIR-CD MAE+MTP(ViT-B+RVSA) F1 92.22 #5 of 37 Archive leaderboard report
Building change detection for remote sensing images LEVIR-CD MAE+MTP(ViT-B+RVSA) Params(M) 86 #5 of 37 Archive leaderboard report
Change Detection CDD Dataset (season-varying) IMP+MTP(InternImage-XL) F1-Score 98.33 #2 of 18 Archive leaderboard report
Change Detection CDD Dataset (season-varying) MAE+MTP(ViT-L+RVSA) F1-Score 97.98 #3 of 18 Archive leaderboard report
Change Detection CDD Dataset (season-varying) MAE+MTP(ViT-B+RVSA) F1-Score 97.87 #5 of 18 Archive leaderboard report
Change Detection CLCD MTP (ViT-B + RVSA) F1 80.3 #2 of 3 Archive leaderboard report
Change Detection EGY-BCD MTP (VIT-B+RVSA) F1 85.9 #1 of 3 Archive leaderboard report
Change Detection GVLM MTP (ViT-B + RVSA) F1 89.9 #3 of 4 Archive leaderboard report
Change Detection LEVIR-CD MAE+MTP(ViT-L+RVSA) F1 92.67 #2 of 28 Archive leaderboard report
Change Detection LEVIR-CD IMP+MTP(InternImage-XL) F1 92.54 #3 of 28 Archive leaderboard report
Change Detection LEVIR-CD MAE+MTP(ViT-B+RVSA) F1 92.22 #9 of 28 Archive leaderboard report
Change Detection OSCD - 3ch MAE+MTP(ViT-L+RVSA) F1 55.92 #1 of 6 Archive leaderboard report
Change Detection OSCD - 3ch IMP+MTP(InternImage-XL) F1 55.61 #2 of 6 Archive leaderboard report
Change Detection OSCD - 3ch MAE+MTP(ViT-B+RVSA) F1 53.36 #4 of 6 Archive leaderboard report
Change Detection WHU Building Dataset IMP+MTP(InternImage-XL) F1-score 0.9559 #1 of 7 Archive leaderboard report
Change Detection WHU Building Dataset MAE+MTP(ViT-L+RVSA) F1-score 0.9475 #3 of 7 Archive leaderboard report
Change Detection WHU Building Dataset MAE+MTP(ViT-B+RVSA) F1-score 0.9432 #5 of 7 Archive leaderboard report
Change detection for remote sensing images CDD Dataset (season-varying) IMP+MTP(InternImage-XL) F1-Score 0.9833 #2 of 25 Archive leaderboard report
Change detection for remote sensing images CDD Dataset (season-varying) MAE+MTP(ViT-L+RVSA) F1-Score 0.9798 #3 of 25 Archive leaderboard report
Change detection for remote sensing images CDD Dataset (season-varying) MAE+MTP(ViT-B+RVSA) F1-Score 0.9787 #4 of 25 Archive leaderboard report
Image Classification EuroSAT IMP+MTP(IntenImage-XL) Accuracy (%) 99.24 #2 of 15 Archive leaderboard report
Image Classification EuroSAT MAE+MTP(ViT-L+RVSA) Accuracy (%) 98.78 #9 of 15 Archive leaderboard report
Image Classification EuroSAT MAE+MTP(ViT-B+RVSA) Accuracy (%) 98.76 #10 of 15 Archive leaderboard report
Object Detection In Aerial Images DIOR MAE+MTP(ViT-L+RVSA) AP50 81.1 #1 of 4 Archive leaderboard report
Object Detection In Aerial Images DIOR MAE+MTP(ViT-B+RVSA) AP50 79.4 #2 of 4 Archive leaderboard report
Object Detection In Aerial Images DIOR IMP+MTP(InternImage-XL) AP50 78.0 #3 of 4 Archive leaderboard report
Object Detection In Aerial Images DIOR-R MAE+MTP(ViT-L+RVSA) mAP 74.54 #1 of 9 Archive leaderboard report
Object Detection In Aerial Images DIOR-R IMP+MTP(InternImage-XL) mAP 72.17 #3 of 9 Archive leaderboard report
Object Detection In Aerial Images DIOR-R MAE+MTP(ViT-B+RVSA) mAP 71.29 #4 of 9 Archive leaderboard report
Object Detection In Aerial Images DOTA MAE+MTP(ViT-L+RVSA) mAP 81.66% #9 of 58 Archive leaderboard report
Object Detection In Aerial Images DOTA IMP+MTP(InternImage-XL) mAP 80.77% #15 of 58 Archive leaderboard report
Object Detection In Aerial Images DOTA MAE+MTP(ViT-B+RVSA) mAP 80.67% #17 of 58 Archive leaderboard report
Object Detection In Aerial Images FAIR1M-2.0 MAE+MTP(ViT-L+RVSA) mAP 53.00 #1 of 3 Archive leaderboard report
Object Detection In Aerial Images FAIR1M-2.0 MAE+MTP(ViT-B+RVSA) mAP 51.92 #2 of 3 Archive leaderboard report
Object Detection In Aerial Images FAIR1M-2.0 IMP+MTP(InternImage-XL) mAP 50.93 #3 of 3 Archive leaderboard report
Object Detection In Aerial Images xView MAE+MTP(ViT-L+RVSA) AP50 19.4 #1 of 3 Archive leaderboard report
Object Detection In Aerial Images xView IMP+MTP(InternImage-XL) AP50 18.2 #2 of 3 Archive leaderboard report
Object Detection In Aerial Images xView MAE+MTP(ViT-B+RVSA) AP50 16.4 #3 of 3 Archive leaderboard report
Semantic Segmentation LoveDA MAE+MTP(ViT-L+RVSA) Category mIoU 54.17 #6 of 19 Archive leaderboard report
Semantic Segmentation LoveDA IMP+MTP(InternImage-XL) Category mIoU 54.17 #7 of 19 Archive leaderboard report
Semantic Segmentation LoveDA MAE+MTP(ViT-B+RVSA) Category mIoU 52.39 #17 of 19 Archive leaderboard report
Semantic Segmentation SpaceNet 1 MAE+MTP(ViT-L) Mean IoU 79.69 #1 of 10 Archive leaderboard report
Semantic Segmentation SpaceNet 1 MAE+MTP(ViT-B+RVSA) Mean IoU 79.63 #2 of 10 Archive leaderboard report
Semantic Segmentation SpaceNet 1 MAE+MTP(ViT-L+RVSA) Mean IoU 79.54 #3 of 10 Archive leaderboard report
Semantic Segmentation SpaceNet 1 IMP+MTP(InternImage-XL) Mean IoU 79.16 #5 of 10 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

AttentionDense ConnectionsLayer NormalizationLinear LayerMulti-Head AttentionResidual ConnectionSoftmaxVision Transformer

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