Search Results for author:
Found 67 papers, 28 papers with code
ReDro: Efficiently Learning Large-sized SPD Visual Representation
When learning this representation in deep networks, eigen-decomposition of covariance matrix is usually needed for a key step called matrix normalisation.
AWF: Adaptive Weight Fusion for Enhanced Class Incremental Semantic Segmentation
Class Incremental Semantic Segmentation (CISS) aims to mitigate catastrophic forgetting by maintaining a balance between previously learned and newly introduced knowledge.
Class-Incremental Semantic Segmentation
Knowledge Distillation
KARGEN: Knowledge-enhanced Automated Radiology Report Generation Using Large Language Models
Harnessing the robust capabilities of Large Language Models (LLMs) for narrative generation, logical reasoning, and common-sense knowledge integration, this study delves into utilizing LLMs to enhance automated radiology report generation (R2Gen).
PoinTramba: A Hybrid Transformer-Mamba Framework for Point Cloud Analysis
In this study, we introduce PoinTramba, a pioneering hybrid framework that synergies the analytical power of Transformer with the remarkable computational efficiency of Mamba for enhanced point cloud analysis.
LighTDiff: Surgical Endoscopic Image Low-Light Enhancement with T-Diffusion
We further introduce a Chroma Balancer (CB) to mitigate this issue.
Group-aware Parameter-efficient Updating for Content-Adaptive Neural Video Compression
Content-adaptive compression is crucial for enhancing the adaptability of the pre-trained neural codec for various contents.
MRScore: Evaluating Radiology Report Generation with LLM-based Reward System
This paper introduces MRScore, an automatic evaluation metric tailored for radiology report generation by leveraging Large Language Models (LLMs).
Roll With the Punches: Expansion and Shrinkage of Soft Label Selection for Semi-supervised Fine-Grained Learning
While semi-supervised learning (SSL) has yielded promising results, the more realistic SSL scenario remains to be explored, in which the unlabeled data exhibits extremely high recognition difficulty, e. g., fine-grained visual classification in the context of SSL (SS-FGVC).
Fine-Grained Image Classification
Semi-Supervised Image Classification
MedXChat: A Unified Multimodal Large Language Model Framework towards CXRs Understanding and Generation
Multimodal Large Language Models (MLLMs) have shown success in various general image processing tasks, yet their application in medical imaging is nascent, lacking tailored models.
Alternate Diverse Teaching for Semi-supervised Medical Image Segmentation
To mitigate the confirmation bias from the diverse supervision, the core of AD-MT lies in two proposed modules: the Random Periodic Alternate (RPA) Updating Module and the Conflict-Combating Module (CCM).
Clean Label Disentangling for Medical Image Segmentation with Noisy Labels
Current methods focusing on medical image segmentation suffer from incorrect annotations, which is known as the noisy label issue.
Progressive Classifier and Feature Extractor Adaptation for Unsupervised Domain Adaptation on Point Clouds
In this work, we propose a novel framework that deeply couples the classifier and feature extractor adaption for 3D UDA, dubbed Progressive Classifier and Feature Extractor Adaptation (PCFEA).
UFDA: Universal Federated Domain Adaptation with Practical Assumptions
Conventional Federated Domain Adaptation (FDA) approaches usually demand an abundance of assumptions, which makes them significantly less feasible for real-world situations and introduces security hazards.
GPT4Video: A Unified Multimodal Large Language Model for lnstruction-Followed Understanding and Safety-Aware Generation
While the recent advances in Multimodal Large Language Models (MLLMs) constitute a significant leap forward in the field, these models are predominantly confined to the realm of input-side multimodal comprehension, lacking the capacity for multimodal content generation.
A Systematic Evaluation of GPT-4V's Multimodal Capability for Medical Image Analysis
This work conducts an evaluation of GPT-4V's multimodal capability for medical image analysis, with a focus on three representative tasks of radiology report generation, medical visual question answering, and medical visual grounding.
