Search · four archives
Search · four archives
23 papers · ranked by Valyu relevance
Cuong Manh Hoang
Instance segmentation is essential for numerous computer vision applications, including robotics, human-computer interaction, and autonomous driving. Currently, popular models bring impressive performance in instance segmentation by training with a large number of human annotations, which are costly to collect. For…
Dantong Niu, Xudong Wang, Xinyang Han, Long Lian + 2 more
Although CutLER provides high-quality instance segmentation masks without human annotations, the predicted masks are class-agnostic, and thus do not include semantic labels for each instance. Our method addresses this issue by grouping the detected instances with a clustering method. In this way, instances assigned to…
Andrii Zadaianchuk, Matthaeus Kleindessner, Yi Zhu, Francesco Locatello + 1 more
'Francesco Locatello' 'Thomas Brox'] In this paper, we show that recent advances in self-supervised representation learning enable unsupervised object discovery and semantic segmentation with a performance that matches the state of the field on supervised semantic segmentation 10 years ago. We propose a methodology…
Paul Engstler, Luke Melas-Kyriazi, Christian Rupprecht, Iro Laina
Self-supervised learning (SSL) can be used to solve complex visual tasks without human labels. Self-supervised representations encode useful semantic information about images, and as a result, they have already been used for tasks such as unsupervised semantic segmentation. In this paper, we investigate self-supervised…
Farnoosh Arefi, Amir M. Mansourian, Shohreh Kasaei, Yawen Lu
Recently, there has been growing interest in deep spectral methods for image localization and segmentation, influenced by traditional spectral segmentation approaches. These methods reframe the image decomposition process as a graph partitioning task by extracting features using self-supervised learning and utilizing…
Xudong Wang, Jingfeng Yang, Trevor Darrell
The Segmentation Anything Model (SAM) requires labor-intensive data labeling. We present Unsupervised SAM (UnSAM) for promptable and automatic wholeimage segmentation that does not require human annotations. UnSAM utilizes a divide-and-conquer strategy to "discover" the hierarchical structure of visual scenes. We first…
Zhenyu Wang, Yali Li, Shengjin Wang
Current instance segmentation methods rely heavily on pixel-level annotated images. The huge cost to obtain such fully-annotated images restricts the dataset scale and limits the performance. In this paper, we formally address semisupervised instance segmentation, where unlabeled images are employed to boost the…
Wu, Ziling, Moemeni, Armaghan + 1 more
Unsupervised object discovery (UOD) aims to detect and segment objects in 2D images without handcrafted annotations. Recent progress in self-supervised representation learning [9, [66]] has led to some success in UOD algorithms [21, 53, [69]]. However, the absence of ground truth provides existing UOD methods with two…
Bogdan Kochetov, Phoenix Bell, Paulo S. Garcia, Akram S. Shalaby + 12 more
Multiplexed imaging technologies have made it possible to interrogate complex tumor microenvironments at sub-cellular resolution within their native spatial context. However, proper quantification of this complexity requires the ability to easily and accurately segment cells into their sub-cellular compartments. Within…
Bogdan Kochetov, Phoenix Bell, Paulo S. Garcia, Akram S. Shalaby + 12 more
'Rebecca Raphael' 'Benjamin Raymond' 'Brian J. Leibowitz' 'Karen Schoedel' 'Rhonda M. Brand' 'Randall E. Brand' 'Jian Yu' 'Lin Zhang' 'Brenda Diergaarde' 'Robert E. Schoen' 'Aatur Singhi' 'Shikhar Uttam'] Multiplexed imaging technologies have made it possible to interrogate complex tumor microenvironments at…
Pranav Singh, Raviteja Chukkapalli, Shravan Chaudhari, Luoyao Chen + 4 more
'Mei Chen' 'Jinqian Pan' 'Craig Smuda' 'Jacopo Cirrone'] Advancements in clinical treatment are increasingly constrained by the limitations of supervised learning techniques, which depend heavily on large volumes of annotated data. The annotation process is not only costly but also demands substantial time from…
