Search Results for author:
Found 31 papers, 14 papers with code
MiM: Mask in Mask Self-Supervised Pre-Training for 3D Medical Image Analysis
We further scale up the MiM to large pre-training datasets with more than 10k volumes, showing that large-scale pre-training can further enhance the performance of downstream tasks.
Design as Desired: Utilizing Visual Question Answering for Multimodal Pre-training
In this work, we leverage descriptions in medical reports to design multi-granular question-answer pairs associated with different diseases, which assist the framework in pre-training without requiring extra annotations from experts.
Progressive Frequency-Aware Network for Laparoscopic Image Desmoking
Laparoscopic surgery offers minimally invasive procedures with better patient outcomes, but smoke presence challenges visibility and safety.
Shifting More Attention to Breast Lesion Segmentation in Ultrasound Videos
We also devise a localization-based contrastive loss to reduce the lesion location distance between neighboring video frames within the same video and enlarge the location distances between frames from different ultrasound videos.
DISCO: Distribution-Aware Calibration for Object Detection with Noisy Bounding Boxes
Large-scale well-annotated datasets are of great importance for training an effective object detector.
Semi-Supervised Semantic Segmentation With Region Relevance
The most common approach is to generate pseudo-labels for unlabeled images to augment the training data.
Learning Robust Medical Image Segmentation from Multi-source Annotations
Learning segmentation networks from multi-source annotations remains a challenge due to the uncertainties brought by the variance of annotations and the quality of images.
Masked Image Training for Generalizable Deep Image Denoising
To address this issue, we present a novel approach to enhance the generalization performance of denoising networks, known as masked training.
FECANet: Boosting Few-Shot Semantic Segmentation with Feature-Enhanced Context-Aware Network
Few-shot semantic segmentation is the task of learning to locate each pixel of the novel class in the query image with only a few annotated support images.
Ranked #2 on
Few-Shot Semantic Segmentation
on COCO-20i (10-shot)
RepMode: Learning to Re-parameterize Diverse Experts for Subcellular Structure Prediction
In biological research, fluorescence staining is a key technique to reveal the locations and morphology of subcellular structures.
Intra-Modal Constraint Loss For Image-Text Retrieval
Cross-modal retrieval has drawn much attention in both computer vision and natural language processing domains.
Saliency Guided Inter- and Intra-Class Relation Constraints for Weakly Supervised Semantic Segmentation
Specifically, we propose a saliency guided class-agnostic distance module to pull the intra-category features closer by aligning features to their class prototypes.
Acknowledging the Unknown for Multi-label Learning with Single Positive Labels
Due to the difficulty of collecting exhaustive multi-label annotations, multi-label datasets often contain partial labels.
GeoBi-GNN: Geometry-aware Bi-domain Mesh Denoising via Graph Neural Networks
For the first time, we optimize both positions and normals (i. e., dual domains) in a unified framework of GNN, and show the powerful inter-coordination between the dual domains.
PNP: Robust Learning From Noisy Labels by Probabilistic Noise Prediction
Label noise has been a practical challenge in deep learning due to the strong capability of deep neural networks in fitting all training data.
Hepatic vessel segmentation based on 3D swin-transformer with inductive biased multi-head self-attention
In practice, we introduce the voxel-wise embedding rather than patch-wise embedding to locate precise liver vessel voxels, and adopt multi-scale convolutional operators to gain local spatial information.
Flattening Sharpness for Dynamic Gradient Projection Memory Benefits Continual Learning
The backpropagation networks are notably susceptible to catastrophic forgetting, where networks tend to forget previously learned skills upon learning new ones.
Ammonia-induced Calcium Phosphate Nanostructure: A Potential Assay for Studying Osteoporosis and Bone Metastasis
To demon-strate the application in studying bone metastasis, we delivered PC3 prostate cancer conditioned medium and confirmed that both the differentiation of monocytes into osteoclasts and the osteoclastic resorption of the calcium phosphate coating were significantly enhanced.
Semantically Meaningful Class Prototype Learning for One-Shot Image Semantic Segmentation
Then we utilize the fused prototype to guide the final segmentation of the query image.
Globular structure of the hypermineralized tissue in human femoral neck
Transmission electron microscopy showed the apatite inside globules were poorly crystalline, while those at the boundaries between the globules had well-defined lattice structure with crystallinity similar to the apatite mineral in lamellar bone.
Instance Shadow Detection
Then, we pair up the predicted shadow and object instances, and match them with the predicted shadow-object associations to generate the final results.
Ranked #2 on
Instance Shadow Detection
on SOBA
Revisiting Shadow Detection: A New Benchmark Dataset for Complex World
Shadow detection in general photos is a nontrivial problem, due to the complexity of the real world.
Group Sparsity Residual with Non-Local Samples for Image Denoising
Inspired by group-based sparse coding, recently proposed group sparsity residual (GSR) scheme has demonstrated superior performance in image processing.
Grassmannian Manifold Optimization Assisted Sparse Spectral Clustering
Spectral Clustering is one of pioneered clustering methods in machine learning and pattern recognition field.
Group-based Sparse Representation for Image Compressive Sensing Reconstruction with Non-Convex Regularization
In this paper, a group-based sparse representation method with non-convex regularization (GSR-NCR) for image CS reconstruction is proposed.
Non-Convex Weighted Lp Nuclear Norm based ADMM Framework for Image Restoration
Since the matrix formed by nonlocal similar patches in a natural image is of low rank, the nuclear norm minimization (NNM) has been widely used in various image processing studies.
Non-Convex Weighted Lp Minimization based Group Sparse Representation Framework for Image Denoising
Nonlocal image representation or group sparsity has attracted considerable interest in various low-level vision tasks and has led to several state-of-the-art image denoising techniques, such as BM3D, LSSC.
Group Sparsity Residual Constraint for Image Denoising
Unlike the conventional group-based sparse representation denoising methods, two kinds of prior, namely, the NSS priors of noisy and pre-filtered images, are used in GSRC.
Image denoising using group sparsity residual and external nonlocal self-similarity prior
To boost the performance of image denoising, the concept of group sparsity residual is proposed, and thus the problem of image denoising is transformed into one that reduces the group sparsity residual.
Analyzing the group sparsity based on the rank minimization methods
Then, we prove that group-based sparse coding is equivalent to the rank minimization problem, and thus the sparse coefficient of each group is measured by estimating the singular values of each group.
Image denoising via group sparsity residual constraint
Group sparsity has shown great potential in various low-level vision tasks (e. g, image denoising, deblurring and inpainting).