Understanding Masked Autoencoders From a Local Contrastive Perspective
Masked AutoEncoder (MAE) has revolutionized the field of self-supervised learning with its simple yet effective masking and reconstruction strategies.
R2GenGPT: Radiology Report Generation with Frozen LLMs
First, it attains state-of-the-art (SOTA) performance by training only the lightweight visual alignment module while freezing all the parameters of LLM.
Enhancing Sample Utilization through Sample Adaptive Augmentation in Semi-Supervised Learning
Sample adaptive augmentation (SAA) is proposed for this stated purpose and consists of two modules: 1) sample selection module; 2) sample augmentation module.
A survey on efficient vision transformers: algorithms, techniques, and performance benchmarking
Summarizing, this paper firstly mathematically defines the strategies used to make Vision Transformer efficient, describes and discusses state-of-the-art methodologies, and analyzes their performances over different application scenarios.
Neural Vector Fields: Generalizing Distance Vector Fields by Codebooks and Zero-Curl Regularization
Recent neural networks based surface reconstruction can be roughly divided into two categories, one warping templates explicitly and the other representing 3D surfaces implicitly.
Rethinking Data Perturbation and Model Stabilization for Semi-supervised Medical Image Segmentation
Studies on semi-supervised medical image segmentation (SSMIS) have seen fast progress recently.
Contrastive Diffusion Model with Auxiliary Guidance for Coarse-to-Fine PET Reconstruction
To obtain high-quality positron emission tomography (PET) scans while reducing radiation exposure to the human body, various approaches have been proposed to reconstruct standard-dose PET (SPET) images from low-dose PET (LPET) images.
Towards Semi-supervised Learning with Non-random Missing Labels
Semi-supervised learning (SSL) tackles the label missing problem by enabling the effective usage of unlabeled data.
Automatic Radiology Report Generation by Learning with Increasingly Hard Negatives
At each iteration, conditioned on a given set of hard negative reports, image and report features are learned as usual by minimising the loss functions related to report generation.
Learning Partial Correlation based Deep Visual Representation for Image Classification
Our work obtains a partial correlation based deep visual representation and mitigates the small sample problem often encountered by covariance matrix estimation in CNN.
METransformer: Radiology Report Generation by Transformer with Multiple Learnable Expert Tokens
In the encoder, each expert token interacts with both vision tokens and other expert tokens to learn to attend different image regions for image representation.
Q2ATransformer: Improving Medical VQA via an Answer Querying Decoder
To bridge this gap, in this paper, we propose a new Transformer based framework for medical VQA (named as Q2ATransformer), which integrates the advantages of both the classification and the generation approaches and provides a unified treatment for the close-end and open-end questions.
Task-Oriented Multi-Modal Mutual Leaning for Vision-Language Models
A contrastive loss is employed to align such augmented text and image representations on downstream tasks.
Neural Vector Fields: Implicit Representation by Explicit Learning
Deep neural networks (DNNs) are widely applied for nowadays 3D surface reconstruction tasks and such methods can be further divided into two categories, which respectively warp templates explicitly by moving vertices or represent 3D surfaces implicitly as signed or unsigned distance functions.
Conflict-Based Cross-View Consistency for Semi-Supervised Semantic Segmentation
In this work, we propose a new conflict-based cross-view consistency (CCVC) method based on a two-branch co-training framework which aims at enforcing the two sub-nets to learn informative features from irrelevant views.
Bridging Synthetic and Real Images: a Transferable and Multiple Consistency aided Fundus Image Enhancement Framework
Moreover, we also propose a novel multi-stage multi-attention guided enhancement network (MAGE-Net) as the backbones of our teacher and student network.
Learning Spatial-context-aware Global Visual Feature Representation for Instance Image Retrieval
To this end, we propose a novel feature learning framework for instance image retrieval, which embeds local spatial context information into the learned global feature representations.
