Xiu-Shen Wei
YOU?
Author Swipe
View article: Efficient and Effective In-context Demonstration Selection with Coreset
Efficient and Effective In-context Demonstration Selection with Coreset Open
In-context learning (ICL) has emerged as a powerful paradigm for Large Visual Language Models (LVLMs), enabling them to leverage a few examples directly from input contexts. However, the effectiveness of this approach is heavily reliant on…
View article: ABO-dependent manner modulates hemostasis in neonatal thrombocytopenia via ADAMTS13-mediated VWF cleavage
ABO-dependent manner modulates hemostasis in neonatal thrombocytopenia via ADAMTS13-mediated VWF cleavage Open
The VWF susceptibility to ADAMTS13 proteolysis was increased as follows: A, B and O blood phenotype during platelet transfusion, causing imbalance of neonatal hemostasis in an ABO-dependent manner.
View article: Learning Attribute-Aware Hash Codes for Fine-Grained Image Retrieval via Query Optimization
Learning Attribute-Aware Hash Codes for Fine-Grained Image Retrieval via Query Optimization Open
Fine-grained hashing has become a powerful solution for rapid and efficient image retrieval, particularly in scenarios requiring high discrimination between visually similar categories. To enable each hash bit to correspond to specific vis…
View article: Object-level Correlation for Few-Shot Segmentation
Object-level Correlation for Few-Shot Segmentation Open
Few-shot semantic segmentation (FSS) aims to segment objects of novel categories in the query images given only a few annotated support samples. Existing methods primarily build the image-level correlation between the support target object…
View article: Toward Safe and Human-Aligned Game Conversational Recommendation via Multi-Agent Decomposition
Toward Safe and Human-Aligned Game Conversational Recommendation via Multi-Agent Decomposition Open
Conversational recommender systems (CRS) have advanced with large language models, showing strong results in domains like movies. These domains typically involve fixed content and passive consumption, where user preferences can be matched …
View article: Addressing Asymmetry in Contrastive Learning: LLM-Driven Sentence Embeddings with Ranking and Label Smoothing
Addressing Asymmetry in Contrastive Learning: LLM-Driven Sentence Embeddings with Ranking and Label Smoothing Open
Unsupervised sentence embedding, vital for numerous NLP tasks, struggles with the inherent asymmetry of semantic relationships within contrastive learning (CL). This paper proposes Label Smoothing-based Ranking Negative Sampling (LS-RNS), …
View article: Beyond Overfitting: Doubly Adaptive Dropout for Generalizable AU Detection
Beyond Overfitting: Doubly Adaptive Dropout for Generalizable AU Detection Open
Facial Action Units (AUs) are essential for conveying psychological states and emotional expressions. While automatic AU detection systems leveraging deep learning have progressed, they often overfit to specific datasets and individual fea…
View article: Research on Preprocessing Techniques for Software Defect Prediction Dataset Based on Hybrid Category Balance and Synthetic Sampling Algorithm
Research on Preprocessing Techniques for Software Defect Prediction Dataset Based on Hybrid Category Balance and Synthetic Sampling Algorithm Open
View article: Automatic Modulation Recognition Method Based on Channel-Enhanced Convolution and Linear-Angular Attention
Automatic Modulation Recognition Method Based on Channel-Enhanced Convolution and Linear-Angular Attention Open
Automatic Modulation Recognition (AMR) is an electronic signal processing technology designed to automatically identify and classify the modulation type of radio signals. Existing AMR methods suffer from a significant decrease in classific…
View article: Explanatory Instructions: Towards Unified Vision Tasks Understanding and Zero-shot Generalization
Explanatory Instructions: Towards Unified Vision Tasks Understanding and Zero-shot Generalization Open
Computer Vision (CV) has yet to fully achieve the zero-shot task generalization observed in Natural Language Processing (NLP), despite following many of the milestones established in NLP, such as large transformer models, extensive pre-tra…
View article: OMuleT: Orchestrating Multiple Tools for Practicable Conversational Recommendation
OMuleT: Orchestrating Multiple Tools for Practicable Conversational Recommendation Open
In this paper, we present a systematic effort to design, evaluate, and implement a realistic conversational recommender system (CRS). The objective of our system is to allow users to input free-form text to request recommendations, and the…
View article: Long-Tailed Object Detection Pre-training: Dynamic Rebalancing Contrastive Learning with Dual Reconstruction
Long-Tailed Object Detection Pre-training: Dynamic Rebalancing Contrastive Learning with Dual Reconstruction Open
Pre-training plays a vital role in various vision tasks, such as object recognition and detection. Commonly used pre-training methods, which typically rely on randomized approaches like uniform or Gaussian distributions to initialize model…
View article: Data tells the truth: A Knowledge distillation method for genomic survival analysis by handling censoring
Data tells the truth: A Knowledge distillation method for genomic survival analysis by handling censoring Open
View article: Attribute-Aware Deep Hashing with Self-Consistency for Large-Scale Fine-Grained Image Retrieval
Attribute-Aware Deep Hashing with Self-Consistency for Large-Scale Fine-Grained Image Retrieval Open
