Youwei Pang

👋 About Me

My Life

🌎 In my free time, I enjoy focused programming⌨️ (current Github ), patient reading📚, musical adventures🎧, fast running🏃‍♂️, slow swimming🏊‍♂️, city walking🚶‍♂️, and exploring delicious food🍲.
🤝 I work very closely with my best friend, Xiaoqi Zhao, on most of my projects.

My Experiences

2019-2025: School of Information and Communication Engineering, Dalian University of Technology (DUT)
Completed my Ph.D. in Signal and Information Processing.
Supervised by Prof. Lihe Zhang and Prof. Huchuan Lu (IEEE Fellow).

2021-2024: X3000 Inspection
Technology Partner at X3000 Inspection.
Focusing on algorithm design and deployment based on the machine vision.

2015-2019: School of Information and Communication Engineering, Dalian University of Technology (DUT)
Received the B.E. in Electronic and Information Engineering.

Research Interests

My current research interests include Deep Learning, Computer Vision, and Neural Network Design.

In particular, I focus on:

Multi-Task Joint Modeling:
- Natural Scene: Context-Dependent (CD) Concept Perception (Salient, Camouflaged, Shadow, Transparent, Change, ...), Remote Sensing Image Analysis, Semantic Segmentation
- Industrial Scene: Quality Inspection (Lithium Battery, Semiconductor)
- Medical Scene: Lesion, Organ, Tissue, ...
- General Architecture: RGB + RGB/Depth/Thermal/Temporal
- Task-Generic Paradigm: Unified Framework for CD Concept Understanding
Multi-Modal Data Integration:
- Vision (Multi-Sensor): RGB, Depth, Thermal, X-ray/CT, ...
- Vision (Multi-View): Scale, Edge, ...
- Vision (Multi-Moment): Temporal Cues (Optical Flow, Difference Map, Video Clip)
- Vision-Language: Open-Vocabulary Learning
Efficient Model Design:
- Lightweight Operation: Efficient Attention, Dynamic Convolution
- Scale-Generic Modeling: Tiny Object Perception, Industrial Quality Inspection
- Resolution Adaptability: High Resolution Object Segmentation

📢 News

2024-12 Finished defending my doctoral dissertation.

📂 Resource

2024-05-31 视觉与语言—开放词汇感知综述

💻 Project

Stars	Name	Description
	Hands-on-Docker (中文)	一份详尽的 Docker 使用指南。
	Awesome-Class-Activation-Map	An awesome list of papers and tools about the class activation map (CAM) technology.
	PyTorchTricks	Some tricks of pytorch…
	MethodsCmp	A Simple Toolkit for Counting the FLOPs/MACs, Parameters and FPS of Pytorch-based Methods.
	PySODEvalToolkit	A Python-based salient object detection and video object segmentation evaluation toolbox.
	PySODMetrics	A simple and efficient implementation of SOD metrcis.
	PyIRSTDMetrics	A simple and efficient implementation for the IRSTD performance analysis.
	PyLoss	Some loss functions for deeplearning.
	OpticalFlowBasedVOS	A simple and efficient codebase for the optical flow based video object segmentation.
	CoSaliencyProj	A project for co-saliency detection. Some codes are borrowed from ICNet (NIPS2020).
	RunIt	A simple program scheduler for your code on different devices.
	RegisterIt	Register it: A more flexible register for the DeepLearning project.
	mssim.pytorch	A better pytorch-based implementation for the mean structural similarity. Differentiable simpler SSIM and MS-SSIM.
	tta.pytorch	Test-Time Augmentation library for Pytorch.
	YuQueTools	A simple tool to download your own articles from yuque.
	ManageMyAttachments	Manage the attachments of your own obsidian vault.

