Search Results for author:
Found 81 papers, 45 papers with code
Exploiting Temporal State Space Sharing for Video Semantic Segmentation
Video semantic segmentation (VSS) plays a vital role in understanding the temporal evolution of scenes.
CamSAM2: Segment Anything Accurately in Camouflaged Videos
Video camouflaged object segmentation (VCOS), aiming at segmenting camouflaged objects that seamlessly blend into their environment, is a fundamental vision task with various real-world applications.
Learning to segment anatomy and lesions from disparately labeled sources in brain MRI
Segmenting healthy tissue structures alongside lesions in brain Magnetic Resonance Images (MRI) remains a challenge for today's algorithms due to lesion-caused disruption of the anatomy and lack of jointly labeled training datasets, where both healthy tissues and lesions are labeled on the same images.
SceneSplat: Gaussian Splatting-based Scene Understanding with Vision-Language Pretraining
In order to power the proposed methods, we introduce SceneSplat-7K, the first large-scale 3DGS dataset for indoor scenes, comprising of 6868 scenes derived from 7 established datasets like ScanNet, Matterport3D, etc.
Generalized Few-shot 3D Point Cloud Segmentation with Vision-Language Model
In this work, we introduce a GFS-PCS framework that synergizes dense but noisy pseudo-labels from 3D VLMs with precise yet sparse few-shot samples to maximize the strengths of both, named GFS-VL.
Conformal forecasting for surgical instrument trajectory
In this work, we explore the application of standard conformal prediction and conformalized quantile regression to estimate uncertainty in forecasting surgical instrument motion, i. e., predicting direction and magnitude of surgical instruments' future motion.
CityLoc: 6DoF Pose Distributional Localization for Text Descriptions in Large-Scale Scenes with Gaussian Representation
Localizing textual descriptions within large-scale 3D scenes presents inherent ambiguities, such as identifying all traffic lights in a city.
Explicit and data-Efficient Encoding via Gradient Flow
However, relying on an encoder for inversion can lead to suboptimal representations, particularly limiting in physical sciences where precision is key.
Energy-Based Prior Latent Space Diffusion model for Reconstruction of Lumbar Vertebrae from Thick Slice MRI
We instead propose a latent space diffusion energy-based prior to leverage diffusion models, which exhibit high-quality image generation.
Diffusion-Based Semantic Segmentation of Lumbar Spine MRI Scans of Lower Back Pain Patients
The results showed that SpineSegDiff achieved comparable outperformed non-diffusion state-of-the-art models in the identification of degenerated IVDs.
Generalizable Single-Source Cross-modality Medical Image Segmentation via Invariant Causal Mechanisms
Single-source domain generalization (SDG) aims to learn a model from a single source domain that can generalize well on unseen target domains.
Multimodality Helps Few-Shot 3D Point Cloud Semantic Segmentation
Few-shot 3D point cloud segmentation (FS-PCS) aims at generalizing models to segment novel categories with minimal annotated support samples.
Few-shot 3D Point Cloud Semantic Segmentation
Point Cloud Segmentation
+1
When SAM2 Meets Video Camouflaged Object Segmentation: A Comprehensive Evaluation and Adaptation
This study presents a comprehensive study on SAM2's ability in VCOS.
Do Vision Foundation Models Enhance Domain Generalization in Medical Image Segmentation?
Our extensive experiments on multiple datasets, encompassing various anatomies and modalities, reveal that FMs, particularly with the HQHSAM decode head, improve domain generalization for medical image segmentation.
Image Segmentation in Foundation Model Era: A Survey
This survey seeks to fill this gap by providing a thorough review of cutting-edge research centered around FM-driven image segmentation.
ShapeSplat: A Large-scale Dataset of Gaussian Splats and Their Self-Supervised Pretraining
In particular, we show that (1) the distribution of the optimized GS centroids significantly differs from the uniformly sampled point cloud (used for initialization) counterpart; (2) this change in distribution results in degradation in classification but improvement in segmentation tasks when using only the centroids; (3) to leverage additional Gaussian parameters, we propose Gaussian feature grouping in a normalized feature space, along with splats pooling layer, offering a tailored solution to effectively group and embed similar Gaussians, which leads to notable improvement in finetuning tasks.
Implicit-Zoo: A Large-Scale Dataset of Neural Implicit Functions for 2D Images and 3D Scenes
Neural implicit functions have demonstrated significant importance in various areas such as computer vision, graphics.
Uncertainty modeling for fine-tuned implicit functions
In this paper, we introduce Dropsembles, a novel method for uncertainty estimation in tuned implicit functions.
