Deep neural networks for aerial image segmentation require large amounts of labeled data, but high-quality aerial datasets with precise annotations are scarce and costly to produce. To address this limitation, we propose a self-supervised pretraining method that improves segmentation performance while reducing reliance on labeled data. Our approach uses inpainting-based pretraining, where the model learns to reconstruct missing regions in aerial images, capturing their inherent structure before being fine-tuned for road extraction. This method improves generalization, enhances robustness to domain shifts, and is invariant to model architecture and dataset choice. Experiments show that our pretraining significantly boosts segmentation accuracy, especially in low-data regimes, making it a scalable solution for aerial image analysis.
In the recent years, the research community has witnessed growing use of 3D point cloud data for the high applicability in various real-world applications. By means of 3D point cloud, this modality enables to consider the actual size and spatial understanding. The applied fields include mechanical control of robots, vehicles, or other real-world systems. Along this line, we would like to improve 3D point cloud instance segmentation which has emerged as a particularly promising approach for these applications. However, the creation of 3D point cloud datasets entails enormous costs compared to 2D image datasets. To train a model of 3D point cloud instance segmentation, it is necessary not only to assign categories but also to provide detailed annotations for each point in the large-scale 3D space. Meanwhile, the increase of recent proposals for generative models in 3D domain has spurred proposals for using a generative model to create 3D point cloud data. In this work, we propose a pre-training with 3D synthetic data to train a 3D point cloud instance segmentation model based on generative model for 3D scenes represented by point cloud data. We directly generate 3D point cloud data with Point-E for inserting a generated data into a 3D scene. More recently in 2025, although there are other accurate 3D generation models, even using the Point-E as an early 3D generative model can effectively support the pre-training with 3D synthetic data. In the experimental section, we compare our pre-training method with baseline methods indicated improved performance, demonstrating the efficacy of 3D generative models for 3D point cloud instance segmentation.
Aerial and satellite imagery are inherently complementary remote sensing sources, offering high-resolution detail alongside expansive spatial coverage. However, the use of these sources for land cover segmentation introduces several challenges, prompting the development of a variety of segmentation methods. Among these approaches, the DeepLabV3+ architecture is considered as a promising approach in the field of single-source image segmentation. However, despite its reliable results for segmentation, there is still a need to increase its robustness and improve its performance. This is particularly crucial for multimodal image segmentation, where the fusion of diverse types of information is essential. An interesting approach involves enhancing this architectural framework through the integration of novel components and the modification of certain internal processes. In this paper, we enhance the DeepLabV3+ architecture by introducing a new transposed conventional layers block for upsampling a second entry to fuse it with high level features. This block is designed to amplify and integrate information from satellite images, thereby enriching the segmentation process through fusion with aerial images. For experiments, we used the LandCover.ai (Land Cover from Aerial Imagery) dataset for aerial images, alongside the corresponding dataset sourced from Sentinel 2 data. Through the fusion of both sources, the mean Intersection over Union (mIoU) achieved a total mIoU of 84.91% without data augmentation.
Early detection, accurate segmentation, classification and tracking of polyps during colonoscopy are critical for preventing colorectal cancer. Many existing deep-learning-based methods for analyzing colonoscopic videos either require task-specific fine-tuning, lack tracking capabilities, or rely on domain-specific pre-training. In this paper, we introduce \textit{PolypSegTrack}, a novel foundation model that jointly addresses polyp detection, segmentation, classification and unsupervised tracking in colonoscopic videos. Our approach leverages a novel conditional mask loss, enabling flexible training across datasets with either pixel-level segmentation masks or bounding box annotations, allowing us to bypass task-specific fine-tuning. Our unsupervised tracking module reliably associates polyp instances across frames using object queries, without relying on any heuristics. We leverage a robust vision foundation model backbone that is pre-trained unsupervisedly on natural images, thereby removing the need for domain-specific pre-training. Extensive experiments on multiple polyp benchmarks demonstrate that our method significantly outperforms existing state-of-the-art approaches in detection, segmentation, classification, and tracking.
