Papers › PAIF: Perception-Aware Infrared-Visible Image Fusion for Attack-Tolerant Semantic Segmentation

PAIF: Perception-Aware Infrared-Visible Image Fusion for Attack-Tolerant Semantic Segmentation

8 Aug 2023arXiv:2308.03979archive 2025-07-28

Zhu Liu, JinYuan Liu, Benzhuang Zhang, Long Ma, Xin Fan, Risheng Liu

Infrared and visible image fusion is a powerful technique that combines complementary information from different modalities for downstream semantic perception tasks. Existing learning-based methods show remarkable performance, but are suffering from the inherent vulnerability of adversarial attacks, causing a significant decrease in accuracy. In this work, a perception-aware fusion framework is proposed to promote segmentation robustness in adversarial scenes. We first conduct systematic analyses about the components of image fusion, investigating the correlation with segmentation robustness under adversarial perturbations. Based on these analyses, we propose a harmonized architecture search with a decomposition-based structure to balance standard accuracy and robustness. We also propose an adaptive learning strategy to improve the parameter robustness of image fusion, which can learn effective feature extraction under diverse adversarial perturbations. Thus, the goals of image fusion (\textit{i.e.,} extracting complementary features from source modalities and defending attack) can be realized from the perspectives of architectural and learning strategies. Extensive experimental results demonstrate that our scheme substantially enhances the robustness, with gains of 15.3% mIOU of segmentation in the adversarial scene, compared with advanced competitors. The source codes are available at https://github.com/LiuZhu-CV/PAIF.

PaperPDFCodeCode 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="2308.03979")

Code

Syntology Ran 13 of 27 code samples harvested from 3 repositories linked to this paper; 14 have no recorded run. Of those that ran: 2 ran · our draft was wrong; 11 ran with no contract checked.

By repository: official repository: 2 samples from 1 repository, 0 ran; community (archive-listed): 25 samples from 2 repositories, 13 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

liuzhu-cv/paif officialmentioned in papermentioned on GitHubpytorch report
LiuZhu-CV/BDLFusion mentioned on GitHubpytorchMIT report
liuzhu-cv/crmef mentioned on GitHubpytorch 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

27 samples harvested; 13 ran; 0 honoured the contract we drafted; 14 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.

2ran · our draft was wrong
11ran
14unverified

Licence: 11 of the 27 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 3 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.

RGB2YCrCb liuzhu-cv/paif/test_original.py official repository unverified no licence file found · pointer only · f724ee102895d8e3 · report
YCrCb2RGB liuzhu-cv/paif/test_original.py official repository unverified no licence file found · pointer only · 96dcdaf98db413c7 · report
CropSample liuzhu-cv/crmef/pietorch/N_modules.py community (archive-listed) ran no licence file found · pointer only · 0415a04e36607241 · report
CropSample2 liuzhu-cv/crmef/pietorch/N_modules.py community (archive-listed) ran no licence file found · pointer only · 79504595f406b0de · report
CropSample3 liuzhu-cv/crmef/pietorch/N_modules.py community (archive-listed) ran no licence file found · pointer only · 747145371dbd7ffb · report
YCrCb2RGB LiuZhu-CV/BDLFusion/model/fcos_fusion.py community (archive-listed) ran fingerprinted MIT (permissive) · 145edd13c3925a58 · report
cal_gradient_penalty liuzhu-cv/crmef/AHDRNAS.py community (archive-listed) ran no licence file found · pointer only · 0c6f4d7bb0001241 · report
compute_cls_loss LiuZhu-CV/BDLFusion/model/loss.py community (archive-listed) ran MIT (permissive) · c567234c5e7fa848 · report
compute_cnt_loss LiuZhu-CV/BDLFusion/model/loss.py community (archive-listed) ran MIT (permissive) · 2fe6b97c7e7cccbb · report
conv3x3 LiuZhu-CV/BDLFusion/model/backbone/resnet.py community (archive-listed) ran · our draft was wrong MIT (permissive) · fac5364e2f53c6db · report
conv3x3 liuzhu-cv/crmef/pietorch/se_nets.py community (archive-listed) ran · our draft was wrong no licence file found · pointer only · 583f9780bdd00a45 · report
conv_layer liuzhu-cv/crmef/AHDRNAS.py community (archive-listed) ran no licence file found · pointer only · d3a234f32905b183 · report
coords_fmap2orig LiuZhu-CV/BDLFusion/model/loss.py community (archive-listed) ran fingerprinted MIT (permissive) · 68ee569246bd7e3a · report
get_patch_from_file liuzhu-cv/crmef/dataset/dataset_patches.py community (archive-listed) ran no licence file found · pointer only · 6a4bda1402e49df9 · report
get_tv liuzhu-cv/crmef/PerceptualLoss.py community (archive-listed) ran fingerprinted no licence file found · pointer only · 1a58de2bd0d27f53 · report
RGB2YCrCb LiuZhu-CV/BDLFusion/model/fcos_fusion.py community (archive-listed) unverified MIT (permissive) · 6b1c47ea9127b33e · report
colorJitter LiuZhu-CV/BDLFusion/dataset/augment.py community (archive-listed) unverified MIT (permissive) · 8995c32130a77e1b · report
data_augmentation liuzhu-cv/crmef/dataset/dataset_patches.py community (archive-listed) unverified no licence file found · pointer only · 0db1cd12ba9b89e6 · report
eval_ap_2d LiuZhu-CV/BDLFusion/eval_detection.py community (archive-listed) unverified MIT (permissive) · f1eaef8506fafbc4 · report
flip LiuZhu-CV/BDLFusion/dataset/VOC_dataset.py community (archive-listed) unverified MIT (permissive) · f282dfb509f5c783 · report
flip LiuZhu-CV/BDLFusion/dataset/VOC_dataset_Fusion.py community (archive-listed) unverified MIT (permissive) · 77ccaaed6fe6ba6c · report
iou_2d LiuZhu-CV/BDLFusion/eval_detection.py community (archive-listed) unverified MIT (permissive) · c756c28cd59b62a3 · report
random_rotation LiuZhu-CV/BDLFusion/dataset/augment.py community (archive-listed) unverified MIT (permissive) · 7a9983c45529c7ed · report
random_rotation2 LiuZhu-CV/BDLFusion/dataset/augment.py community (archive-listed) unverified MIT (permissive) · 6356ce97cd733a2e · report
resnet18 LiuZhu-CV/BDLFusion/model/backbone/resnet.py community (archive-listed) unverified MIT (permissive) · 004e5b2448286424 · report
resnet34 LiuZhu-CV/BDLFusion/model/backbone/resnet.py community (archive-listed) unverified MIT (permissive) · ab6897aaaf1e833e · report
sort_by_score LiuZhu-CV/BDLFusion/eval_detection.py community (archive-listed) unverified MIT (permissive) · 4f5c46171ffa62aa · report

Tasks

Infrared And Visible Image FusionSegmentationSemantic SegmentationThermal Image Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Thermal Image Segmentation MFN Dataset PAIF mIOU 56.5 #22 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.

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