Search · four archives
Search · four archives
24 papers · ranked by Valyu relevance
Yu, Junwei, Darrell, Trevor + 2 more
We present UNSAMV2, a self-supervised framework that enables segmentation at arbitrary levels of granularity without human annotations. Unlike the supervised SAM [[24]] pipeline, which depends on human-labeled object masks, UNSAMV2 learns granularity directly from image statistics through a hierarchy-aware…
Lu, Kaixuan, Kaya, Mehmet Onurcan + 2 more
Video Instance Segmentation (VIS) faces significant annotation challenges due to its dual requirements of pixellevel masks and temporal consistency labels. While recent unsupervised methods like VideoCutLER eliminate optical flow dependencies through synthetic data, they remain constrained by the synthetic-to-real…
Zeyu Lei, Debin Zeng, Liangfang Zheng
This study addresses the challenge of organ-level instance segmentation in cotton point clouds, which arises from significant morphological variations and leaf occlusion across growth stages. To achieve high-precision leaf extraction, a hybrid framework integrating PointNeXt and DBSCAN is proposed. A dataset containing…
Ying Dai, Wei Yu Chen
— This paper presents a novel training-free framework for open-vocabulary image segmentation and object recognition (OVSR), which leverages EfficientNetB0, a convolutional neural network (CNN), for unsupervised segmentation and CLIP, a vision– language model, for open-vocabulary object recognition. The proposed…
Donghua Wu, Yi Tian, Fangqing Gao, Xiukun Wei + 2 more
The high operational velocities of high-speed trains present constraints on their onboard track intrusion detection systems for real-time capture and analysis, encompassing limited computational resources and motion image blurring. This emphasizes the critical necessity of track perimeter intrusion monitoring systems.…
Christoph Reich, Oliver Hahn, Nikita Araslanov, Laura Leal-Taixé + 3 more
Video panoptic segmentation (VPS) aims to jointly detect, segment, and track all objects while partitioning the video into semantically consistent regions. We introduce the task setting of unsupervised VPS, omitting any human supervision. Existing unsupervised scene understanding works mainly focused on image…
Clément Fernandes, Wojciech Pieczynski
- 1 Department Automobiles, Segula Matra Automotive, Zone d'activité Pissaloup, 8 Av. Jean d'Alembert, 78190 Trappes, France - 2 SAMOVAR, Télécom SudParis, Institut Polytechnique de Paris, 91120 Palaiseau, France - \* Correspondence: wojciech.pieczynski@telecom-sudparis.eu; Tel.: +33 1 60 76 44 25 - † This paper is an…
Ke Niu, Jiadong Guo, Ming Zhang, Zhongmin Guo + 4 more
Introduction Brain tissue segmentation in magnetic resonance imaging (MRI) is a fundamental step in quantitative neuroimaging and supports the analysis of structural brain alterations associated with aging. However, voxel-level annotation is expensive and labor-intensive, which limits the development of artificial…
Claudia Delprete, Domenico Buongiorno, Roberto Maria Scardigno, Elena Sibilano + 2 more
Introduction Colorectal cancer originates in most cases from polyps that progressively become malignant over time and colonoscopy offers a highly studied early diagnostic strategy to ensure a timely treatment plan. Automatic image segmentation of polyps, using intelligent supervised approaches, achieved good…
Xiaoying Zhang, Yu Hu, Yuzhuo Li, Zhoucan Nan + 2 more
Point cloud semantic segmentation remains challenging under extremely low annotation budgets due to inefficient utilization of sparse labels and sensitivity to data augmentation noise. To address this, we propose a dual-branch consistency learning (DBCL) framework featuring an EMA teacher for semi-supervised point…
Silvia L. Pintea, Jouke Dijkstra
This work focuses on per-video unsupervised action segmentation, which is of interest to applications where storing large datasets is either not possible, or nor permitted. We propose to segment videos by learning in deep kernel space, to approximate the underlying frame distribution, as closely as possible. To define…
Xiao Zhou, Shihong Wang, Weiguo Hu, Zhaohao Xie + 4 more
Small object localization is one of the most challenging tasks owing to the poor visual appearance and noisy representation caused by the intrinsic structure of small targets. Recent advances in localizing small objects are mainly dependent on regression-based counting approaches, which require considerable annotations…