Kunal Chaturvedi, Ali Braytee, Jun Li, Mukesh Prasad + 2 more
'Shengzong Zhou' 'Jingsha He'] This paper proposes a novel self-supervised based Cut-and-Paste GAN to perform foreground object segmentation and generate realistic composite images without manual annotations. We accomplish this goal by a simple yet effective self-supervised approach coupled with the U-Net…
Shintaro Miyaki, Takashi Morikura, Shori Nishimoto, Yuta Tokuoka + 2 more
Semantic cell segmentation from microscopic images is essential for the quantitative evaluation of cell morphology. Although supervised deep-learning-based models offer accurate segmentation, their performance degrades for unknown cell types. To address this problem, unsupervised domain adaptation methods based on…
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…
Paulo Victor dos Santos, Marcella Scoczynski Ribeiro Martins, Solange Amorim Nogueira, Cristhiane Gonçalves + 3 more
'Solange Amorim Nogueira' 'Cristhiane Gonçalves' 'Rafael Maffei Loureiro' 'Wesley Pacheco Calixto' 'Ihssan S. Masad'] This article presents an unsupervised method for segmenting brain computed tomography scans. The proposed methodology involves image feature extraction and application of similarity and continuity…
Paul W. Sweeney, Lina Hacker, Thierry L. Lefebvre, Emma L. Brown + 2 more
Mesoscopic photoacoustic imaging (PAI) enables label-free visualisation of vascular networks in tissue at high contrast and resolution. The segmentation of vascular networks from 3D PAI data and interpretation of their meaning in the context of physiological and pathological processes is a crucial but time consuming…
Samuel Bourgeat, Fani Derveni, Victoire Gamblin, Ece Naz Bilgiç + 6 more
Biological systems are three-dimensional and complex. Today, images of biological structures can be acquired using different imaging technologies and at increasing resolutions. However, identifying relevant structural features in three-dimensional (3D) images remains a significant challenge. 3D image segmentation is…
Yanchao Zhang, Hao Zhai, Jinyue Guo, Jing Liu + 1 more
Semi-supervised learning holds promise for cost-effective neuron segmentation in Electron Microscopy (EM) volumes. This technique fully leverages extensive unlabeled data to regularize supervised training for robust predictions. However, diverse neuronal patterns and limited annotation budgets may lead to distribution…
Rama El-khawaldeh, Mason Guy, Finn Bork, Nina Taherimakhsousi + 6 more
This work presents a generalizable computer vision (CV) and machine learning model that is used for automated real-time monitoring and control of a diverse array of workup processes. Our system simultaneously monitors multiple physical parameters (e.g., liquid level, homogeneity, turbidity, solid, residue, and color)…
Jens F. Tillmann, Alexander I. Hsu, Martin K. Schwarz, Eric A. Yttri
To identify and extract naturalistic behavior, two schools of methods have become popular: supervised and unsupervised. Each approach carries its own strengths and weaknesses, which the user must weigh in on their decision. Here, a new active learning platform, A-SOiD, blends these strengths and, in doing so, overcomes…
Authors not listed
X-ray diffraction (XRD) is an immediate and powerful characterization technique that provides detailed information on the lattice structure and long-range order in crystalline materials. In recent decades, the quality and quantity of available crystal structure data has exploded, in large part due to the advent of…
Alexander E. Siemenn, Eunice Aissi, Fang Sheng, Armi Tiihonen + 3 more
In materials research, the task of characterizing hundreds of different materials traditionally requires equally many human hours spent measuring samples one by one. We demonstrate that with the integration of computer vision into this material research workflow, many of these tasks can be automated, significantly…
Authors not listed
The analysis of nonadiabatic molecular dynamics (NAMD) data presents significant challenges due to its high dimensionality and complexity. To address these issues, we introduce ULaMDyn, a Python-based, open-source package designed to automate the unsupervised analysis of large datasets generated by NAMD simulations.…