Papers › Multi-interactive Feature Learning and a Full-time Multi-modality Benchmark for Image...

Multi-interactive Feature Learning and a Full-time Multi-modality Benchmark for Image Fusion and Segmentation

4 Aug 2023ICCV 2023 1arXiv:2308.02097archive 2025-07-28

JinYuan Liu, Zhu Liu, Guanyao Wu, Long Ma, Risheng Liu, Wei Zhong, Zhongxuan Luo, Xin Fan

Multi-modality image fusion and segmentation play a vital role in autonomous driving and robotic operation. Early efforts focus on boosting the performance for only one task, e.g., fusion or segmentation, making it hard to reach~`Best of Both Worlds'. To overcome this issue, in this paper, we propose a Multi-interactive Feature learning architecture for image fusion and Segmentation, namely SegMiF, and exploit dual-task correlation to promote the performance of both tasks. The SegMiF is of a cascade structure, containing a fusion sub-network and a commonly used segmentation sub-network. By slickly bridging intermediate features between two components, the knowledge learned from the segmentation task can effectively assist the fusion task. Also, the benefited fusion network supports the segmentation one to perform more pretentiously. Besides, a hierarchical interactive attention block is established to ensure fine-grained mapping of all the vital information between two tasks, so that the modality/semantic features can be fully mutual-interactive. In addition, a dynamic weight factor is introduced to automatically adjust the corresponding weights of each task, which can balance the interactive feature correspondence and break through the limitation of laborious tuning. Furthermore, we construct a smart multi-wave binocular imaging system and collect a full-time multi-modality benchmark with 15 annotated pixel-level categories for image fusion and segmentation. Extensive experiments on several public datasets and our benchmark demonstrate that the proposed method outputs visually appealing fused images and perform averagely 7.66% higher segmentation mIoU in the real-world scene than the state-of-the-art approaches. The source code and benchmark are available at https://github.com/JinyuanLiu-CV/SegMiF.

PaperPDFConference PDFCodeCode 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 26 code samples harvested from 2 repositories linked to this paper: 19 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 1 honoured, 0 violated, 16 with no contract checked; 2 where Syntology's instrument failed) · 7 unverified. Where Syntology's instrument failed: 1 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: 13 samples from 1 repository, 12 ran (10 with no instrument failure; 2 where Syntology's instrument failed); community (archive-listed): 13 samples from 1 repository, 7 ran (7 with no instrument failure; 0 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.

jinyuanliu-cv/segmif officialmentioned in papermentioned on GitHubpytorchSyntology: 13 samples, 12 ran (2 instrument-failed) · 1 unverified report
runjia0124/coconet mentioned on GitHubpytorchMITSyntology: 13 samples, 7 ran (0 instrument-failed) · 6 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

26 samples harvested: 19 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 1 honoured, 0 violated, 16 with no contract checked; 2 where Syntology's instrument failed) · 7 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.

1ran · honoured contract
1ran · our draft was wrong
1ran; the contract check could not run
16ran
7unverified

Licence: 13 of the 26 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”. For 2 samples that ran, the graph records a signature this page does not show: an argument's recorded type or element kind is a printout of an object in Syntology's harness (such as a mock object, a class or a pandas printout), not the type of an input, so it does not describe the call's shape. “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.