Medical image segmentation typically relies solely on visual data, overlooking the rich textual information clinicians use for diagnosis. Vision-language models attempt to bridge this gap, but existing approaches often process visual and textual features independently, resulting in weak cross-modal alignment. Simple fusion techniques fail due to the inherent differences between spatial visual features and sequential text embeddings. Additionally, medical terminology deviates from general language, limiting the effectiveness of off-the-shelf text encoders and further hindering vision-language alignment. We propose BiPVL-Seg, an end-to-end framework that integrates vision-language fusion and embedding alignment through architectural and training innovations, where both components reinforce each other to enhance medical image segmentation. BiPVL-Seg introduces bidirectional progressive fusion in the architecture, which facilitates stage-wise information exchange between vision and text encoders. Additionally, it incorporates global-local contrastive alignment, a training objective that enhances the text encoder's comprehension by aligning text and vision embeddings at both class and concept levels. Extensive experiments on diverse medical imaging benchmarks across CT and MR modalities demonstrate BiPVL-Seg's superior performance when compared with state-of-the-art methods in complex multi-class segmentation. Source code is available in this GitHub repository.
This paper addresses the challenge of data scarcity in semantic segmentation by generating datasets through text-to-image (T2I) generation models, reducing image acquisition and labeling costs. Segmentation dataset generation faces two key challenges: 1) aligning generated samples with the target domain and 2) producing informative samples beyond the training data. Fine-tuning T2I models can help generate samples aligned with the target domain. However, it often overfits and memorizes training data, limiting their ability to generate diverse and well-aligned samples. To overcome these issues, we propose Concept-Aware LoRA (CA-LoRA), a novel fine-tuning approach that selectively identifies and updates only the weights associated with necessary concepts (e.g., style or viewpoint) for domain alignment while preserving the pretrained knowledge of the T2I model to produce informative samples. We demonstrate its effectiveness in generating datasets for urban-scene segmentation, outperforming baseline and state-of-the-art methods in in-domain (few-shot and fully-supervised) settings, as well as in domain generalization tasks, especially under challenging conditions such as adverse weather and varying illumination, further highlighting its superiority.
As a fundamental task in computer vision, semantic segmentation is widely applied in fields such as autonomous driving, remote sensing image analysis, and medical image processing. In recent years, Transformer-based segmentation methods have demonstrated strong performance in global feature modeling. However, they still struggle with blurred target boundaries and insufficient recognition of small targets. To address these issues, this study proposes a Mask2Former-based semantic segmentation algorithm incorporating a boundary enhancement feature bridging module (BEFBM). The goal is to improve target boundary accuracy and segmentation consistency. Built upon the Mask2Former framework, this method constructs a boundary-aware feature map and introduces a feature bridging mechanism. This enables effective cross-scale feature fusion, enhancing the model's ability to focus on target boundaries. Experiments on the Cityscapes dataset demonstrate that, compared to mainstream segmentation methods, the proposed approach achieves significant improvements in metrics such as mIOU, mDICE, and mRecall. It also exhibits superior boundary retention in complex scenes. Visual analysis further confirms the model's advantages in fine-grained regions. Future research will focus on optimizing computational efficiency and exploring its potential in other high-precision segmentation tasks.
Motivation: Lack of tools for comprehensive and complete segmentation of deep grey nuclei using a single software for reproducibility and repeatability Goal(s): A fast accurate and robust method for segmentation of deep grey nuclei (thalamic nuclei, basal ganglia, claustrum, red nucleus) from structural T1 MRI data at conventional field strengths Approach: We leverage the improved contrast of white-matter-nulled imaging by using the recently proposed Histogram-based Polynomial Synthesis (HIPS) to synthesize WMn-like images from standard T1 and then use a multi-atlas segmentation with joint label fusion to segment deep grey nuclei. Results: The method worked robustly on all field strengths (1.5/3/7) and Dice coefficients of 0.7 or more were achieved for all structures compared against manual segmentation ground truth. Impact: This method facilitates careful investigation of the role of deep grey nuclei by enabling the use of conventional T1 data from large public databases, which has not been possible, hitherto, due to lack of robust reproducible segmentation tools.
Camouflaged object segmentation presents unique challenges compared to traditional segmentation tasks, primarily due to the high similarity in patterns and colors between camouflaged objects and their backgrounds. Effective solutions to this problem have significant implications in critical areas such as pest control, defect detection, and lesion segmentation in medical imaging. Prior research has predominantly emphasized supervised or unsupervised pre-training methods, leaving zero-shot approaches significantly underdeveloped. Existing zero-shot techniques commonly utilize the Segment Anything Model (SAM) in automatic mode or rely on vision-language models to generate cues for segmentation; however, their performances remain unsatisfactory. Optical flow, commonly utilized for detecting moving objects, has demonstrated effectiveness even with camouflaged entities. Our method integrates optical flow, a vision-language model, and SAM 2 into a sequential pipeline, where the output of one component provides cues for the next. Evaluated on the MoCA-Masks dataset, our approach achieves outstanding performance improvements, significantly outperforming existing zero-shot methods by raising the mean Intersection-over-Union (mIoU) from 0.273 to 0.561. Remarkably, this simple yet effective approach also surpasses supervised methods, increasing mIoU from 0.422 to 0.561. Additionally, evaluation on the MoCA-Filter dataset demonstrates an increase in the success rate from 0.628 to 0.697 when compared with FlowSAM, a supervised transfer method. A thorough ablation study further validates the individual contributions of each component.