📖 Paper

Preprint

CGCOD: Class-Guided Camouflaged Object Detection

Chenxi Zhang, Qing Zhang#, Jiayun Wu, Youwei Pang#

ArXiv 2024

[Paper (ArXiv)] [Code (GitHub)]

Inspiring the Next Generation of Segment Anything Models: Comprehensively Evaluate SAM and SAM 2 with Diverse Prompts Towards Context-Dependent Concepts under Different Scenes

Xiaoqi Zhao*, Youwei Pang*, Shijie Chang*, Yuan Zhao*, Lihe Zhang, Huchuan Lu, Jinsong Ouyang, Georges El Fakhri, Xiaofeng Liu

ArXiv 2024

[Paper (ArXiv)] [Code (GitHub)]

M2SNet: Multi-scale in Multi-scale Subtraction Network for Medical Image Segmentation

Xiaoqi Zhao, Hongpeng Jia, Youwei Pang, Long Lv, Feng Tian, Lihe Zhang, Weibing Sun, Huchuan Lu

The second place (2/100) in the MICCAI 2022 Challenge: Glaucoma Oct Analysis and Layer Segmentation (GOALS)

[Paper (ArXiv)]

Publication

ComPtr: Towards Diverse Bi-source Dense Prediction Tasks via A Simple yet General Complementary Transformer

Youwei Pang, Xiaoqi Zhao, Lihe Zhang, Huchuan Lu

Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 2025, IEEE

[DOI:10.1109/TPAMI.2025.3578494] [Paper (ArXiv)] [Code (GitHub)]

Segment Concealed Objects with Incomplete Supervision

Chunming He, Kai Li, Yachao Zhang, Ziyun Yang, Youwei Pang, Longxiang Tang, Chengyu Fang, Yulun Zhang, Linghe Kong, Xiu Li, Sina Farsiu

Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 2025, IEEE

[DOI:10.1109/TPAMI.2025.3576209] [Paper (IEEE Xplore)] [Code (GitHub)]

Beyond Mask: Rethinking Guidance Types in Few-shot Segmentation

Shijie Chang*, Youwei Pang*, Xiaoqi Zhao*, Lihe Zhang, Huchuan Lu

Pattern Recognition (PR) 2025, Elsevier

[Paper (ArXiv)] [Code (GitHub)]

Open-Vocabulary Camouflaged Object Segmentation

Youwei Pang*, Xiaoqi Zhao*, Jiaming Zuo, Lihe Zhang, Huchuan Lu

European Conference on Computer Vision (ECCV) 2024, Springer

[Paper (ArXiv)] [Code (GitHub)]

ZoomNeXt: A Unified Collaborative Pyramid Network for Camouflaged Object Detection

Youwei Pang*, Xiaoqi Zhao*, Tian-Zhu Xiang*, Lihe Zhang, Huchuan Lu

Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 2024, IEEE

[EI:20242616353583] [DOI:10.1109/TPAMI.2024.3417329] [Paper (ArXiv)] [Code (GitHub)]

Spider: A Unified Framework for Context-dependent Concept Understanding

Xiaoqi Zhao*, Youwei Pang*, Wei Ji*, Baicheng Sheng, Jiaming Zuo, Lihe Zhang, Huchuan Lu

International Conference on Machine Learning (ICML) 2024, PMLR

[EI:20243817053162] [Paper (ArXiv)] [Code]

Towards Automatic Power Battery Detection: New Challenge, Benchmark Dataset and Baseline

Xiaoqi Zhao*, Youwei Pang*, Zhenyu Chen, Qian Yu, Lihe Zhang, Hanqi Liu, Jiaming Zuo

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2024, IEEE

[EI:20244317260998] [DOI:10.1109/CVPR52733.2024.02079] [Paper (ArXiv)] [Project] [工源三仟公众号] [Code]

Multi-view Aggregation Network for Dichotomous Image Segmentation

Qian Yu*, Xiaoqi Zhao*, Youwei Pang*, Lihe Zhang, Huchuan Lu

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2024, IEEE Highlight

[EI:20244317260270] [DOI:10.1109/CVPR52733.2024.00376] [Paper (ArXiv)] [Code]

Towards Diverse Binary Segmentation via A Simple yet General Gated Network

Xiaoqi Zhao, Youwei Pang, Lihe Zhang, Huchuan Lu, Lei Zhang

International Journal of Computer Vision (IJCV) 2024, Springer

[EI:20241916055804] [WOS:001215379300003] [DOI:10.1007/s11263-024-02058-y] [Paper (ArXiv)] [Code]

