Search Results for author:
Found 63 papers, 18 papers with code
Unsupervised Low-light Image Enhancement with Lookup Tables and Diffusion Priors
As diffusion models are sensitive to noise, diffusion priors are introduced to achieve high-performance noise suppression.
Bootstrap Segmentation Foundation Model under Distribution Shift via Object-Centric Learning
Foundation models have made incredible strides in achieving zero-shot or few-shot generalization, leveraging prompt engineering to mimic the problem-solving approach of human intelligence.
Mixstyle-Entropy: Domain Generalization with Causal Intervention and Perturbation
In this paper, we propose a novel and holistic framework based on causality, named InPer, designed to enhance model generalization by incorporating causal intervention during training and causal perturbation during testing.
AGLLDiff: Guiding Diffusion Models Towards Unsupervised Training-free Real-world Low-light Image Enhancement
Existing low-light image enhancement (LIE) methods have achieved noteworthy success in solving synthetic distortions, yet they often fall short in practical applications.
Unity in Diversity: Multi-expert Knowledge Confrontation and Collaboration for Generalizable Vehicle Re-identification
To solve this complex and common problem, this paper proposes the two-stage Multi-expert Knowledge Confrontation and Collaboration (MiKeCoCo) method, which incorporates multiple experts with unique perspectives into Contrastive Language-Image Pretraining (CLIP) and fully leverages high-level semantic knowledge for comprehensive feature representation.
InstantSplat: Sparse-view SfM-free Gaussian Splatting in Seconds
InstantSplat adopts a self-supervised framework that bridges the gap between 2D images and 3D representations using Gaussian Bundle Adjustment (GauBA) and can be optimized in an end-to-end manner.
Data-driven Modeling and Inference for Bayesian Gaussian Process ODEs via Double Normalizing Flows
Bayesian inference for these models has been extensively studied and applied in tasks such as time series prediction.
SRCD: Semantic Reasoning with Compound Domains for Single-Domain Generalized Object Detection
In this paper, we introduce Semantic Reasoning with Compound Domains (SRCD) for Single-DGOD.
Ranked #2 on
Robust Object Detection
on DWD
MASNet: A Robust Deep Marine Animal Segmentation Network
Specifically, we design a new data augmentation strategy to randomly change the degradation and camouflage attributes of the original objects.
Ranked #3 on
Image Segmentation
on RMAS
Learning a Simple Low-Light Image Enhancer From Paired Low-Light Instances
Those solutions, however, often fail in revealing image details due to the limited information in a single image and the poor adaptability of handcrafted priors.
Ranked #3 on
Low-Light Image Enhancement
on VV
Hint-dynamic Knowledge Distillation
Knowledge Distillation (KD) transfers the knowledge from a high-capacity teacher model to promote a smaller student model.
Uncertainty Inspired Underwater Image Enhancement
After that, we adopt a consensus process to predict a deterministic result based on a set of samples from the distribution.
Knowledge Condensation Distillation
Knowledge Distillation (KD) transfers the knowledge from a high-capacity teacher network to strengthen a smaller student.
Relation Matters: Foreground-aware Graph-based Relational Reasoning for Domain Adaptive Object Detection
However, both the global and local alignment approaches fail to capture the topological relations among different foreground objects as the explicit dependencies and interactions between and within domains are neglected.
A Closer Look at Personalization in Federated Image Classification
This paper shows that it is possible to achieve flexible personalization after the convergence of the global model by introducing representation learning.
AFSC: Adaptive Fourier Space Compression for Anomaly Detection
Data augmentation based methods construct pseudo-healthy images by "pasting" fake lesions on real healthy ones, and a network is trained to predict healthy images in a supervised manner.
Acoustic-Net: A Novel Neural Network for Sound Localization and Quantification
Acoustic source localization has been applied in different fields, such as aeronautics and ocean science, generally using multiple microphones array data to reconstruct the source location.
Harmonizing Pathological and Normal Pixels for Pseudo-healthy Synthesis
Comprehensive experiments on the T2 modality of BraTS demonstrate that the proposed method substantially outperforms the state-of-the-art methods.
Self-Verification in Image Denoising
Specifically, we treat the output of the network as a ``prior'' that we denoise again after ``re-noising''.
Domain Generalization on Medical Imaging Classification using Episodic Training with Task Augmentation
In this paper, we propose a novel DG scheme of episodic training with task augmentation on medical imaging classification.