Accurate segmentation of sea ice types is essential for mapping and operational forecasting of sea ice conditions for safe navigation and resource extraction in ice-covered waters, as well as for understanding polar climate processes. While deep learning methods have shown promise in automating sea ice segmentation, they often rely on extensive labeled datasets which require expert knowledge and are time-consuming to create. Recently, foundation models (FMs) have shown excellent results for segmenting remote sensing images by utilizing pre-training on large datasets using self-supervised techniques. However, their effectiveness for sea ice segmentation remains unexplored, especially given sea ice's complex structures, seasonal changes, and unique spectral signatures, as well as peculiar Synthetic Aperture Radar (SAR) imagery characteristics including banding and scalloping noise, and varying ice backscatter characteristics, which are often missing in standard remote sensing pre-training datasets. In particular, SAR images over polar regions are acquired using different modes than used to capture the images at lower latitudes by the same sensors that form training datasets for FMs. This study evaluates ten remote sensing FMs for sea ice type segmentation using Sentinel-1 SAR imagery, focusing on their seasonal and spatial generalization. Among the selected models, Prithvi-600M outperforms the baseline models, while CROMA achieves a very similar performance in F1-score. Our contributions include offering a systematic methodology for selecting FMs for sea ice data analysis, a comprehensive benchmarking study on performances of FMs for sea ice segmentation with tailored performance metrics, and insights into existing gaps and future directions for improving domain-specific models in polar applications using SAR data.
Before deployment in the real-world deep neural networks require thorough evaluation of how they handle both knowns, inputs represented in the training data, and unknowns (anomalies). This is especially important for scene understanding tasks with safety critical applications, such as in autonomous driving. Existing datasets allow evaluation of only knowns or unknowns - but not both, which is required to establish "in the wild" suitability of deep neural network models. To bridge this gap, we propose a novel anomaly segmentation dataset, ISSU, that features a diverse set of anomaly inputs from cluttered real-world environments. The dataset is twice larger than existing anomaly segmentation datasets, and provides a training, validation and test set for controlled in-domain evaluation. The test set consists of a static and temporal part, with the latter comprised of videos. The dataset provides annotations for both closed-set (knowns) and anomalies, enabling closed-set and open-set evaluation. The dataset covers diverse conditions, such as domain and cross-sensor shift, illumination variation and allows ablation of anomaly detection methods with respect to these variations. Evaluation results of current state-of-the-art methods confirm the need for improvements especially in domain-generalization, small and large object segmentation.
Brain vessel segmentation of MR scans is a critical step in the diagnosis of cerebrovascular diseases. Due to the fine vessel structure, manual vessel segmentation is time consuming. Therefore, automatic deep learning (DL) based segmentation techniques are intensively investigated. As conventional DL models yield a high complexity and lack an indication of decision reliability, they are often considered as not trustworthy. This work aims to increase trust in DL based models by incorporating epistemic uncertainty quantification into cerebrovascular segmentation models for the first time. By implementing an efficient ensemble model combining the advantages of Bayesian Approximation and Deep Ensembles, we aim to overcome the high computational costs of conventional probabilistic networks. Areas of high model uncertainty and erroneous predictions are aligned which demonstrates the effectiveness and reliability of the approach. We perform extensive experiments applying the ensemble model on out-of-distribution (OOD) data. We demonstrate that for OOD-images, the estimated uncertainty increases. Additionally, omitting highly uncertain areas improves the segmentation quality, both for in- and out-of-distribution data. The ensemble model explains its limitations in a reliable manner and can maintain trustworthiness also for OOD data and could be considered in clinical applications
Moving object segmentation is a crucial task for achieving a high-level understanding of visual scenes and has numerous downstream applications. Humans can effortlessly segment moving objects in videos. Previous work has largely relied on optical flow to provide motion cues; however, this approach often results in imperfect predictions due to challenges such as partial motion, complex deformations, motion blur and background distractions. We propose a novel approach for moving object segmentation that combines long-range trajectory motion cues with DINO-based semantic features and leverages SAM2 for pixel-level mask densification through an iterative prompting strategy. Our model employs Spatio-Temporal Trajectory Attention and Motion-Semantic Decoupled Embedding to prioritize motion while integrating semantic support. Extensive testing on diverse datasets demonstrates state-of-the-art performance, excelling in challenging scenarios and fine-grained segmentation of multiple objects. Our code is available at https://motion-seg.github.io/.