Adaptive Multi-source Predictor for Zero-shot Video Object Segmentation

Xiaoqi Zhao, Shijie Chang, Youwei Pang, Jiaxing Yang, Lihe Zhang, Huchuan Lu

International Journal of Computer Vision (IJCV) 2024, Springer

[EI:20241015709995] [WOS:001176531200002] [DOI:10.1007/s11263-024-02024-8] [Paper (ArXiv)]

Adaptive Illumination Mapping for Shadow Detection in Raw Images

Jiayu Sun, Ke Xu, Youwei Pang, Lihe Zhang, Huchuan Lu, Gerhard Hancke, Rynson Lau

IEEE/CVF International Conference on Computer Vision (ICCV) 2023, IEEE

[EI:20240915634899] [WOS:001169499005013] [DOI:10.1109/ICCV51070.2023.01167] [Paper (CVF)] [Code]

CAVER: Cross-Modal View-Mixed Transformer for Bi-Modal Salient Object Detection

Youwei Pang, Xiaoqi Zhao, Lihe Zhang, Huchuan Lu

Transactions on Image Processing (TIP) 2023, IEEE

[EI:20230613542686] [WOS:000922870200004] (🏆 ESI Highly Cited Paper) [DOI:10.1109/TIP.2023.3234702] [Paper (ArXiv)] [Paper (IEEE)] [Code] [Project]

Joint Learning of Salient Object Detection, Depth Estimation and Contour Extraction

Xiaoqi Zhao, Youwei Pang, Lihe Zhang, Huchuan Lu

Transactions on Image Processing (TIP) 2022, IEEE

[EI:20225113272379] [WOS:000892917400002] [DOI:10.1109/TIP.2022.3222641] [Paper] [Code]

Zoom In and Out: A Mixed-scale Triplet Network for Camouflaged Object Detection

Youwei Pang*, Xiaoqi Zhao*, Tian-zhu Xiang, Lihe Zhang, Huchuan Lu

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2022, IEEE

[EI:20224613119658] [WOS:000867754202041] [DOI:10.1109/CVPR52688.2022.00220] [Paper] [Code] [Project]

Self-Supervised Pretraining for RGB-D Salient Object Detection

Xiaoqi Zhao, Youwei Pang, Lihe Zhang, Huchuan Lu, Xiang Ruan

Association for the Advancement of Artificial Intelligence (AAAI) 2022

[EI:20230713571733] [WOS:000893636203061] [Paper] [Slide&极市平台推送] [Code]

Multi-Source Fusion and Automatic Predictor Selection for Zero-Shot Video Object Segmentation

Xiaoqi Zhao, Youwei Pang, Jiaxing Yang, Lihe Zhang, Huchuan Lu

ACM International Conference on Multimedia (ACM MM) 2021 Oral

[EI:20214711200241] [WOS:001147786902077] [Paper] [Slide&极市平台推送] [Code]

Hierarchical Dynamic Filtering Network for RGB-D Salient Object Detection

Youwei Pang, Lihe Zhang, Xiaoqi Zhao, Huchuan Lu

European Conference on Computer Vision (ECCV) 2020, Springer

[EI:20205009617977] [DOI:10.1007/978-3-030-58595-2_15] [Paper] [Slide] [Code]

Suppress and Balance: A Simple Gated Network for Salient Object Detection

Xiaoqi Zhao*, Youwei Pang*, Lihe Zhang, Huchuan Lu, Lei Zhang

European Conference on Computer Vision (ECCV) 2020, Springer Oral

[EI:20205009597084] [DOI:10.1007/978-3-030-58536-5_3] [Paper] [Slide] [Code]

A Single Stream Network for Robust and Real-time RGB-D Salient Object Detection

Xiaoqi Zhao, Lihe Zhang, Youwei Pang, Huchuan Lu, Lei Zhang

European Conference on Computer Vision (ECCV) 2020, Springer

[EI:20205009601094] [DOI:10.1007/978-3-030-58542-6_39] [Paper] [Code]

Multi-scale Interactive Network for Salient Object Detection

Youwei Pang*, Xiaoqi Zhao*, Lihe Zhang, Huchuan Lu

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2020, IEEE

[EI:20204409431574] [WOS:001309199902028] [DOI:10.1109/CVPR42600.2020.00943] [Paper] [Code]