Vision-Based Neurosurgical Guidance: Unsupervised Localization and Camera-Pose Prediction
Localizing oneself during endoscopic procedures can be problematic due to the lack of distinguishable textures and landmarks, as well as difficulties due to the endoscopic device such as a limited field of view and challenging lighting conditions.
QUBIQ: Uncertainty Quantification for Biomedical Image Segmentation Challenge
The challenge focuses on the uncertainty quantification of medical image segmentation which considers the omnipresence of inter-rater variability in imaging datasets.
Canonical normalizing flows for manifold learning
Alternatively, if a locally orthogonal and/or sparse basis is to be learned, here coined canonical intrinsic basis, it can serve in learning a more compact latent space representation.
Expert load matters: operating networks at high accuracy and low manual effort
In this paper, we argue that deep neural networks should be trained by taking into account both accuracy and expert load and, to that end, propose a new complementary loss function for classification that maximizes the area under this COC curve.
Quantification of Predictive Uncertainty via Inference-Time Sampling
Predictive variability due to data ambiguities has typically been addressed via construction of dedicated models with built-in probabilistic capabilities that are trained to predict uncertainty estimates as variables of interest.
Explicitly Minimizing the Blur Error of Variational Autoencoders
Variational autoencoders (VAEs) are powerful generative modelling methods, however they suffer from blurry generated samples and reconstructions compared to the images they have been trained on.
Live image-based neurosurgical guidance and roadmap generation using unsupervised embedding
With this motivation, we present a method for live image-only guidance leveraging a large data set of annotated neurosurgical videos. First, we report the performance of a deep learning-based object detection method, YOLO, on detecting anatomical structures in neurosurgical images.
InOR-Net: Incremental 3D Object Recognition Network for Point Cloud Representation
Moreover, they cannot explore which 3D geometric characteristics are essential to alleviate the catastrophic forgetting on old classes of 3D objects.
FedFA: Federated Feature Augmentation
To reach this goal, we propose FedFA to tackle federated learning from a distinct perspective of federated feature augmentation.
Unsupervised Superpixel Generation using Edge-Sparse Embedding
Partitioning an image into superpixels based on the similarity of pixels with respect to features such as colour or spatial location can significantly reduce data complexity and improve subsequent image processing tasks.
Neural Vector Fields for Implicit Surface Representation and Inference
With neural networks, several other variations and training principles have been proposed with the goal to represent all classes of shapes.
Rethinking Semantic Segmentation: A Prototype View
Prevalent semantic segmentation solutions, despite their different network designs (FCN based or attention based) and mask decoding strategies (parametric softmax based or pixel-query based), can be placed in one category, by considering the softmax weights or query vectors as learnable class prototypes.
Zero Pixel Directional Boundary by Vector Transform
One of the key problems in boundary detection is the label representation, which typically leads to class imbalance and, as a consequence, to thick boundaries that require non-differential post-processing steps to be thinned.
A Field of Experts Prior for Adapting Neural Networks at Test Time
We use 1D marginal distributions of a trained task CNN's features as experts in the FoE model.
Wiener Guided DIP for Unsupervised Blind Image Deconvolution
In addition, the image generator reproduces low-frequency features of the deconvolved image faster than that of a blurry image.
Local contrastive loss with pseudo-label based self-training for semi-supervised medical image segmentation
In this paper, we propose a local contrastive loss to learn good pixel level features useful for segmentation by exploiting semantic label information obtained from pseudo-labels of unlabeled images alongside limited annotated images.
ISNAS-DIP: Image-Specific Neural Architecture Search for Deep Image Prior
Our experiments show that image-specific metrics can reduce the search space to a small cohort of models, of which the best model outperforms current NAS approaches for image restoration.
Quality-Aware Memory Network for Interactive Volumetric Image Segmentation
The proposed network has two appealing characteristics: 1) The memory-augmented network offers the ability to quickly encode past segmentation information, which will be retrieved for the segmentation of other slices; 2) The quality assessment module enables the model to directly estimate the qualities of segmentation predictions, which allows an active learning paradigm where users preferentially label the lowest-quality slice for multi-round refinement.
Gradient flow encoding with distance optimization adaptive step size
In this work, we investigate a decoder-only method that uses gradient flow to encode data samples in the latent space.
Contrastive Learning of Single-Cell Phenotypic Representations for Treatment Classification
Learning robust representations to discriminate cell phenotypes based on microscopy images is important for drug discovery.
Constrained Optimization to Train Neural Networks on Critical and Under-Represented Classes
Such class imbalance is ubiquitous in clinical applications and very crucial to handle because the classes with fewer samples most often correspond to critical cases (e. g., cancer) where misclassifications can have severe consequences.