Hierarchical Deep Network with Uncertainty-aware Semi-supervised Learning for Vessel Segmentation
In this paper, to address the above issues, we propose a hierarchical deep network where an attention mechanism localizes the low-contrast capillary regions guided by the whole vessels, and enhance the spatial activation in those areas for the sub-type vessels.
I3Net: Implicit Instance-Invariant Network for Adapting One-Stage Object Detectors
Motivated by this, we propose an Implicit Instance-Invariant Network (I3Net), which is tailored for adapting one-stage detectors and implicitly learns instance-invariant features via exploiting the natural characteristics of deep features in different layers.
Consistent Posterior Distributions under Vessel-Mixing: A Regularization for Cross-Domain Retinal Artery/Vein Classification
In this paper, we propose a novel vessel-mixing based consistency regularization framework, for cross-domain learning in retinal A/V classification.
Unsupervised Anomaly Segmentation using Image-Semantic Cycle Translation
In this paper, to alleviate this issue, we introduce the semantic space of healthy anatomy in the process of modeling healthy-data distribution.
Twice Mixing: A Rank Learning based Quality Assessment Approach for Underwater Image Enhancement
Our approach, termed Twice Mixing, is motivated by the observation that a mid-quality image can be generated by mixing a high-quality image with its low-quality version.
TRAR: Routing the Attention Spans in Transformer for Visual Question Answering
Due to the superior ability of global dependency modeling, Transformer and its variants have become the primary choice of many vision-and-language tasks.
Dual Bipartite Graph Learning: A General Approach for Domain Adaptive Object Detection
Domain Adaptive Object Detection (DAOD) relieves the reliance on large-scale annotated data by transferring the knowledge learned from a labeled source domain to a new unlabeled target domain.
Few-shot Medical Image Segmentation using a Global Correlation Network with Discriminative Embedding
Motivated by the spatial consistency and regularity in medical images, we developed an efficient global correlation module to capture the correlation between a support and query image and incorporate it into the deep network called global correlation network.
Adaptive noise imitation for image denoising
Coupling the noisy data output from ADANI with the corresponding ground-truth, a denoising CNN is then trained in a fully-supervised manner.
A Teacher-Student Framework for Semi-supervised Medical Image Segmentation From Mixed Supervision
We further proposed a localization branch realized via an aggregation of high-level features in a deep decoder to predict locations of organ and lesion, which enriches student segmentor with precise localization information.
Hard Class Rectification for Domain Adaptation
Second, we further consider that the predictions of target samples belonging to the hard class are vulnerable to perturbations.
Semi-supervised Domain Adaptation
Unsupervised Domain Adaptation
Multi-Task Neural Networks with Spatial Activation for Retinal Vessel Segmentation and Artery/Vein Classification
In this paper, we propose a multi-task deep neural network with spatial activation mechanism that is able to segment full retinal vessel, artery and vein simultaneously, without the pre-requirement of vessel segmentation.
Cardiac Segmentation on Late Gadolinium Enhancement MRI: A Benchmark Study from Multi-Sequence Cardiac MR Segmentation Challenge
In addition, the paired MS-CMR images could enable algorithms to combine the complementary information from the other sequences for the segmentation of LGE CMR.
Harmonizing Transferability and Discriminability for Adapting Object Detectors
Recent advances in adaptive object detection have achieved compelling results in virtue of adversarial feature adaptation to mitigate the distributional shifts along the detection pipeline.
A Real-time Global Inference Network for One-stage Referring Expression Comprehension
Referring Expression Comprehension (REC) is an emerging research spot in computer vision, which refers to detecting the target region in an image given an text description.
Noise2Blur: Online Noise Extraction and Denoising
Using the new image pair, the denoising network learns to generate clean and high-quality images from noisy observations.
Learning Rate Dropout
The uncertainty of the descent path helps the model avoid saddle points and bad local minima.
Multi-sequence Cardiac MR Segmentation with Adversarial Domain Adaptation Network
Automatic and accurate segmentation of the ventricles and myocardium from multi-sequence cardiac MRI (CMR) is crucial for the diagnosis and treatment management for patients suffering from myocardial infarction (MI).
Uncertainty-Guided Domain Alignment for Layer Segmentation in OCT Images
Automatic and accurate segmentation for retinal and choroidal layers of Optical Coherence Tomography (OCT) is crucial for detection of various ocular diseases.
