Search Results for author: Yiping Ke

Found 20 papers, 13 papers with code

BrainOOD: Out-of-distribution Generalizable Brain Network Analysis

1 code implementation2 Feb 2025 Jiaxing Xu, Yongqiang Chen, Xia Dong, Mengcheng Lan, Tiancheng Huang, Qingtian Bian, James Cheng, Yiping Ke

Graph Neural Networks (GNNs) have shown promising in analyzing brain networks, but there are two major challenges in using GNNs: (1) distribution shifts in multi-site brain network data, leading to poor Out-of-Distribution (OOD) generalization, and (2) limited interpretability in identifying key brain regions critical to neurological disorders.

GeoGround: A Unified Large Vision-Language Model for Remote Sensing Visual Grounding

1 code implementation16 Nov 2024 Yue Zhou, Mengcheng Lan, Xiang Li, Yiping Ke, Xue Jiang, Litong Feng, Wayne Zhang

Remote sensing (RS) visual grounding aims to use natural language expression to locate specific objects (in the form of the bounding box or segmentation mask) in RS images, enhancing human interaction with intelligent RS interpretation systems.

Language Modeling Language Modelling +3

Text4Seg: Reimagining Image Segmentation as Text Generation

1 code implementation13 Oct 2024 Mengcheng Lan, Chaofeng Chen, Yue Zhou, Jiaxing Xu, Yiping Ke, Xinjiang Wang, Litong Feng, Wayne Zhang

Multimodal Large Language Models (MLLMs) have shown exceptional capabilities in vision-language tasks; however, effectively integrating image segmentation into these models remains a significant challenge.

Image Segmentation Referring Expression +4

Multi-Atlas Brain Network Classification through Consistency Distillation and Complementary Information Fusion

no code implementations28 Sep 2024 Jiaxing Xu, Mengcheng Lan, Xia Dong, Kai He, Wei zhang, Qingtian Bian, Yiping Ke

Some recent methods have proposed utilizing multiple atlases, but they neglect consistency across atlases and lack ROI-level information exchange.

Contrasformer: A Brain Network Contrastive Transformer for Neurodegenerative Condition Identification

1 code implementation17 Sep 2024 Jiaxing Xu, Kai He, Mengcheng Lan, Qingtian Bian, Wei Li, Tieying Li, Yiping Ke, Miao Qiao

It generates a prior-knowledge-enhanced contrast graph to address the distribution shifts across sub-populations by a two-stream attention mechanism.

ProxyCLIP: Proxy Attention Improves CLIP for Open-Vocabulary Segmentation

1 code implementation9 Aug 2024 Mengcheng Lan, Chaofeng Chen, Yiping Ke, Xinjiang Wang, Litong Feng, Wayne Zhang

ProxyCLIP leverages the spatial feature correspondence from VFMs as a form of proxy attention to augment CLIP, thereby inheriting the VFMs' robust local consistency and maintaining CLIP's exceptional zero-shot transfer capacity.

Open Vocabulary Semantic Segmentation Open-Vocabulary Semantic Segmentation +2

ClearCLIP: Decomposing CLIP Representations for Dense Vision-Language Inference

no code implementations17 Jul 2024 Mengcheng Lan, Chaofeng Chen, Yiping Ke, Xinjiang Wang, Litong Feng, Wayne Zhang

Despite the success of large-scale pretrained Vision-Language Models (VLMs) especially CLIP in various open-vocabulary tasks, their application to semantic segmentation remains challenging, producing noisy segmentation maps with mis-segmented regions.

Open Vocabulary Semantic Segmentation Open-Vocabulary Semantic Segmentation +1

Towards Vision-Language Geo-Foundation Model: A Survey

1 code implementation13 Jun 2024 Yue Zhou, Litong Feng, Yiping Ke, Xue Jiang, Junchi Yan, Xue Yang, Wayne Zhang

Vision-Language Foundation Models (VLFMs) have made remarkable progress on various multimodal tasks, such as image captioning, image-text retrieval, visual question answering, and visual grounding.

Earth Observation Image Captioning +7

CPMR: Context-Aware Incremental Sequential Recommendation with Pseudo-Multi-Task Learning

1 code implementation9 Sep 2023 Qingtian Bian, Jiaxing Xu, Hui Fang, Yiping Ke

To dually improve the performance of temporal states evolution and incremental recommendation, we design a Pseudo-Multi-Task Learning (PMTL) paradigm by stacking the incremental single-target recommendations into one multi-target task for joint optimization.

Multi-Task Learning Sequential Recommendation

Contrastive Graph Pooling for Explainable Classification of Brain Networks

2 code implementations7 Jul 2023 Jiaxing Xu, Qingtian Bian, Xinhang Li, Aihu Zhang, Yiping Ke, Miao Qiao, Wei zhang, Wei Khang Jeremy Sim, Balázs Gulyás

Our contributions underscore the potential of ContrastPool for advancing the understanding of brain networks and neurodegenerative conditions.

Classification

Union Subgraph Neural Networks

1 code implementation25 May 2023 Jiaxing Xu, Aihu Zhang, Qingtian Bian, Vijay Prakash Dwivedi, Yiping Ke

We first investigate different kinds of connectivities existing in a local neighborhood and identify a substructure called union subgraph, which is able to capture the complete picture of the 1-hop neighborhood of an edge.

Computational Efficiency Graph Representation Learning

Data-Driven Network Neuroscience: On Data Collection and Benchmark

1 code implementation NeurIPS 2023 Jiaxing Xu, Yunhan Yang, David Tse Jung Huang, Sophi Shilpa Gururajapathy, Yiping Ke, Miao Qiao, Alan Wang, Haribalan Kumar, Josh McGeown, Eryn Kwon

This paper presents a comprehensive and quality collection of functional human brain network data for potential research in the intersection of neuroscience, machine learning, and graph analytics.

Functional Connectivity

A Class-Aware Representation Refinement Framework for Graph Classification

no code implementations2 Sep 2022 Jiaxing Xu, Jinjie Ni, Yiping Ke

In this paper, we propose a Class-Aware Representation rEfinement (CARE) framework for the task of graph classification.

Graph Classification Graph Representation Learning

Mitigating Performance Saturation in Neural Marked Point Processes: Architectures and Loss Functions

1 code implementation7 Jul 2021 Tianbo Li, Tianze Luo, Yiping Ke, Sinno Jialin Pan

Neural marked point processes possess good interpretability of probabilistic models as well as the representational power of neural networks.

Model Selection Point Processes

Subdomain Adaptation with Manifolds Discrepancy Alignment

no code implementations6 May 2020 Pengfei Wei, Yiping Ke, Xinghua Qu, Tze-Yun Leong

Specifically, we propose to use low-dimensional manifold to represent subdomain, and align the local data distribution discrepancy in each manifold across domains.

Subdomain adaptation Transfer Learning

Thinning for Accelerating the Learning of Point Processes

no code implementations NeurIPS 2019 Tianbo Li, Yiping Ke

Experimental results on synthetic and real-world datasets validate the effectiveness of thinning in the tasks of parameter and gradient estimation, as well as stochastic optimization.

Point Processes Stochastic Optimization

Stochastic Variance Reduced Riemannian Eigensolver

no code implementations26 May 2016 Zhiqiang Xu, Yiping Ke

We generalize it to Riemannian manifolds and realize it to solve the non-convex eigen-decomposition problem.

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