Search Results for author: Ze Chen

Found 28 papers, 13 papers with code

Taylor expansion-based Kolmogorov-Arnold network for blind image quality assessment

1 code implementation27 May 2025 Ze Chen, Shaode Yu

Kolmogorov-Arnold Network (KAN) has attracted growing interest for its strong function approximation capability.

Blind Image Quality Assessment Computational Efficiency +1

ROUTE: Robust Multitask Tuning and Collaboration for Text-to-SQL

1 code implementation13 Dec 2024 Yang Qin, Chao Chen, Zhihang Fu, Ze Chen, Dezhong Peng, Peng Hu, Jieping Ye

To address this challenge, we propose a novel RObust mUltitask Tuning and collaboration mEthod (ROUTE) to improve the comprehensive capabilities of open-source LLMs for Text2SQL, thereby providing a more practical solution.

In-Context Learning Text to SQL +1

Class Balance Matters to Active Class-Incremental Learning

1 code implementation9 Dec 2024 Zitong Huang, Ze Chen, Yuanze Li, Bowen Dong, Erjin Zhou, Yong liu, Rick Siow Mong Goh, Chun-Mei Feng, WangMeng Zuo

Then for each cluster, we employ greedy selection strategy to ensure that the Gaussian distribution of the sampled features closely matches the Gaussian distribution of all unlabeled features within the cluster.

Active Learning class-incremental learning +3

Rethinking Out-of-Distribution Detection on Imbalanced Data Distribution

1 code implementation23 Jul 2024 Kai Liu, Zhihang Fu, Sheng Jin, Chao Chen, Ze Chen, Rongxin Jiang, Fan Zhou, Yaowu Chen, Jieping Ye

Detecting and rejecting unknown out-of-distribution (OOD) samples is critical for deployed neural networks to void unreliable predictions.

Out-of-Distribution Detection

ESOD: Efficient Small Object Detection on High-Resolution Images

1 code implementation23 Jul 2024 Kai Liu, Zhihang Fu, Sheng Jin, Ze Chen, Fan Zhou, Rongxin Jiang, Yaowu Chen, Jieping Ye

The resulting Efficient Small Object Detection (ESOD) approach is a generic framework, which can be applied to both CNN- and ViT-based detectors to save the computation and GPU memory costs.

Object object-detection +1

Structure-aware Domain Knowledge Injection for Large Language Models

1 code implementation23 Jul 2024 Kai Liu, Ze Chen, Zhihang Fu, Rongxin Jiang, Fan Zhou, Yaowu Chen, Yue Wu, Jieping Ye

Remarkably, our method demonstrates the potential of comparable improvement against the state-of-the-art MMedLM2 on MMedBench, while significantly reducing the training costs to 5%.

Question Answering

CARES: A Comprehensive Benchmark of Trustworthiness in Medical Vision Language Models

1 code implementation10 Jun 2024 Peng Xia, Ze Chen, Juanxi Tian, Yangrui Gong, Ruibo Hou, Yue Xu, Zhenbang Wu, Zhiyuan Fan, Yiyang Zhou, Kangyu Zhu, Wenhao Zheng, Zhaoyang Wang, Xiao Wang, Xuchao Zhang, Chetan Bansal, Marc Niethammer, Junzhou Huang, Hongtu Zhu, Yun Li, Jimeng Sun, ZongYuan Ge, Gang Li, James Zou, Huaxiu Yao

Artificial intelligence has significantly impacted medical applications, particularly with the advent of Medical Large Vision Language Models (Med-LVLMs), sparking optimism for the future of automated and personalized healthcare.

Fairness

IMWA: Iterative Model Weight Averaging Benefits Class-Imbalanced Learning Tasks

no code implementations25 Apr 2024 Zitong Huang, Ze Chen, Bowen Dong, Chaoqi Liang, Erjin Zhou, WangMeng Zuo

Model Weight Averaging (MWA) is a technique that seeks to enhance model's performance by averaging the weights of multiple trained models.

image-classification Image Classification +3

RetiGen: A Framework for Generalized Retinal Diagnosis Using Multi-View Fundus Images

no code implementations22 Mar 2024 Ze Chen, Gongyu Zhang, Jiayu Huo, Joan Nunez do Rio, Charalampos Komninos, Yang Liu, Rachel Sparks, Sebastien Ourselin, Christos Bergeles, Timothy Jackson

This study introduces a novel framework for enhancing domain generalization in medical imaging, specifically focusing on utilizing unlabelled multi-view colour fundus photographs.

Domain Generalization Test-time Adaptation

OPDAI at SemEval-2024 Task 6: Small LLMs can Accelerate Hallucination Detection with Weakly Supervised Data

no code implementations20 Feb 2024 Chengcheng Wei, Ze Chen, Songtan Fang, Jiarong He, Max Gao

This paper mainly describes a unified system for hallucination detection of LLMs, which wins the second prize in the model-agnostic track of the SemEval-2024 Task 6, and also achieves considerable results in the model-aware track.

