Xiaoqi (Jackie) Zhao 赵骁骐

Radiology & Biomedical Imaging, Yale University

Email: xiaoqi.zhao[at]yale.edu

GitHub
Google Scholar

Biography

I am a Postdoctoral Researcher at Yale University working with Prof. Xiaofeng Liu and Prof. Georges El Fakhri (AIMBE and IEEE Fellow). Previously, I received my Ph.D. degree in Signal and Information Processing from the Dalian University of Technology (DUT) in 2024, where I conducted my research at the IIAU-Lab under the supervision of Prof. Lihe Zhang and Prof. Huchuan Lu (IEEE Fellow). I also obtained my B.E. degree in Electronic Information Engineering from DUT in 2019. Beyond academic research, I am deeply passionate about AI + X entrepreneurship. I am a Founding Partner of X3000 INSPECTION (Startup, Series A+). From 2021 to 2024, I served as its Chief AI Scientist, leading the development of X3000Former, X3000NeXt and other foundational models for power battery generation and inspection, which have been deployed to serve top power battery companies.

Research Fields

My research aims to develop a general-purpose visual intelligence engine that supports multi-source inputs, multi-task processing, multi-modal fusion, and cross-domain generalization. This engine is designed to balance expert-level performance in specific scenarios with unified modeling across diverse visual tasks, laying the foundation for semantic understanding and generalizable perception in future visual AGI systems. In recent years, my work has spanned both theoretical advancements and practical deployments, focusing on four core areas: Unified Visual Perception Systems, Industrial X-ray/CT Machine Vision (Ai4Industry), Multi-modal Collaborative Medical Image Analysis (Ai4Health), and Self-driven Learning Mode.

Unified Visual Perception System
- Context-Dependent Multi-Concept Understanding Models
- Unified Multi-modal/Image-Video/Multi-view Models
Representative works: Spider (ICML'24), GateNet (IJCV'24 & ECCV'20), UniMRSeg (NeurIPS'25), UniMMAD (arXiv'25), UniFSS (PR'25), SAM-EVA (arXiv'25), ComPtr (PAMI'25), MoSE (CVPR'25), SR-ICL (CVPR'25), MS-ASP (IJCV'24 & MM'21), ZoomNeXt (PAMI'24), MVANet (CVPR'24), MMFT (TIP'23)
Industrial X-ray/CT/Surface Machine Vision (Ai4Industry)
- Power Battery Image Detection and Generation
- Unsupervised Anomaly Detection
- Industrial CT Reconstruction
- Industrial Blind Image Enhancement
Representative works: MDCNet (CVPR'24), MDCNeXt (arXiv'25), UniMMAD (arXiv'25), DGDM (TCSVT'25)
Multi-modal Collaborative Medical Image Analysis (Ai4Health)
- Unified Modality-Relax Imaging and Segmentation
- Medical Generalist
Representative works: UniMRSeg (NeurIPS'25), SR-ICL (CVPR'25)
Self-driven Learning Mode
- Self-supervised/Unsupervised/Few-shot/In-context/Prompt/Open-Vocabulary Learning
Representative works: SSLSOD (AAAI'22), Spider (ICML'24), UniMRSeg (NeurIPS'25), OVCoser (ECCV'24), UniMMAD (arXiv'25), DGDM (TCSVT'25), UniFSS (PR'25), SAM-EVA (arXiv'25), SR-ICL (CVPR'25)

News

[09/2025] Two papers accepted at NeurIPS 2025.
[08/2025] I was nominated as a Rising Star at WAIC Yunfan!
[02/2025] Our ComPtr (General Bi-source Transformer Model) was accepted by TPAMI 2025. Congratulations to Youwei!
[02/2025] Two papers accepted at CVPR 2025. Congratulations to Shijie and Jia!
[01/2025] Our CAVER (IEEE TIP 2023) is an ESI Highly Cited Paper (Top 1%).
[12/2024] I successfully defended my PhD dissertation! Call me Dr. Zhao! 😎😎😎
[08/2024] X3000 INSPECTION finished Series A and A+ financing rounds. 🎉🎉🎉 Ai4EVSafety is all you need!
[07/2024] One paper accepted at ECCV 2024. New Task! Open-Vocabulary Camouflaged Object Segmentation.
[06/2024] One paper accepted at TPAMI 2024.
[05/2024] One paper accepted at ICML 2024.
[03/2024] One paper accepted at IJCV 2024.
[02/2024] Two papers accepted at CVPR 2024 (1 highlight ~3% [324/11532]). Congratulations to Qian!
[01/2024] One paper accepted at IJCV 2024.
[07/2023] One paper accepted at ICCV 2023. Congratulations to Yichen!
[01/2023] One paper accepted at IEEE TIP 2023.
[12/2022] One paper accepted at IEEE TIP 2022.
[03/2022] One paper accepted at CVPR 2022.
[11/2021] One paper accepted at AAAI 2022 (~15% [1349/9020]).
[07/2021] One paper accepted at ACM MM 2021 (oral ~9% [179/1942]).
[06/2021] One paper accepted at MICCAI 2021.
[07/2020] Three papers accepted at ECCV 2020 (1 oral ~2% [104/5025]).
[03/2020] One paper accepted at CVPR 2020.

Awesome-AI4X-NSCLR-Papers

A curated collection of AI+X papers published in Nature / Science / Cell / Lancet / Radiology and their flagship sub-journals.

Python

Awesome-Open-Vision-Problem-Modeling

Awesome List for Diverse Open Vision Problems and Modeling Solutions.

Python

Awesome-Unified-Context-dependent-Concept-Segmentation

Awesome List for Unified Context-dependent Concept Segmentation.