Augmentation Matters: A Simple-yet-Effective Approach to Semi-supervised Semantic Segmentation
Differently, in this work, we follow a standard teacher-student framework and propose AugSeg, a simple and clean approach that focuses mainly on data perturbations to boost the SSS performance.
Instance-specific and Model-adaptive Supervision for Semi-supervised Semantic Segmentation
Relying on the model's performance, iMAS employs a class-weighted symmetric intersection-over-union to evaluate quantitative hardness of each unlabeled instance and supervises the training on unlabeled data in a model-adaptive manner.
A Medical Semantic-Assisted Transformer for Radiographic Report Generation
Automated radiographic report generation is a challenging cross-domain task that aims to automatically generate accurate and semantic-coherence reports to describe medical images.
Instance Image Retrieval by Learning Purely From Within the Dataset
Although achieving promising results, this approach is restricted by two issues: 1) the domain gap between benchmark datasets and the dataset of a given retrieval task; 2) the required auxiliary dataset cannot be readily obtained.
RDA: Reciprocal Distribution Alignment for Robust Semi-supervised Learning
In this work, we propose Reciprocal Distribution Alignment (RDA) to address semi-supervised learning (SSL), which is a hyperparameter-free framework that is independent of confidence threshold and works with both the matched (conventionally) and the mismatched class distributions.
Single-view 3D Mesh Reconstruction for Seen and Unseen Categories
Single-view 3D object reconstruction is a fundamental and challenging computer vision task that aims at recovering 3D shapes from single-view RGB images.
Action Recognition With Motion Diversification and Dynamic Selection
To address this issue, we introduce a Motion Diversification and Selection (MoDS) module to generate diversified spatio-temporal motion features and then select the suitable motion representation dynamically for categorizing the input video.
Ranked #19 on
Action Recognition
on Something-Something V1
Inverse design of nano-photonic wavelength demultiplexer with a deep neural network approach
The correlation coefficient of the prediction by the presented PTCN model remains greater than 0. 974 even when the size of training data is decreased to 17%.
MutexMatch: Semi-Supervised Learning with Mutex-Based Consistency Regularization
The core issue in semi-supervised learning (SSL) lies in how to effectively leverage unlabeled data, whereas most existing methods tend to put a great emphasis on the utilization of high-confidence samples yet seldom fully explore the usage of low-confidence samples.
DC-SSL: Addressing Mismatched Class Distribution in Semi-Supervised Learning
Consistency-based Semi-supervised learning (SSL) has achieved promising performance recently.
Few-shot Unsupervised Domain Adaptation with Image-to-class Sparse Similarity Encoding
Inspired by the recent local descriptor based few-shot learning (FSL), our general UDA model is fully built upon local descriptors (LDs) for image classification and domain adaptation.
Crosslink-Net: Double-branch Encoder Segmentation Network via Fusing Vertical and Horizontal Convolutions
Together, the above two schemes give rise to a novel double-branch encoder segmentation framework for medical image segmentation, namely Crosslink-Net.
A Self-Boosting Framework for Automated Radiographic Report Generation
On one hand, the image-text matching branch helps to learn highly text-correlated visual features for the report generation branch to output high quality reports.
ASMFS: Adaptive-Similarity-based Multi-modality Feature Selection for Classification of Alzheimer's Disease
With the increasing amounts of high-dimensional heterogeneous data to be processed, multi-modality feature selection has become an important research direction in medical image analysis.
Improving Auto-Augment via Augmentation-Wise Weight Sharing
On CIFAR-10, we achieve a top-1 error rate of 1. 24%, which is currently the best performing single model without extra training data.
BriNet: Towards Bridging the Intra-class and Inter-class Gaps in One-Shot Segmentation
(2) The object categories at the training and inference stages have no overlap, leaving the inter-class gap.
DSU-net: Dense SegU-net for automatic head-and-neck tumor segmentation in MR images
In this paper, we propose a Dense SegU-net (DSU-net) framework for automatic NPC segmentation in MRI.