Niall Rodgers
Palaeontology has seen widespread and growing use of machine learning to classify and analyse large datasets of fossils. However, palaeontology is a challenging field in which to apply machine learning. Datasets may be small or unlabelled, images may be complex and different from standard datasets and palaeontologists…
Sreenivas Bhattiprolu, Manita Toor, Sebastian Soyer
Modern biological imaging generates large, complex datasets that require scalable and reproducible image analysis methods. Deep learning has demonstrated strong performance on bioimage segmentation tasks, but training custom models has remained inaccessible to many researchers due to requirements for GPU…
Yuqian Yuan, Wentong Li, Zhaocheng Li, Yutong Lin + 5 more
In this paper, we introduce InstructSAM, a unified and streamlined framework designed for multi-instance segmentation under arbitrary instructions. We formulates instruction-driven instance segmentation as a set-structured query prediction problem and propose an explicit reasoning-to-instance query interface that…
Abrar Rahman Abir, Anik Saha, Ruwad Naswan, Md. Shamsuzzoha Bayzid
Accurate reconstruction of neural circuits from electron microscopy (EM) data is central to connectomics, yet modern datasets are now so large and heterogeneous that manual annotation and dataset-specific model retraining have become major challenges. While recent EM foundation models provide general visual…
Youqing Chen, Hang Liu, Lun Wang, Chen Chen + 7 more
Infrared images of caged chickens can provide valuable insights into their health status. Accurately detecting and segmenting individual chickens in these images is essential for effective health monitoring in large-scale chicken farming. However, the presence of obstacles such as cages, feeders, and drinkers can…
Romane Dubois, Lydia Bousset, Stéphane Jumel, Melen Leclerc + 2 more
Accurate segmentation of plant disease symptoms is essential for crop monitoring and phenotyping, yet it typically requires costly pixel-level annotations. Weakly supervised semantic segmentation (WSSS) alleviates this burden using image-level labels, but its performance depends on the quality of spatial priors such as…
Soham Mandal, José Guilherme de Almeida, Nickolas Papanikolaou, Trevor A Graham
Cell segmentation and phenotyping in histopathology samples are essential techniques applied across diagnostic and research workflows. However, annotation by human experts requires significant time and domain expertise and is affected by inter-observer variability. While multiple artificial intelligence methods have…
Authors not listed
The discovery of chemically novel or structurally anomalous metal-organic frameworks (MOFs) is essential for expanding reticular design space and enhancing dataset reliability. We present CHEM-AD (Chemically Unusual Metal–organic Frameworks via Autoencoder-based Detection), a label-free, CPU-efficient pipeline that…
Yichen He, Eleftherios Ioannou, Kathryn Harris, Gavin Thomas + 3 more
Fine-grained localisation of plumage regions is a prerequisite for computational analyses of avian colouration, patterning and visual traits in ecological and evolutionary research. Progress is limited by the scarcity of image resources with annotations aligned to biologically meaningful anatomical units: existing…
Authors not listed
Machine olfaction—the artificial replication of the sense of smell—faces significant challenges due to the absence of large, standardized training datasets. Unlike vision, language, and audio models, which benefit from extensive corpora such as ImageNet, GLUE, and AudioSet, olfaction lacks scaled equivalents and…
Authors not listed
Machine learning models are increasingly applied to heterogeneous materials datasets spanning different synthesis routes, measurement protocols, and structural classes. Although multi-task and representation-learning approaches are commonly used to improve predictive performance, the latent representations learned by…
Authors not listed
The integration of machine learning methods is transforming many areas of research by, for instance, accelerating molecular dynamics simulations and enabling improved prediction and optimization of chemical reactions. However, despite this progress, the adoption of data-driven approaches in atomic layer deposition…