Exploring Cross-Image Pixel Contrast for Semantic Segmentation
Inspired by the recent advance in unsupervised contrastive representation learning, we propose a pixel-wise contrastive framework for semantic segmentation in the fully supervised setting.
Hyperspectral Image Super-Resolution with Spectral Mixup and Heterogeneous Datasets
With these contributions, our method is able to learn from heterogeneous datasets and lift the requirement for having a large amount of HD HSI training samples.
Probabilistic 3D surface reconstruction from sparse MRI information
Surface reconstruction from magnetic resonance (MR) imaging data is indispensable in medical image analysis and clinical research.
Sampling possible reconstructions of undersampled acquisitions in MR imaging
In this paper, we propose a method that instead returns multiple images which are possible under the acquisition model and the chosen prior to capture the uncertainty in the inversion process.
RevPHiSeg: A Memory-Efficient Neural Network for Uncertainty Quantification in Medical Image Segmentation
We incorporate the reversible blocks into a recently proposed architecture called PHiSeg that is developed for uncertainty quantification in medical image segmentation.
Joint reconstruction and bias field correction for undersampled MR imaging
To this end, we use an unsupervised learning based reconstruction algorithm as our basis and combine it with a N4-based bias field estimation method, in a joint optimization scheme.
Modelling the Distribution of 3D Brain MRI using a 2D Slice VAE
We propose a method to model 3D MR brain volumes distribution by combining a 2D slice VAE with a Gaussian model that captures the relationships between slices.
Semi-supervised Task-driven Data Augmentation for Medical Image Segmentation
In this work, we propose a novel task-driven data augmentation method for learning with limited labeled data where the synthetic data generator, is optimized for the segmentation task.
Contrastive learning of global and local features for medical image segmentation with limited annotations
In this work, we propose strategies for extending the contrastive learning framework for segmentation of volumetric medical images in the semi-supervised setting with limited annotations, by leveraging domain-specific and problem-specific cues.
Task-agnostic Out-of-Distribution Detection Using Kernel Density Estimation
The results demonstrate that the proposed method consistently achieves high OOD detection performance in both classification and segmentation tasks and improves state-of-the-art in almost all cases.
Unsupervised Lesion Detection via Image Restoration with a Normative Prior
In this work, we approach unsupervised lesion detection as an image restoration problem and propose a probabilistic model that uses a network-based prior as the normative distribution and detect lesions pixel-wise using MAP estimation.
Test-Time Adaptable Neural Networks for Robust Medical Image Segmentation
In medical image segmentation, this premise is violated when there is a mismatch between training and test images in terms of their acquisition details, such as the scanner model or the protocol.
Automated quantification of myocardial tissue characteristics from native T1 mapping using neural networks with Bayesian inference for uncertainty-based quality-control
The PHiSeg network and QC were validated against manual analysis on a cohort of the UK Biobank containing healthy subjects and chronic cardiomyopathy patients.
Machine Learning with Multi-Site Imaging Data: An Empirical Study on the Impact of Scanner Effects
This is an empirical study to investigate the impact of scanner effects when using machine learning on multi-site neuroimaging data.
A Partially Reversible U-Net for Memory-Efficient Volumetric Image Segmentation
Increasing network depth led to higher segmentation accuracy while growing the memory footprint only by a very small fraction, thanks to the partially reversible architecture.
PHiSeg: Capturing Uncertainty in Medical Image Segmentation
Segmentation of anatomical structures and pathologies is inherently ambiguous.
Medical Imaging with Deep Learning: MIDL 2019 -- Extended Abstract Track
This compendium gathers all the accepted extended abstracts from the Second International Conference on Medical Imaging with Deep Learning (MIDL 2019), held in London, UK, 8-10 July 2019.
Adversarial Augmentation for Enhancing Classification of Mammography Images
Supervised deep learning relies on the assumption that enough training data is available, which presents a problem for its application to several fields, like medical imaging.
Semi-Supervised and Task-Driven Data Augmentation
However, there is potential to improve the approach by (i) explicitly modeling deformation fields (non-affine spatial transformation) and intensity transformations and (ii) leveraging unlabelled data during the generative process.
Injecting and removing malignant features in mammography with CycleGAN: Investigation of an automated adversarial attack using neural networks
At the higher resolution, all radiologists showed significantly lower detection rate of cancer in the modified images (0. 77-0. 84 vs. 0. 59-0. 69, p=0. 008), however, they were now able to reliably detect modified images due to better visibility of artifacts (0. 92, 0. 92 and 0. 97).
