SAM-Enhanced Segmentation on Road Datasets: Balancing Critical Classes in Autonomous Driving

• URL: http://arxiv.org/abs/2605.28136v1
• Date: Wed, 27 May 2026 08:21:04 GMT
• Title: SAM-Enhanced Segmentation on Road Datasets: Balancing Critical Classes in Autonomous Driving
• Abstract summary: Zenseact Open dataset (ZOD) provides rich multi-sensor data but only bounding-box labels.<n>Our pipeline produces dense, pixel-level annotations for ZOD by converting bounding boxes into semantic masks.<n>Dense semantic segmentation is essential for autonomous driving, yet many multi-modal datasets lack pixel-level annotations.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Dense semantic segmentation is essential for autonomous driving, yet many multi-modal datasets lack pixel-level annotations. The Zenseact Open Dataset (ZOD) provides rich multi-sensor data but only bounding-box labels, limiting its use for segmentation research. Our primary contribution is a Segment Anything Model (SAM)-based annotation pipeline that produces dense, pixel-level annotations for ZOD by converting bounding boxes into semantic masks. In this pilot study, we process over 100,000 frames and manually curate a 2,300-frame subset (36% acceptance rate) to establish a reliable baseline. Using these annotations, we evaluate transformer-based CLFT and CNN-based DeepLabV3+ architectures across diverse weather conditions, achieving up to 48.1% mIoU with CLFT-Hybrid. To address extreme class imbalance, where pedestrians, cyclists, and signs constitute less than 1% of pixels, we explore specialized models targeting rare classes. We further validate the pipeline on the Iseauto autonomous-vehicle platform, achieving 77.5% mIoU, and show that SAM-derived representations transfer effectively across sensor configurations via bidirectional transfer learning. All code and annotations are released to support reproducible research.

Related papers

• SegEarth-OV3: Exploring SAM 3 for Open-Vocabulary Semantic Segmentation in Remote Sensing Images [51.42466259821335]
  We present a preliminary exploration of applying SAM 3 to the remote sensing OVSS task without any training.<n>First, we implement a mask fusion strategy that combines the outputs from SAM 3's semantic segmentation head and the Transformer decoder.<n>Second, we utilize the presence score from the presence head to filter out categories that do not exist in the scene.
  arXiv  Detail & Related papers  (2025-12-09T15:42:28Z)
• Segment Any Vehicle: Semantic and Visual Context Driven SAM and A Benchmark [12.231630639022335]
  We propose SAV, a novel framework comprising three core components: a SAM-based encoder-decoder, a vehicle part knowledge graph, and a context sample retrieval encoding module.<n>The knowledge graph explicitly models the spatial and geometric relationships among vehicle parts through a structured ontology, effectively encoding prior structural knowledge.<n>We introduce a new large-scale benchmark dataset for vehicle part segmentation, named VehicleSeg10K, which contains 11,665 high-quality pixel-level annotations.
  arXiv  Detail & Related papers  (2025-08-06T09:46:49Z)
• JiSAM: Alleviate Labeling Burden and Corner Case Problems in Autonomous Driving via Minimal Real-World Data [49.2298619289506]
  We propose a plug-and-play method called JiSAM, shorthand for Jittering augmentation, domain-aware backbone and memory-based Sectorized AlignMent.<n>In extensive experiments conducted on the famous AD dataset NuScenes, we demonstrate that, with SOTA 3D object detector, JiSAM is able to utilize the simulation data and only labels on 2.5% available real data to achieve comparable performance to models trained on all real data.
  arXiv  Detail & Related papers  (2025-03-11T13:35:39Z)
• Prompting DirectSAM for Semantic Contour Extraction in Remote Sensing Images [11.845626002236772]
  We introduce a foundation model derived from DirectSAM, termed DirectSAM-RS, which inherits the strong segmentation capability acquired from natural images. This dataset comprises over 34k image-text-contour triplets, making it at least 30 times larger than individual dataset. We evaluate the DirectSAM-RS in both zero-shot and fine-tuning setting, and demonstrate that it achieves state-of-the-art performance across several downstream benchmarks.
  arXiv  Detail & Related papers  (2024-10-08T16:55:42Z)
• Navya3DSeg -- Navya 3D Semantic Segmentation Dataset & split generation for autonomous vehicles [63.20765930558542]
  3D semantic data are useful for core perception tasks such as obstacle detection and ego-vehicle localization. We propose a new dataset, Navya 3D (Navya3DSeg), with a diverse label space corresponding to a large scale production grade operational domain. It contains 23 labeled sequences and 25 supplementary sequences without labels, designed to explore self-supervised and semi-supervised semantic segmentation benchmarks on point clouds.
  arXiv  Detail & Related papers  (2023-02-16T13:41:19Z)
• LESS: Label-Efficient Semantic Segmentation for LiDAR Point Clouds [62.49198183539889]
  We propose a label-efficient semantic segmentation pipeline for outdoor scenes with LiDAR point clouds. Our method co-designs an efficient labeling process with semi/weakly supervised learning. Our proposed method is even highly competitive compared to the fully supervised counterpart with 100% labels.
  arXiv  Detail & Related papers  (2022-10-14T19:13:36Z)
• SELMA: SEmantic Large-scale Multimodal Acquisitions in Variable Weather, Daytime and Viewpoints [36.57734409668748]
  We introduce SELMA, a novel dataset for semantic segmentation. It contains more than 30K unique waypoints acquired from 24 different sensors including RGB, depth, semantic cameras and LiDARs. It is based on CARLA, an open-source simulator for generating synthetic data in autonomous driving scenarios.
  arXiv  Detail & Related papers  (2022-04-20T21:22:56Z)
• MSeg: A Composite Dataset for Multi-domain Semantic Segmentation [100.17755160696939]
  We present MSeg, a composite dataset that unifies semantic segmentation datasets from different domains. We reconcile the generalization and bring the pixel-level annotations into alignment by relabeling more than 220,000 object masks in more than 80,000 images. A model trained on MSeg ranks first on the WildDash-v1 leaderboard for robust semantic segmentation, with no exposure to WildDash data during training.
  arXiv  Detail & Related papers  (2021-12-27T16:16:35Z)
• Detecting 32 Pedestrian Attributes for Autonomous Vehicles [103.87351701138554]
  In this paper, we address the problem of jointly detecting pedestrians and recognizing 32 pedestrian attributes. We introduce a Multi-Task Learning (MTL) model relying on a composite field framework, which achieves both goals in an efficient way. We show competitive detection and attribute recognition results, as well as a more stable MTL training.
  arXiv  Detail & Related papers  (2020-12-04T15:10:12Z)
• Monocular Instance Motion Segmentation for Autonomous Driving: KITTI InstanceMotSeg Dataset and Multi-task Baseline [5.000331633798637]
  Moving object segmentation is a crucial task for autonomous vehicles as it can be used to segment objects in a class agnostic manner. Although pixel-wise motion segmentation has been studied in autonomous driving literature, it has been rarely addressed at the instance level. We create a new InstanceMotSeg dataset comprising of 12.9K samples improving upon our KITTIMoSeg dataset.
  arXiv  Detail & Related papers  (2020-08-16T21:47:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.