jinyuanliu-cv/segmif official repository 13 samples, 12 ran (2 instrument-failed) · 1 unverified
YCrCb2RGB core/model_fusion.py ran fingerprinted no licence file found · pointer only · 145edd13c3925a58 · report fixture: signature input_im:Tensor/4/float · returned Tensor · level recorded 2026-09-24
compute_cls_loss core/loss.py ran no licence file found · pointer only · c567234c5e7fa848 · report fixture: signature preds:list/1/Tensor, targets:Tensor/3/float, mask:Tensor/2/float · returned Tensor · level recorded 2026-09-24
compute_cnt_loss core/loss.py ran no licence file found · pointer only · 2fe6b97c7e7cccbb · report fixture: signature preds:list/1/Tensor, targets:Tensor/3/float, mask:Tensor/2/bool · returned Tensor · level recorded 2026-09-24
coords_fmap2orig core/loss.py ran fingerprinted no licence file found · pointer only · 68ee569246bd7e3a · report fixture: signature feature:Tensor/4/float, stride:int/0/int · returned Tensor · level recorded 2026-09-24
downsample in 59 papers lap_loss.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · 1f6001e1c3b06556 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
gauss_kernel in 15 papers lap_loss.py ran no licence file found · pointer only · 4a150d48b91667f9 · report fixture: signature size:int/0/int, device:device/0/?, channels:int/0/int · returned Tensor · level recorded 2026-09-24
load_img_name_list datasets/voc_method.py ran no licence file found · pointer only · 0cc9285c14985e5d · report fixture: signature img_name_list_path:str/0/str · returned ndarray · level recorded 2026-09-24
normalize_img in 12 papers datasets/imutils.py ran no licence file found · pointer only · d1a6979f946f9e74 · report fixture: signature img:ndarray/3/int, mean:list/1/float, std:list/1/float · returned ndarray · level recorded 2026-09-24
prepare_data_path TaskFusion_dataset2.py ran · our draft was wrong no licence file found · pointer only · b79bae2be65a7ef0 · report fixture: signature dataset_path:str/0/str · returned tuple · level recorded 2026-09-24
random_scaling datasets/imutils.py ran no licence file found · pointer only · a920d698dd17a625 · report fixture: signature image:ndarray/3/float, label:ndarray/2/int, size_range:tuple/1/int, scale_range:tuple/1/float · returned tuple · level recorded 2026-09-24
random_scaling2 datasets/imutils.py ran no licence file found · pointer only · 49fc95c7acdb2ea4 · report fixture: signature image:ndarray/3/int, image_vis:ndarray/2/int, image_mask:ndarray/2/int, label:ndarray/2/int, size_range:tuple/1/int, scale_range:tuple/1/float · returned tuple · level recorded 2026-09-24
upsample in 87 papers
census: 11 implementations from 16 papers, 9 distinct outputs across 3 buckets, one shared input per bucket
lap_loss.py ran fingerprinted no licence file found · pointer only · 267b7d002ecac955 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
RGB2YCrCb core/model_fusion.py unverified no licence file found · pointer only · 6b1c47ea9127b33e · report
runjia0124/coconet community (archive-listed) 13 samples, 7 ran (0 instrument-failed) · 6 unverified
YCbCr2RGB utils/utils.py ran fingerprinted MIT (permissive) · 92167228343b84a5 · report fixture: signature Y:Tensor/2/float, Cb:Tensor/2/float, Cr:Tensor/2/float · returned tuple · level recorded 2026-09-24
fname_presuffix utils/utils.py ran MIT (permissive) · 71a890b56b7f51ea · report fixture: signature fname:str/0/str, prefix:str/0/str, suffix:str/0/str, newpath:str/0/str, use_ext:bool/0/bool · returned str · level recorded 2026-09-24
normPRED in 5 papers utils/save_image.py ran · honoured contract fingerprinted MIT (permissive) · 89e4412c100b0f9b · report fixture: signature d:Tensor/2/float · returned Tensor · level recorded 2026-09-22
normimage utils/save_image.py ran MIT (permissive) · df54d7f9e9e4ab99 · report fixture: returned ndarray · level recorded 2026-09-24
normimage_test utils/save_image.py ran MIT (permissive) · 1d18356aa2fee4e0 · report fixture: returned ndarray · level recorded 2026-09-24
split_filename utils/utils.py ran fingerprinted MIT (permissive) · 47482689d9a75517 · report fixture: signature fname:str/0/str · returned tuple · level recorded 2026-09-24
weights_to_cpu utils/checkpoint.py ran MIT (permissive) · b683a315ccc25715 · report fixture: signature state_dict:dict/0/? · returned OrderedDict · level recorded 2026-09-24
load_model in 479 papers models/P_loss.py unverified MIT (permissive) · bbfe8d248ce2ed69 · report
load_part utils/checkpoint.py unverified MIT (permissive) · 0511b91fcab989b2 · report
measure_info models/train_tasks.py unverified MIT (permissive) · 76e6bd620ca82ccc · report
measure_module1 models/train_tasks.py unverified MIT (permissive) · 4f4b727b0fc6cd95 · report
resume in 9 papers utils/checkpoint.py unverified MIT (permissive) · a3db2d0cc62c57ce · report

Tasks

Autonomous DrivingSegmentationSemantic SegmentationThermal Image Segmentation

Datasets

Introduced by this paper, per the archive.

FMB Dataset

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semantic Segmentation FMB Dataset SegMiF (RGB-Infrared) mIoU 54.80 #7 of 14 Archive leaderboard report
Semantic Segmentation FMB Dataset SegMiF (RGB) mIoU 50.50 #10 of 14 Archive leaderboard report
Thermal Image Segmentation MFN Dataset SegMiF mIOU 56.1 #25 of 55 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

Focus

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