{"url":"/dataset/fmb-dataset","name":"FMB Dataset","full_name":"Full-time Multi-modality Benchmark Dataset","description_markdown":"FMB contains 1500 well-registered infrared and visible image pairs with 14 annotated pixel-level categories. Also, it covers a wide range of pixel variations and various severe environments, e.g., dense fog, heavy rain, and low-light condition. The FMB dataset includes rich scenes under different illumination conditions, so that it enables fusion/segmentation model to improve the generalization ability greatly. We labeled 98.16% of all pixels into 14 different categories including Road, Sidewalk, Building, Traffic Light, Traffic Sign, Vegetation, Sky, Person, Car, Truck, Bus, Motorcycle, Bicycle and Pole, which often appear in real world automatic driving and semantic understanding tasks.","description_withheld":null,"homepage":"https://github.com/JinyuanLiu-CV/SegMiF","introduced_date":"2023-08-04","introduced_date_note":null,"introduced_by":{"paper":"/paper/multi-interactive-feature-learning-and-a-full","title":"Multi-interactive Feature Learning and a Full-time Multi-modality Benchmark for Image Fusion and Segmentation","first_author":"JinYuan Liu","url":null},"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Semantic Segmentation","url":"/task/semantic-segmentation","datasets_with_task":"/datasets/task/semantic-segmentation"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["FMB Dataset"],"data_loaders":[],"num_papers_in_archive":20,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/semantic-segmentation-on-fmb-dataset","task":"Semantic Segmentation","dataset_variant":"FMB Dataset","rows":14,"metrics":["mIoU"],"first_row_in_archive_order":{"model":"RoadFormer+ (RGB-Infrared)","paper":"/paper/roadformer-delivering-rgb-x-scene-parsing","metrics":{"mIoU":"73.1"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/unveiling-the-potential-of-segment-anything","title":"Unveiling the Potential of Segment Anything Model 2 for RGB-Thermal Semantic Segmentation with Language Guidance","date":"2025-03-04","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/2408-01343","title":"StitchFusion: Weaving Any Visual Modalities to Enhance Multimodal Semantic Segmentation","date":"2024-08-02","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/roadformer-delivering-rgb-x-scene-parsing","title":"RoadFormer+: Delivering RGB-X Scene Parsing through Scale-Aware Information Decoupling and Advanced Heterogeneous Feature Fusion","date":"2024-07-31","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/multimodal-transformer-for-material","title":"MMSFormer: Multimodal Transformer for Material and Semantic Segmentation","date":"2023-09-07","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/egfnet-edge-aware-guidance-fusion-network-for","title":"EGFNet: Edge-Aware Guidance Fusion Network for RGB–Thermal Urban Scene Parsing","date":"2023-08-15","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/multi-interactive-feature-learning-and-a-full","title":"Multi-interactive Feature Learning and a Full-time Multi-modality Benchmark for Image Fusion and Segmentation","date":"2023-08-04","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":26,"samples_ran":19,"samples_unverified":7,"pointer_only_for_licence":13,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/target-aware-dual-adversarial-learning-and-a","title":"Target-aware Dual Adversarial Learning and a Multi-scenario Multi-Modality Benchmark to Fuse Infrared and Visible for Object Detection","date":"2022-03-30","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/feanet-feature-enhanced-attention-network-for","title":"FEANet: Feature-Enhanced Attention Network for RGB-Thermal Real-time Semantic Segmentation","date":"2021-10-18","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":1,"samples_unverified":4,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/gmnet-graph-matching-network-for-large-scale","title":"GMNet: Graph Matching Network for Large Scale Part Semantic Segmentation in the Wild","date":"2020-07-17","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/didfuse-deep-image-decomposition-for-infrared","title":"DIDFuse: Deep Image Decomposition for Infrared and Visible Image Fusion","date":"2020-03-20","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":6,"samples_unverified":1,"pointer_only_for_licence":7,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/reconet-real-time-coherent-video-style","title":"ReCoNet: Real-time Coherent Video Style Transfer Network","date":"2018-07-03","rows_on_this_dataset":1,"code_links":8,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":3,"samples_harvested":38,"samples_ran":26,"samples_unverified":12,"pointer_only_for_licence":20,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}