Yanwei Pang
YOU?
Author Swipe
View article: Interpretable Few-Shot Image Classification via Prototypical Concept-Guided Mixture of LoRA Experts
Interpretable Few-Shot Image Classification via Prototypical Concept-Guided Mixture of LoRA Experts Open
Self-Explainable Models (SEMs) rely on Prototypical Concept Learning (PCL) to enable their visual recognition processes more interpretable, but they often struggle in data-scarce settings where insufficient training samples lead to subopti…
View article: HGOT: Self-supervised Heterogeneous Graph Neural Network with Optimal Transport
HGOT: Self-supervised Heterogeneous Graph Neural Network with Optimal Transport Open
Heterogeneous Graph Neural Networks (HGNNs), have demonstrated excellent capabilities in processing heterogeneous information networks. Self-supervised learning on heterogeneous graphs, especially contrastive self-supervised strategy, show…
View article: Design simulation of high‐homogeneity portable MRI magnet array using global optimization algorithm and equivalent currents model
Design simulation of high‐homogeneity portable MRI magnet array using global optimization algorithm and equivalent currents model Open
Background High‐field magnetic resonance imaging (MRI) systems offer high sensitivity and resolution but are costly and bulky, limiting their widespread use, particularly in remote areas. Conversely, portable MRI systems have emerged as a …
View article: Optimal Transport Adapter Tuning for Bridging Modality Gaps in Few-Shot Remote Sensing Scene Classification
Optimal Transport Adapter Tuning for Bridging Modality Gaps in Few-Shot Remote Sensing Scene Classification Open
Few-Shot Remote Sensing Scene Classification (FS-RSSC) presents the challenge of classifying remote sensing images with limited labeled samples. Existing methods typically emphasize single-modal feature learning, neglecting the potential b…
View article: Underlying Semantic Diffusion for Effective and Efficient In-Context Learning
Underlying Semantic Diffusion for Effective and Efficient In-Context Learning Open
Diffusion models has emerged as a powerful framework for tasks like image controllable generation and dense prediction. However, existing models often struggle to capture underlying semantics (e.g., edges, textures, shapes) and effectively…
View article: Domino volumetric metamaterial resonator for very‐low‐field MRI
Domino volumetric metamaterial resonator for very‐low‐field MRI Open
Background Very‐low‐field magnetic resonance imaging (VLF‐MRI) plays a significant role in medical imaging diagnosis due to its low cost and light weight. High‐quality MR images are essential for accurate medical diagnosis. It is urgent to…
View article: CLIPer: Hierarchically Improving Spatial Representation of CLIP for Open-Vocabulary Semantic Segmentation
CLIPer: Hierarchically Improving Spatial Representation of CLIP for Open-Vocabulary Semantic Segmentation Open
Contrastive Language-Image Pre-training (CLIP) exhibits strong zero-shot classification ability on various image-level tasks, leading to the research to adapt CLIP for pixel-level open-vocabulary semantic segmentation without additional tr…
View article: Multi-Stage Knowledge Integration of Vision-Language Models for Continual Learning
Multi-Stage Knowledge Integration of Vision-Language Models for Continual Learning Open
Vision Language Models (VLMs), pre-trained on large-scale image-text datasets, enable zero-shot predictions for unseen data but may underperform on specific unseen tasks. Continual learning (CL) can help VLMs effectively adapt to new data …
View article: A Fresh Look at Generalized Category Discovery through Non-negative Matrix Factorization
A Fresh Look at Generalized Category Discovery through Non-negative Matrix Factorization Open
Generalized Category Discovery (GCD) aims to classify both base and novel images using labeled base data. However, current approaches inadequately address the intrinsic optimization of the co-occurrence matrix $\bar{A}$ based on cosine sim…
View article: iSeg: An Iterative Refinement-based Framework for Training-free Segmentation
iSeg: An Iterative Refinement-based Framework for Training-free Segmentation Open
Stable diffusion has demonstrated strong image synthesis ability to given text descriptions, suggesting it to contain strong semantic clue for grouping objects. The researchers have explored employing stable diffusion for training-free seg…
View article: Pseudo-Multispectral Pedestrian Detection with Deep Thermal Feature Guidance
Pseudo-Multispectral Pedestrian Detection with Deep Thermal Feature Guidance Open
With complementary multi-modal information (i.e. visible and thermal), multispectral pedestrian detection is essential for around-the-clock applications, such as autonomous driving, video surveillance, and vicinagearth security. Despite it…
View article: Raformer: Redundancy-Aware Transformer for Video Wire Inpainting
Raformer: Redundancy-Aware Transformer for Video Wire Inpainting Open
Video Wire Inpainting (VWI) is a prominent application in video inpainting, aimed at flawlessly removing wires in films or TV series, offering significant time and labor savings compared to manual frame-by-frame removal. However, wire remo…
View article: Implicit and Explicit Language Guidance for Diffusion-based Visual Perception
Implicit and Explicit Language Guidance for Diffusion-based Visual Perception Open
Text-to-image diffusion models have shown powerful ability on conditional image synthesis. With large-scale vision-language pre-training, diffusion models are able to generate high-quality images with rich texture and reasonable structure …
View article: Accurate blood glucose level monitoring using microwave imaging
Accurate blood glucose level monitoring using microwave imaging Open
Painless and non-invasive detection techniques are needed to replace finger-prick blood collection for people with diabetes. A first-of-its-kind, noninvasive, and continuous blood glucose level (BGL) detection method based on microwave ima…