Vision Foundation Model (VFM) such as the Segment Anything Model (SAM) and Contrastive Language-Image Pre-training Model (CLIP) has shown promising performance for segmentation and detection tasks. However, although SAM excels in fine-grained segmentation, it faces major challenges when applying it to semantic-aware segmentation. While CLIP exhibits a strong semantic understanding capability via aligning the global features of language and vision, it has deficiencies in fine-grained segmentation tasks. Human parsing requires to segment human bodies into constituent parts and involves both accurate fine-grained segmentation and high semantic understanding of each part. Based on traits of SAM and CLIP, we formulate high efficient modules to effectively integrate features of them to benefit human parsing. We propose a Semantic-Refinement Module to integrate semantic features of CLIP with SAM features to benefit parsing. Moreover, we formulate a high efficient Fine-tuning Module to adjust the pretrained SAM for human parsing that needs high semantic information and simultaneously demands spatial details, which significantly reduces the training time compared with full-time training and achieves notable performance. Extensive experiments demonstrate the effectiveness of our method on LIP, PPP, and CIHP databases.
Open-vocabulary querying in 3D space is crucial for enabling more intelligent perception in applications such as robotics, autonomous systems, and augmented reality. However, most existing methods rely on 2D pixel-level parsing, leading to multi-view inconsistencies and poor 3D object retrieval. Moreover, they are limited to static scenes and struggle with dynamic scenes due to the complexities of motion modeling. In this paper, we propose Segment then Splat, a 3D-aware open vocabulary segmentation approach for both static and dynamic scenes based on Gaussian Splatting. Segment then Splat reverses the long established approach of "segmentation after reconstruction" by dividing Gaussians into distinct object sets before reconstruction. Once the reconstruction is complete, the scene is naturally segmented into individual objects, achieving true 3D segmentation. This approach not only eliminates Gaussian-object misalignment issues in dynamic scenes but also accelerates the optimization process, as it eliminates the need for learning a separate language field. After optimization, a CLIP embedding is assigned to each object to enable open-vocabulary querying. Extensive experiments on various datasets demonstrate the effectiveness of our proposed method in both static and dynamic scenarios.
Instance segmentation is essential for augmented reality and virtual reality (AR/VR) as it enables precise object recognition and interaction, enhancing the integration of virtual and real-world elements for an immersive experience. However, the high computational overhead of segmentation limits its application on resource-constrained AR/VR devices, causing large processing latency and degrading user experience. In contrast to conventional scenarios, AR/VR users typically focus on only a few regions within their field of view before shifting perspective, allowing segmentation to be concentrated on gaze-specific areas. This insight drives the need for efficient segmentation methods that prioritize processing instance of interest, reducing computational load and enhancing real-time performance. In this paper, we present a foveated instance segmentation (FovealSeg) framework that leverages real-time user gaze data to perform instance segmentation exclusively on instance of interest, resulting in substantial computational savings. Evaluation results show that FSNet achieves an IoU of 0.56 on ADE20K and 0.54 on LVIS, notably outperforming the baseline. The code is available at https://github.com/SAI-
Purpose: The distribution of visceral adipose tissue (VAT) in cystectomy patients is indicative of the incidence of post-operative complications. Existing VAT segmentation methods for computed tomography (CT) employing intensity thresholding have limitations relating to inter-observer variability. Moreover, the difficulty in creating ground-truth masks limits the development of deep learning (DL) models for this task. This paper introduces a novel method for VAT prediction in pre-cystectomy CT, which is fully automated and does not require ground-truth VAT masks for training, overcoming aforementioned limitations. Methods: We introduce the Kernel density Enhanced VAT Segmentator ( KEVS), combining a DL semantic segmentation model, for multi-body feature prediction, with Gaussian kernel density estimation analysis of predicted subcutaneous adipose tissue to achieve accurate scan-specific predictions of VAT in the abdominal cavity. Uniquely for a DL pipeline, KEVS does not require ground-truth VAT masks. Results: We verify the ability of KEVS to accurately segment abdominal organs in unseen CT data and compare KEVS VAT segmentation predictions to existing state-of-the-art (SOTA) approaches in a dataset of 20 pre-cystectomy CT scans, collected from University College London Hospital (UCLH-Cyst), with expert ground-truth annotations. KEVS presents a 4.80% and 6.02% improvement in Dice Coefficient over the second best DL and thresholding-based VAT segmentation techniques respectively when evaluated on UCLH-Cyst. Conclusion: This research introduces KEVS; an automated, SOTA method for the prediction of VAT in pre-cystectomy CT which eliminates inter-observer variability and is trained entirely on open-source CT datasets which do not contain ground-truth VAT masks.