Morpho-MNIST: Quantitative Assessment and Diagnostics for Representation Learning
Revealing latent structure in data is an active field of research, having introduced exciting technologies such as variational autoencoders and adversarial networks, and is essential to push machine learning towards unsupervised knowledge discovery.
Uncertainty Quantification in CNN-Based Surface Prediction Using Shape Priors
Surface reconstruction is a vital tool in a wide range of areas of medical image analysis and clinical research.
Combining Heterogeneously Labeled Datasets For Training Segmentation Networks
In this work we propose a cost function which allows integration of multiple datasets with heterogeneous label subsets into a joint training.
Iterative Interaction Training for Segmentation Editing Networks
Automatic segmentation has great potential to facilitate morphological measurements while simultaneously increasing efficiency.
Generative Adversarial Networks for MR-CT Deformable Image Registration
Performance for the abdominal region was similar to that of CT-MRI NMI registration (77. 4 vs. 78. 8%) when using 3D synthesizing MRIs (12 slices) and medium sized receptive fields for the discriminator.
Learning to Segment Medical Images with Scribble-Supervision Alone
We find that the networks trained on scribbles suffer from a remarkably small degradation in Dice of only 2. 9% (cardiac) and 4. 5% (prostate) with respect to a network trained on full annotations.
Deep Generative Models in the Real-World: An Open Challenge from Medical Imaging
In this paper, we explore the feasibility of using state-of-the-art auto-encoder-based deep generative models, such as variational and adversarial auto-encoders, for one such task: abnormality detection in medical imaging.
Unsupervised Detection of Lesions in Brain MRI using constrained adversarial auto-encoders
Lesion detection in brain Magnetic Resonance Images (MRI) remains a challenging task.
A Lifelong Learning Approach to Brain MR Segmentation Across Scanners and Protocols
We evaluate the method for brain structure segmentation in MR images.
Temporal Interpolation via Motion Field Prediction
Temporal interpolation of navigator slices an be used to reduce the number of navigator acquisitions without degrading specificity in stacking.
MR image reconstruction using deep density priors
Deep learning (DL) provides a powerful framework for extracting such information from existing image datasets, through learning, and then using it for reconstruction.
Visual Feature Attribution using Wasserstein GANs
Attributing the pixels of an input image to a certain category is an important and well-studied problem in computer vision, with applications ranging from weakly supervised localisation to understanding hidden effects in the data.
An Exploration of 2D and 3D Deep Learning Techniques for Cardiac MR Image Segmentation
Accurate segmentation of the heart is an important step towards evaluating cardiac function.
Sparse-then-Dense Alignment based 3D Map Reconstruction Method for Endoscopic Capsule Robots
Since the development of capsule endoscopcy technology, substantial progress were made in converting passive capsule endoscopes to robotic active capsule endoscopes which can be controlled by the doctor.
Deep EndoVO: A Recurrent Convolutional Neural Network (RCNN) based Visual Odometry Approach for Endoscopic Capsule Robots
Ingestible wireless capsule endoscopy is an emerging minimally invasive diagnostic technology for inspection of the GI tract and diagnosis of a wide range of diseases and pathologies.
A fully dense and globally consistent 3D map reconstruction approach for GI tract to enhance therapeutic relevance of the endoscopic capsule robot
In the gastrointestinal (GI) tract endoscopy field, ingestible wireless capsule endoscopy is emerging as a novel, minimally invasive diagnostic technology for inspection of the GI tract and diagnosis of a wide range of diseases and pathologies.
Magnetic-Visual Sensor Fusion based Medical SLAM for Endoscopic Capsule Robot
A reliable, real-time simultaneous localization and mapping (SLAM) method is crucial for the navigation of actively controlled capsule endoscopy robots.
A Non-Rigid Map Fusion-Based RGB-Depth SLAM Method for Endoscopic Capsule Robots
In this paper, we propose to our knowledge for the first time in literature a visual simultaneous localization and mapping (SLAM) method specifically developed for endoscopic capsule robots.
A Deep Learning Based 6 Degree-of-Freedom Localization Method for Endoscopic Capsule Robots
We present a robust deep learning based 6 degrees-of-freedom (DoF) localization system for endoscopic capsule robots.
Reconstructing Subject-Specific Effect Maps
Analyses on the ADNI dataset show that RSM can also improve correlation between subject-specific detections in cortical thickness data and non-imaging markers of Alzheimer's Disease (AD), such as the Mini Mental State Examination Score and Cerebrospinal Fluid amyloid-$\beta$ levels.
Approximate False Positive Rate Control in Selection Frequency for Random Forest
Random Forest has become one of the most popular tools for feature selection.