Few-Shot Learning Hallucination +2

INSIDE: LLMs' Internal States Retain the Power of Hallucination Detection

1 code implementation6 Feb 2024 Chao Chen, Kai Liu, Ze Chen, Yi Gu, Yue Wu, Mingyuan Tao, Zhihang Fu, Jieping Ye

Knowledge hallucination have raised widespread concerns for the security and reliability of deployed LLMs.

Diversity Hallucination +1

Optimal Parameter and Neuron Pruning for Out-of-Distribution Detection

no code implementations NeurIPS 2023 Chao Chen, Zhihang Fu, Kai Liu, Ze Chen, Mingyuan Tao, Jieping Ye

Most existing OOD detection methods focused on exploring advanced training skills or training-free tricks to prevent the model from yielding overconfident confidence score for unknown samples.

Out-of-Distribution Detection

Learning Prompt with Distribution-Based Feature Replay for Few-Shot Class-Incremental Learning

1 code implementation3 Jan 2024 Zitong Huang, Ze Chen, Zhixing Chen, Erjin Zhou, Xinxing Xu, Rick Siow Mong Goh, Yong liu, WangMeng Zuo, ChunMei Feng

When progressing to a new session, pseudo-features are sampled from old-class distributions combined with training images of the current session to optimize the prompt, thus enabling the model to learn new knowledge while retaining old knowledge.

class-incremental learning Few-Shot Class-Incremental Learning +2

Sentence-Level Relation Extraction via Contrastive Learning with Descriptive Relation Prompts

no code implementations11 Apr 2023 Jiewen Zheng, Ze Chen

Sentence-level relation extraction aims to identify the relation between two entities for a given sentence.

Contrastive Learning Descriptive +4

Enhancing Model Performance in Multilingual Information Retrieval with Comprehensive Data Engineering Techniques

no code implementations14 Feb 2023 Qi Zhang, Zijian Yang, Yilun Huang, Ze Chen, Zijian Cai, Kangxu Wang, Jiewen Zheng, Jiarong He, Jin Gao

In this paper, we present our solution to the Multilingual Information Retrieval Across a Continuum of Languages (MIRACL) challenge of WSDM CUP 2023\footnote{https://project-miracl. github. io/}.

Data Augmentation Information Retrieval +1

OPD@NL4Opt: An ensemble approach for the NER task of the optimization problem

no code implementations6 Jan 2023 Kangxu Wang, Ze Chen, Jiewen Zheng

In this paper, we present an ensemble approach for the NL4Opt competition subtask 1(NER task).

NER

Using Deep Mixture-of-Experts to Detect Word Meaning Shift for TempoWiC

no code implementations7 Nov 2022 Ze Chen, Kangxu Wang, Zijian Cai, Jiewen Zheng, Jiarong He, Max Gao, Jason Zhang

This paper mainly describes the dma submission to the TempoWiC task, which achieves a macro-F1 score of 77. 05% and attains the first place in this task.

Data Augmentation Mixture-of-Experts +1

A Semantic Alignment System for Multilingual Query-Product Retrieval

no code implementations5 Aug 2022 Qi Zhang, Zijian Yang, Yilun Huang, Ze Chen, Zijian Cai, Kangxu Wang, Jiewen Zheng, Jiarong He, Jin Gao

Our models are all trained with cross-entropy loss to classify the query-product pairs into ESCI 4 categories at first, and then we use weighted sum with the 4-class probabilities to get the score for ranking.

Data Augmentation Retrieval +1

Spatial Likelihood Voting with Self-Knowledge Distillation for Weakly Supervised Object Detection

no code implementations14 Apr 2022 Ze Chen, Zhihang Fu, Jianqiang Huang, Mingyuan Tao, Rongxin Jiang, Xiang Tian, Yaowu Chen, Xian-Sheng Hua

The likelihood maps generated by the SLV module are used to supervise the feature learning of the backbone network, encouraging the network to attend to wider and more diverse areas of the image.

Multiple Instance Learning object-detection +3

Dynamic Supervisor for Cross-dataset Object Detection

no code implementations1 Apr 2022 Ze Chen, Zhihang Fu, Jianqiang Huang, Mingyuan Tao, Shengyu Li, Rongxin Jiang, Xiang Tian, Yaowu Chen, Xian-Sheng Hua

The application of cross-dataset training in object detection tasks is complicated because the inconsistency in the category range across datasets transforms fully supervised learning into semi-supervised learning.

Object object-detection +1

Guiding Query Position and Performing Similar Attention for Transformer-Based Detection Heads

no code implementations22 Aug 2021 Xiaohu Jiang, Ze Chen, Zhicheng Wang, Erjin Zhou, ChunYuan

After DETR was proposed, this novel transformer-based detection paradigm which performs several cross-attentions between object queries and feature maps for predictions has subsequently derived a series of transformer-based detection heads.

Object Position

SLV: Spatial Likelihood Voting for Weakly Supervised Object Detection

no code implementations CVPR 2020 Ze Chen, Zhihang Fu, Rongxin Jiang, Yaowu Chen, Xian-Sheng Hua

In this paper, we propose a spatial likelihood voting (SLV) module to converge the proposal localizing process without any bounding box annotations.

General Classification Multiple Instance Learning +4

Cannot find the paper you are looking for? You can Submit a new open access paper.