Semantic scene understanding is crucial for robotics and computer vision applications. In autonomous driving, 3D semantic segmentation plays an important role for enabling safe navigation. Despite significant advances in the field, the complexity of collecting and annotating 3D data is a bottleneck in this developments. To overcome that data annotation limitation, synthetic simulated data has been used to generate annotated data on demand. There is still however a domain gap between real and simulated data. More recently, diffusion models have been in the spotlight, enabling close-to-real data synthesis. Those generative models have been recently applied to the 3D data domain for generating scene-scale data with semantic annotations. Still, those methods either rely on image projection or decoupled models trained with different resolutions in a coarse-to-fine manner. Such intermediary representations impact the generated data quality due to errors added in those transformations. In this work, we propose a novel approach able to generate 3D semantic scene-scale data without relying on any projection or decoupled trained multi-resolution models, achieving more realistic semantic scene data generation compared to previous state-of-the-art methods. Besides improving 3D semantic scene-scale data synthesis, we thoroughly evaluate the use of the synthetic scene samples as labeled data to train a semantic segmentation network. In our experiments, we show that using the synthetic annotated data generated by our method as training data together with the real semantic segmentation labels, leads to an improvement in the semantic segmentation model performance. Our results show the potential of generated scene-scale point clouds to generate more training data to extend existing datasets, reducing the data annotation effort. Our code is available at https://github.com/PRBonn/3DiSS.
Mapping standing dead trees is critical for assessing forest health, monitoring biodiversity, and mitigating wildfire risks, for which aerial imagery has proven useful. However, dense canopy structures, spectral overlaps between living and dead vegetation, and over-segmentation errors limit the reliability of existing methods. This study introduces a hybrid postprocessing framework that refines deep learning-based tree segmentation by integrating watershed algorithms with adaptive filtering, enhancing boundary delineation, and reducing false positives in complex forest environments. Tested on high-resolution aerial imagery from boreal forests, the framework improved instance-level segmentation accuracy by 41.5% and reduced positional errors by 57%, demonstrating robust performance in densely vegetated regions. By balancing detection accuracy and over-segmentation artifacts, the method enabled the precise identification of individual dead trees, which is critical for ecological monitoring. The framework's computational efficiency supports scalable applications, such as wall-to-wall tree mortality mapping over large geographic regions using aerial or satellite imagery. These capabilities directly benefit wildfire risk assessment (identifying fuel accumulations), carbon stock estimation (tracking emissions from decaying biomass), and precision forestry (targeting salvage loggings). By bridging advanced remote sensing techniques with practical forest management needs, this work advances tools for large-scale ecological conservation and climate resilience planning.
The modernization of smart farming is a way to improve agricultural production efficiency, and improve the agricultural production environment. Although many large models have achieved high accuracy in the task of object recognition and segmentation, they cannot really be put into use in the farming industry due to their own poor interpretability and limitations in computational volume. In this paper, we built AnYue Shelduck Dateset, which contains a total of 1951 Shelduck datasets, and performed target detection and segmentation annotation with the help of professional annotators. Based on AnYue ShelduckDateset, this paper describes DuckProcessing, an efficient and powerful module for duck identification based on real shelduckfarms. First of all, using the YOLOv8 module designed to divide the mahjong between them, Precision reached 98.10%, Recall reached 96.53% and F1 score reached 0.95 on the test set. Again using the DuckSegmentation segmentation model, DuckSegmentation reached 96.43% mIoU. Finally, the excellent DuckSegmentation was used as the teacher model, and through knowledge distillation, Deeplabv3 r50 was used as the student model, and the final student model achieved 94.49% mIoU on the test set. The method provides a new way of thinking in practical sisal duck smart farming.