View article: The state-of-the-art in Cardiac MRI Reconstruction: Results of the CMRxRecon Challenge in MICCAI 2023
The state-of-the-art in Cardiac MRI Reconstruction: Results of the CMRxRecon Challenge in MICCAI 2023 Open
Cardiac MRI, crucial for evaluating heart structure and function, faces limitations like slow imaging and motion artifacts. Undersampling reconstruction, especially data-driven algorithms, has emerged as a promising solution to accelerate …
View article: CLIP-VIS: Adapting CLIP for Open-Vocabulary Video Instance Segmentation
CLIP-VIS: Adapting CLIP for Open-Vocabulary Video Instance Segmentation Open
Open-vocabulary video instance segmentation strives to segment and track instances belonging to an open set of categories in a videos. The vision-language model Contrastive Language-Image Pre-training (CLIP) has shown robust zero-shot clas…
View article: NTK-Guided Few-Shot Class Incremental Learning
NTK-Guided Few-Shot Class Incremental Learning Open
The proliferation of Few-Shot Class Incremental Learning (FSCIL) methodologies has highlighted the critical challenge of maintaining robust anti-amnesia capabilities in FSCIL learners. In this paper, we present a novel conceptualization of…
View article: Joint Attention-Guided Feature Fusion Network for Saliency Detection of Surface Defects
Joint Attention-Guided Feature Fusion Network for Saliency Detection of Surface Defects Open
Surface defect inspection plays an important role in the process of industrial manufacture and production. Though Convolutional Neural Network (CNN) based defect inspection methods have made huge leaps, they still confront a lot of challen…
View article: High-Q metasurface signal isolator for 1.5T surface coil magnetic resonance imaging on the go
High-Q metasurface signal isolator for 1.5T surface coil magnetic resonance imaging on the go Open
The combination of surface coils and metamaterials remarkably enhance magnetic resonance imaging (MRI) performance for significant local staging flexibility. However, due to the coupling in between, impeded signal-to-noise ratio (SNR) and …
View article: EEUR-Net: End-to-End Optimization of Under-Sampling and Reconstruction Network for 3D Magnetic Resonance Imaging
EEUR-Net: End-to-End Optimization of Under-Sampling and Reconstruction Network for 3D Magnetic Resonance Imaging Open
It is time-consuming to acquire complete data by fully phase encoding in two orthogonal directions along with one frequency encoding direction. Under-sampling in the 3D k-space is promising in accelerating such 3D MRI process. Although 3D …
View article: EEUR-Net: End-to-End Optimization of Undersampling and Reconstruction Network for 3D Magnetic Resonance Imaging
EEUR-Net: End-to-End Optimization of Undersampling and Reconstruction Network for 3D Magnetic Resonance Imaging Open
It is time-consuming for acquiring complete data by fully phase encoding in two orthogonal directions along with one frequency encoding direction. Undersampling in the 3D k-space is promising in accelerating such 3D MRI process. Though 3D …
View article: SED: A Simple Encoder-Decoder for Open-Vocabulary Semantic Segmentation
SED: A Simple Encoder-Decoder for Open-Vocabulary Semantic Segmentation Open
Open-vocabulary semantic segmentation strives to distinguish pixels into different semantic groups from an open set of categories. Most existing methods explore utilizing pre-trained vision-language models, in which the key is to adopt the…
View article: Integrating Visual Perception With Decision Making in Neuromorphic Fault-Tolerant Quadruplet-Spike Learning Framework
Integrating Visual Perception With Decision Making in Neuromorphic Fault-Tolerant Quadruplet-Spike Learning Framework Open
The brain possesses the remarkable ability to seamlessly integrate perception with decision making within a dynamically changing environment in a fault-tolerant, end-to-end manner. This extraordinary capability offers a compelling solution…
View article: A high-Q metasurface signal isolator for 1.5T surface coil magnetic resonance imaging on the go
A high-Q metasurface signal isolator for 1.5T surface coil magnetic resonance imaging on the go Open
The combination of surface coils and metamaterials remarkably enhance magnetic resonance imaging (MRI) performance for significant local staging flexibility. However, due to the coupling in between, impeded signal-to-noise ratio (SNR) and …
View article: Hierarchical Matching and Reasoning for Multi-Query Image Retrieval
Hierarchical Matching and Reasoning for Multi-Query Image Retrieval Open
As a promising field, Multi-Query Image Retrieval (MQIR) aims at searching for the semantically relevant image given multiple region-specific text queries. Existing works mainly focus on a single-level similarity between image regions and …
View article: DFormer: Diffusion-guided Transformer for Universal Image Segmentation
DFormer: Diffusion-guided Transformer for Universal Image Segmentation Open
This paper introduces an approach, named DFormer, for universal image segmentation. The proposed DFormer views universal image segmentation task as a denoising process using a diffusion model. DFormer first adds various levels of Gaussian …
View article: Image Reconstruction for Accelerated MR Scan with Faster Fourier Convolutional Neural Networks
Image Reconstruction for Accelerated MR Scan with Faster Fourier Convolutional Neural Networks Open
Partial scan is a common approach to accelerate Magnetic Resonance Imaging (MRI) data acquisition in both 2D and 3D settings. However, accurately reconstructing images from partial scan data (i.e., incomplete k-space matrices) remains chal…
View article: Non-invasive, intelligent, and continuous monitoring of human blood glucose with UWB dual-antenna and cascade CNN
Non-invasive, intelligent, and continuous monitoring of human blood glucose with UWB dual-antenna and cascade CNN Open
Finger-prick blood collection process has become unrealistic for a long-term and frequent blood glucose detection. Hence, an appropriate non-invasive detection system is highly desirable to effectively address this concern. A non-invasive …