Our work focuses on tackling large-scale fine-grained image retrieval as ranking the images depicting the concept of interests (i.e., the same sub-category labels) highest based on the fine-grained details in the query. It is desirable to …
View article: Hyperbolic Space with Hierarchical Margin Boosts Fine-Grained Learning from Coarse Labels
Hyperbolic Space with Hierarchical Margin Boosts Fine-Grained Learning from Coarse Labels Open
Learning fine-grained embeddings from coarse labels is a challenging task due to limited label granularity supervision, i.e., lacking the detailed distinctions required for fine-grained tasks. The task becomes even more demanding when atte…
View article: Hawkeye: A PyTorch-based Library for Fine-Grained Image Recognition with Deep Learning
Hawkeye: A PyTorch-based Library for Fine-Grained Image Recognition with Deep Learning Open
Fine-Grained Image Recognition (FGIR) is a fundamental and challenging task in computer vision and multimedia that plays a crucial role in Intellectual Economy and Industrial Internet applications. However, the absence of a unified open-so…
View article: Watch out Venomous Snake Species: A Solution to SnakeCLEF2023
Watch out Venomous Snake Species: A Solution to SnakeCLEF2023 Open
The SnakeCLEF2023 competition aims to the development of advanced algorithms for snake species identification through the analysis of images and accompanying metadata. This paper presents a method leveraging utilization of both images and …
View article: CAT: a coarse-to-fine attention tree for semantic change detection
CAT: a coarse-to-fine attention tree for semantic change detection Open
Semantic change detection (SCD) and land cover mapping (LCM) are always treated as a dual task in the field of remote sensing. However, due to diverse real-world scenarios, many SCD categories are not easy to be clearly recognized, such as…
View article: Equiangular Basis Vectors
Equiangular Basis Vectors Open
We propose Equiangular Basis Vectors (EBVs) for classification tasks. In deep neural networks, models usually end with a k-way fully connected layer with softmax to handle different classification tasks. The learning objective of these met…
View article: Delving Deep into Simplicity Bias for Long-Tailed Image Recognition
Delving Deep into Simplicity Bias for Long-Tailed Image Recognition Open
Simplicity Bias (SB) is a phenomenon that deep neural networks tend to rely favorably on simpler predictive patterns but ignore some complex features when applied to supervised discriminative tasks. In this work, we investigate SB in long-…
View article: Bridge the Gap between Supervised and Unsupervised Learning for Fine-Grained Classification
Bridge the Gap between Supervised and Unsupervised Learning for Fine-Grained Classification Open
View article: SEMICON: A Learning-to-hash Solution for Large-scale Fine-grained Image Retrieval
SEMICON: A Learning-to-hash Solution for Large-scale Fine-grained Image Retrieval Open
In this paper, we propose Suppression-Enhancing Mask based attention and Interactive Channel transformatiON (SEMICON) to learn binary hash codes for dealing with large-scale fine-grained image retrieval tasks. In SEMICON, we first develop …
View article: An Embarrassingly Simple Approach to Semi-Supervised Few-Shot Learning
An Embarrassingly Simple Approach to Semi-Supervised Few-Shot Learning Open
Semi-supervised few-shot learning consists in training a classifier to adapt to new tasks with limited labeled data and a fixed quantity of unlabeled data. Many sophisticated methods have been developed to address the challenges this probl…
View article: RPC: a large-scale and fine-grained retail product checkout dataset
RPC: a large-scale and fine-grained retail product checkout dataset Open
View article: Webly-Supervised Fine-Grained Recognition with Partial Label Learning
Webly-Supervised Fine-Grained Recognition with Partial Label Learning Open
The task of webly-supervised fine-grained recognition is to boost recognition accuracy of classifying subordinate categories (e.g., different bird species) by utilizing freely available but noisy web data. As the label noises significantly…
View article: Dual Attention Networks for Few-Shot Fine-Grained Recognition
Dual Attention Networks for Few-Shot Fine-Grained Recognition Open
The task of few-shot fine-grained recognition is to classify images belonging to subordinate categories merely depending on few examples. Due to the fine-grained nature, it is desirable to capture subtle but discriminative part-level patte…
View article: Preface
Preface Open
View article: Bridge the Gap between Supervised and Unsupervised Learning for Fine-Grained Classification
Bridge the Gap between Supervised and Unsupervised Learning for Fine-Grained Classification Open
Unsupervised learning technology has caught up with or even surpassed supervised learning technology in general object classification (GOC) and person re-identification (re-ID). However, it is found that the unsupervised learning of fine-g…
View article: Relieving Long-tailed Instance Segmentation via Pairwise Class Balance
Relieving Long-tailed Instance Segmentation via Pairwise Class Balance Open
Long-tailed instance segmentation is a challenging task due to the extreme imbalance of training samples among classes. It causes severe biases of the head classes (with majority samples) against the tailed ones. This renders "how to appro…
View article: Fine-Grained Image Analysis with Deep Learning: A Survey
Fine-Grained Image Analysis with Deep Learning: A Survey Open
Fine-grained image analysis (FGIA) is a longstanding and fundamental problem in computer vision and pattern recognition, and underpins a diverse set of real-world applications. The task of FGIA targets analyzing visual objects from subordi…