Class Distribution Alignment for Adversarial Domain Adaptation
To address this issue, we propose a novel approach called Conditional ADversarial Image Translation (CADIT) to explicitly align the class distributions given samples between the two domains.
Epileptic Seizure Classification with Symmetric and Hybrid Bilinear Models
Epilepsy affects nearly 1% of the global population, of which two thirds can be treated by anti-epileptic drugs and a much lower percentage by surgery.
Deep Learning based HEp-2 Image Classification: A Comprehensive Review
This paper provides a comprehensive review of the existing deep learning based HEp-2 cell image classification methods.
Improving Action Localization by Progressive Cross-stream Cooperation
Specifically, we first generate a larger set of region proposals by combining the latest region proposals from both streams, from which we can readily obtain a larger set of labelled training samples to help learn better action detection models.
A Novel Unsupervised Camera-aware Domain Adaptation Framework for Person Re-identification
For the first issue, we highlight the presence of camera-level sub-domains as a unique characteristic of person Re-ID, and develop camera-aware domain adaptation to reduce the discrepancy not only between source and target domains but also across these sub-domains.
Ranked #20 on
Unsupervised Domain Adaptation
on Market to Duke
Interactive Medical Image Segmentation via Point-Based Interaction and Sequential Patch Learning
In this paper, we present a novel method for interactive medical image segmentation with the following merits.
DeepKSPD: Learning Kernel-matrix-based SPD Representation for Fine-grained Image Recognition
Being symmetric positive-definite (SPD), covariance matrix has traditionally been used to represent a set of local descriptors in visual recognition.
Revisiting Metric Learning for SPD Matrix Based Visual Representation
The proposed method has been tested on multiple SPD-based visual representation data sets used in the literature, and the results demonstrate its interesting properties and attractive performance.
Exploiting Structure Sparsity for Covariance-based Visual Representation
A variety of methods have been proposed to boost its efficacy, with some recent ones resorting to nonlinear kernel technique.
OPML: A One-Pass Closed-Form Solution for Online Metric Learning
To achieve a low computational cost when performing online metric learning for large-scale data, we present a one-pass closed-form solution namely OPML in this paper.
Beyond Covariance: Feature Representation With Nonlinear Kernel Matrices
It proposes an open framework to use the kernel matrix over feature dimensions as a generic representation and discusses its properties and advantages.
Learning Discriminative Bayesian Networks from High-dimensional Continuous Neuroimaging Data
This brings two general discriminative learning frameworks for Gaussian Bayesian networks (GBN).
HEp-2 Cell Image Classification with Deep Convolutional Neural Networks
Efficient Human Epithelial-2 (HEp-2) cell image classification can facilitate the diagnosis of many autoimmune diseases.
Learning Discriminative Stein Kernel for SPD Matrices and Its Applications
A comprehensive experimental study is conducted on a variety of image classification tasks to compare our proposed discriminative Stein kernel with the original Stein kernel and other commonly used methods for evaluating the similarity between SPD matrices.
Discriminative Sparse Inverse Covariance Matrix: Application in Brain Functional Network Classification
In this paper, we propose a learning framework to effectively improve the discriminative power of SICEs by taking advantage of the samples in the opposite class.
Multiple Kernel Learning in the Primal for Multi-modal Alzheimer's Disease Classification
In this work, we propose a novel multiple kernel learning framework to combine multi-modal features for AD classification, which is scalable and easy to implement.
Discriminative Brain Effective Connectivity Analysis for Alzheimer's Disease: A Kernel Learning Approach upon Sparse Gaussian Bayesian Network
Analyzing brain networks from neuroimages is becoming a promising approach in identifying novel connectivitybased biomarkers for the Alzheimer's disease (AD).
A Fast Approximate AIB Algorithm for Distributional Word Clustering
Distributional word clustering merges the words having similar probability distributions to attain reliable parameter estimation, compact classification models and even better classification performance.