Unsupervised Adversarial Graph Alignment with Graph Embedding
In this paper, we propose an Unsupervised Adversarial Graph Alignment (UAGA) framework to learn a cross-graph alignment between two embedding spaces of different graphs in a fully unsupervised fashion (\emph{i. e.,} no existing anchor links and no users' personal profile or attribute information is available).
Look More Than Once: An Accurate Detector for Text of Arbitrary Shapes
Previous scene text detection methods have progressed substantially over the past years.
Rain O'er Me: Synthesizing real rain to derain with data distillation
We present a supervised technique for learning to remove rain from images without using synthetic rain software.
A^2Net: Adjacent Aggregation Networks for Image Raindrop Removal
Existing methods for single images raindrop removal either have poor robustness or suffer from parameter burdens.
Progressive Feature Alignment for Unsupervised Domain Adaptation
Unsupervised domain adaptation (UDA) transfers knowledge from a label-rich source domain to a fully-unlabeled target domain.
Ranked #8 on
Domain Adaptation
on SVHN-to-MNIST
A Deep Tree-Structured Fusion Model for Single Image Deraining
We propose a simple yet effective deep tree-structured fusion model based on feature aggregation for the deraining problem.
An Adversarial Learning Approach to Medical Image Synthesis for Lesion Detection
Being able to provide a "normal" counterpart to a medical image can provide useful side information for medical imaging tasks like lesion segmentation or classification validated by our experiments.
Lightweight Pyramid Networks for Image Deraining
In this paper, we propose a lightweight pyramid of networks (LPNet) for single image deraining.
A Deeply-Recursive Convolutional Network for Crowd Counting
The estimation of crowd count in images has a wide range of applications such as video surveillance, traffic monitoring, public safety and urban planning.
Joint CS-MRI Reconstruction and Segmentation with a Unified Deep Network
The need for fast acquisition and automatic analysis of MRI data is growing in the age of big data.
Residual-Guide Feature Fusion Network for Single Image Deraining
Single image rain streaks removal is extremely important since rainy images adversely affect many computer vision systems.
A Deep Information Sharing Network for Multi-contrast Compressed Sensing MRI Reconstruction
In multi-contrast magnetic resonance imaging (MRI), compressed sensing theory can accelerate imaging by sampling fewer measurements within each contrast.
A Segmentation-aware Deep Fusion Network for Compressed Sensing MRI
In this paper, we proposed a segmentation-aware deep fusion network called SADFN for compressed sensing MRI.
A Divide-and-Conquer Approach to Compressed Sensing MRI
Compressed sensing (CS) theory assures us that we can accurately reconstruct magnetic resonance images using fewer k-space measurements than the Nyquist sampling rate requires.
A Deep Error Correction Network for Compressed Sensing MRI
Existing CS-MRI algorithms can serve as the template module for guiding the reconstruction.
PanNet: A Deep Network Architecture for Pan-Sharpening
We incorporate domain-specific knowledge to design our PanNet architecture by focusing on the two aims of the pan-sharpening problem: spectral and spatial preservation.
High Efficient Reconstruction of Single-shot T2 Mapping from OverLapping-Echo Detachment Planar Imaging Based on Deep Residual Network
After the ResNet was trained, it was applied to reconstruct the T2 mapping from simulation and in vivo human brain data.
Removing Rain From Single Images via a Deep Detail Network
We propose a new deep network architecture for removing rain streaks from individual images based on the deep convolutional neural network (CNN).
Clearing the Skies: A deep network architecture for single-image rain removal
We introduce a deep network architecture called DerainNet for removing rain streaks from an image.
Ranked #11 on
Single Image Deraining
on Test100
(SSIM metric)
A Weighted Variational Model for Simultaneous Reflectance and Illumination Estimation
We propose a weighted variational model to estimate both the reflectance and the illumination from an observed image.
Saliency Detection with Spaces of Background-based Distribution
In this letter, an effective image saliency detection method is proposed by constructing some novel spaces to model the background and redefine the distance of the salient patches away from the background.
Pan-Sharpening With a Hyper-Laplacian Penalty
Our objective incorporates the L1/2-norm in a way that can leverage recent computationally efficient methods, and L1 for which the alternating direction method of multipliers can be used.
Bayesian Nonparametric Dictionary Learning for Compressed Sensing MRI
The size of the dictionary and the patch-specific sparsity pattern are inferred from the data, in addition to other dictionary learning variables.
