Search Results for author: Qingdong He

Found 23 papers, 10 papers with code

KAN or MLP? Point Cloud Shows the Way Forward

no code implementations18 Apr 2025 Yan Shi, Qingdong He, Yijun Liu, Xiaoyu Liu, Jingyong Su

To overcome the high parameter counts and computational inefficiency of standard KANs, we develop Efficient-KANs in the PointKAN-elite variant, which significantly reduces parameters while maintaining accuracy.

Few-Shot Learning Kolmogorov-Arnold Networks

UniCombine: Unified Multi-Conditional Combination with Diffusion Transformer

no code implementations12 Mar 2025 Haoxuan Wang, Jinlong Peng, Qingdong He, Hao Yang, Ying Jin, Jiafu Wu, Xiaobin Hu, Yanjie Pan, Zhenye Gan, Mingmin Chi, Bo Peng, Yabiao Wang

With the rapid development of diffusion models in image generation, the demand for more powerful and flexible controllable frameworks is increasing.

Image Generation

Unveil Inversion and Invariance in Flow Transformer for Versatile Image Editing

no code implementations24 Nov 2024 Pengcheng Xu, Boyuan Jiang, Xiaobin Hu, Donghao Luo, Qingdong He, Jiangning Zhang, Chengjie Wang, Yunsheng Wu, Charles Ling, Boyu Wang

Leveraging the large generative prior of the flow transformer for tuning-free image editing requires authentic inversion to project the image into the model's domain and a flexible invariance control mechanism to preserve non-target contents.

FitDiT: Advancing the Authentic Garment Details for High-fidelity Virtual Try-on

2 code implementations15 Nov 2024 Boyuan Jiang, Xiaobin Hu, Donghao Luo, Qingdong He, Chengming Xu, Jinlong Peng, Jiangning Zhang, Chengjie Wang, Yunsheng Wu, Yanwei Fu

Although image-based virtual try-on has made considerable progress, emerging approaches still encounter challenges in producing high-fidelity and robust fitting images across diverse scenarios.

Virtual Try-on

MureObjectStitch: Multi-reference Image Composition

1 code implementation12 Nov 2024 Jiaxuan Chen, Bo Zhang, Qingdong He, Jinlong Peng, Li Niu

Generative image composition aims to regenerate the given foreground object in the background image to produce a realistic composite image.

Object

Typicalness-Aware Learning for Failure Detection

1 code implementation4 Nov 2024 Yijun Liu, Jiequan Cui, Zhuotao Tian, Senqiao Yang, Qingdong He, Xiaoling Wang, Jingyong Su

We observe that, with the cross-entropy loss, model predictions are optimized to align with the corresponding labels via increasing logit magnitude or refining logit direction.

Mamba-YOLO-World: Marrying YOLO-World with Mamba for Open-Vocabulary Detection

1 code implementation13 Sep 2024 Haoxuan Wang, Qingdong He, Jinlong Peng, Hao Yang, Mingmin Chi, Yabiao Wang

However, its performance is hindered by its neck feature fusion mechanism, which causes the quadratic complexity and the limited guided receptive fields.

Mamba Open Vocabulary Object Detection

DualAnoDiff: Dual-Interrelated Diffusion Model for Few-Shot Anomaly Image Generation

1 code implementation24 Aug 2024 Ying Jin, Jinlong Peng, Qingdong He, Teng Hu, Hao Chen, Jiafu Wu, Wenbing Zhu, Mingmin Chi, Jun Liu, Yabiao Wang, Chengjie Wang

In this paper, we overcome these challenges from a new perspective, simultaneously generating a pair of the overall image and the corresponding anomaly part.

Anomaly Classification Anomaly Detection +3

MM-Tracker: Motion Mamba with Margin Loss for UAV-platform Multiple Object Tracking

1 code implementation15 Jul 2024 Mufeng Yao, Jinlong Peng, Qingdong He, Bo Peng, Hao Chen, Mingmin Chi, Chao Liu, Jon Atli Benediktsson

To address these issues, we propose the Motion Mamba Module, which explores both local and global motion features through cross-correlation and bi-directional Mamba Modules for better motion modeling.

Mamba Multiple Object Tracking

A Comprehensive Library for Benchmarking Multi-class Visual Anomaly Detection

1 code implementation5 Jun 2024 Jiangning Zhang, Haoyang He, Zhenye Gan, Qingdong He, Yuxuan Cai, Zhucun Xue, Yabiao Wang, Chengjie Wang, Lei Xie, Yong liu

This paper addresses this issue by proposing a comprehensive visual anomaly detection benchmark, ADer, which is a modular framework that is highly extensible for new methods.

Benchmarking Lesion Detection +1

NoiseBoost: Alleviating Hallucination with Noise Perturbation for Multimodal Large Language Models

1 code implementation30 May 2024 Kai Wu, Boyuan Jiang, Zhengkai Jiang, Qingdong He, Donghao Luo, Shengzhi Wang, Qingwen Liu, Chengjie Wang

Multimodal large language models (MLLMs) contribute a powerful mechanism to understanding visual information building on large language models.

Hallucination

AdapNet: Adaptive Noise-Based Network for Low-Quality Image Retrieval

no code implementations28 May 2024 Sihe Zhang, Qingdong He, Jinlong Peng, Yuxi Li, Zhengkai Jiang, Jiafu Wu, Mingmin Chi, Yabiao Wang, Chengjie Wang

To mitigate this issue, we introduce a novel setting for low-quality image retrieval, and propose an Adaptive Noise-Based Network (AdapNet) to learn robust abstract representations.

Image Retrieval Re-Ranking +1

PointRWKV: Efficient RWKV-Like Model for Hierarchical Point Cloud Learning

no code implementations24 May 2024 Qingdong He, Jiangning Zhang, Jinlong Peng, Haoyang He, Xiangtai Li, Yabiao Wang, Chengjie Wang

Transformers have revolutionized the point cloud learning task, but the quadratic complexity hinders its extension to long sequence and makes a burden on limited computational resources.

Mamba

Single-temporal Supervised Remote Change Detection for Domain Generalization

no code implementations17 Apr 2024 Qiangang Du, Jinlong Peng, Xu Chen, Qingdong He, Liren He, Qiang Nie, Wenbing Zhu, Mingmin Chi, Yabiao Wang, Chengjie Wang

In this paper, we propose a multimodal contrastive learning (ChangeCLIP) based on visual-language pre-training for change detection domain generalization.

Change Detection Contrastive Learning +2

PointSeg: A Training-Free Paradigm for 3D Scene Segmentation via Foundation Models

no code implementations11 Mar 2024 Qingdong He, Jinlong Peng, Zhengkai Jiang, Xiaobin Hu, Jiangning Zhang, Qiang Nie, Yabiao Wang, Chengjie Wang

On top of that, PointSeg can incorporate with various foundation models and even surpasses the specialist training-based methods by 3. 4$\%$-5. 4$\%$ mAP across various datasets, serving as an effective generalist model.

Scene Segmentation

Stereo RGB and Deeper LIDAR Based Network for 3D Object Detection

no code implementations9 Jun 2020 Qingdong He, Zhengning Wang, Hao Zeng, Yijun Liu, Shuaicheng Liu, Bing Zeng

After aligning the interior points with fused features, the proposed network refines the prediction in a more accurate manner and encodes the whole box in a novel compact method.

3D Object Detection Autonomous Driving +2

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