Python

SAMs-CDConcepts-Eval

Comprehensively Evaluate SAM and SAM 2 with Diverse Prompts Towards Context-Dependent Concepts under Different Scenes.

Python

PySegMetrics

A Python-based Simple yet Efficient Evaluation Toolbox for Segmentation-like tasks.

Python

Honor

2025 WAIC Yunfan Award, Rising Star Nomination (10 winners worldwide)
2025 Profiled by People’s Daily《人民日报》as an Outstanding PhD Student Representative (100 PhD students nationwide; 1 PhD student from DLUT)
2020-2024 AI 2000 Most Influential Scholars by Aminer in Computer Vision
2022 & 2024 Doctoral National Scholarship
2023 3rd Place in Video Semantic Segmentation Track of the CVPR PVUW challenge
2023 Gold Award of The 8th China International College Students' 'Internet+' Innovation and Entrepreneurship Competition (Company/Project: 工源三仟; ~0.05‰[161/3,400,000+])
2022 CVPR 2022 Outstanding Reviewer (~2%[156/6247])
2022 Huawei Camera, Academic Rising Star Award (8 winners worldwide; 170,000+ viewers watched the live talk; 30,000 RMB bonus)
2022 MICCAI Challenge: Glaucoma Oct Analysis and Layer Segmentation (GOALS) (Team: IIAU-Segmentors; Glaucoma Detection:1/100; OCT Layer Segmentation: 3/100; GOALS: 2/100; $1,300 bonus)
2019-2024 Outstanding graduate student of Dalian University of Technology
2018 3rd place of OPPO Top AI Competition (Portrait Segmentation) (3/456; 50,000 RMB bonus)

Academic Service

Program Committee or Reviewer
Conference on Computer Vision and Pattern Recognition (CVPR), 2022-2025 (Outstanding Reviewer ~2%[156/6247])
International Conference on Computer Vision (ICCV), 2021-2025
European Conference on Computer Vision (ECCV), 2022-2024
AAAI Conference on Artificial Intelligence (AAAI), 2022-2026
Neural Information Processing Systems (NeurIPS), 2023-2025
International Conference on Learning Representations (ICLR), 2024-2026
International Conference on Machine Learning (ICML), 2024-2025
Regular Journal Reviewer and Guest Editor
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
International Journal of Computer Vision (IJCV)
IEEE Transactions on Image Processing (TIP)
IEEE Transactions on Medical Imaging (TMI)
Guest Editor of the J. Imaging Special Issue

Publications [Google Scholar (3,800 + citations)]

TPAMI/IJCV/TIP: 7
NeurIPS/ICML/CVPR/ECCV/ICCV/AAAI/MM/MICCAI: 17 (2 oral, 1 highlight)
Papers with 500+ Citations: 2
Papers with 100+ Citations: 9
Papers as First/co-First/Last Author: 19

arXiv 2025	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, Chenyang Yu, Hanqi Liu, Jiaming Zuo, Jinsong Ouyang, Weisi Lin, Georges El Fakhri, Huchuan Lu, Xiaofeng Liu arXiv, 2025. Code arXiv
arXiv 2025	Power Battery Detection Xiaoqi Zhao, Peiqian Cao, Chenyang Yu, Zonglei Feng, Lihe Zhang, Hanqi Liu, Jiaming Zuo, Youwei Pang, Jinsong Ouyang, Weisi Lin, Georges El Fakhri, Huchuan Lu, Xiaofeng Liu arXiv, 2025. Code arXiv
arXiv 2025	UniMMAD: Unified Multi-Modal and Multi-Class Anomaly Detection via MoE-Driven Feature Decompression Yuan Zhao, Youwei Pang, Lihe Zhang, Hanqi Liu, Jiaming Zuo, Huchuan Lu, Xiaoqi Zhao arXiv, 2025. Code arXiv
NeurIPS 2025	UniMRSeg: Unified Modality-Relax Segmentation via Hierarchical Self-Supervised Compensation Xiaoqi Zhao, Youwei Pang, Chenyang Yu, Lihe Zhang, Huchuan Lu, Shijian Lu, Georges El Fakhri, Xiaofeng Liu Neural Information Processing Systems (NeurIPS), 2025. Code arXiv
NeurIPS 2025	Rethinking Evaluation of Infrared Small Target Detection Youwei Pang, Xiaoqi Zhao, Lihe Zhang, Huchuan Lu, Georges El Fakhri, Xiaofeng Liu, Shijian Lu Neural Information Processing Systems (NeurIPS), 2025. Code arXiv
TPAMI 2025	ComPtr: Toward Diverse Bi-Source Dense Prediction Tasks via a Simple Yet General Complementary Transformer Youwei Pang, Xiaoqi Zhao, Lihe Zhang, Huchuan Lu IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2025. Code arXiv
CVPR 2025	Unified Medical Lesion Segmentation via Self-referring Indicator Shijie Chang, Xiaoqi Zhao, Lihe Zhang, Tiancheng Wang IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2025. Code arXiv
CVPR 2025	Mixture-of-Shape-Experts (MoSE): End-to-End Shape Dictionary Framework to Prompt SAM for Generalizable Medical Segmentation Jia Wei, Xiaoqi Zhao, Jonghye Woo, Jinsong Ouyang, Georges El Fakhri, Qingyu Chen, Xiaofeng Liu IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2025. Code arXiv
PR 2025	Beyond Mask: Rethinking Guidance Types in Few-shot Segmentation Shijie Chang, Youwei Pang, Xiaoqi Zhao, Huchuan Lu, Lihe Zhang Pattern Recognition (PR), 2025. Code arXiv

ICML 2024	Spider: A Unified Framework for Context-dependent Concept Segmentation Xiaoqi Zhao, Youweii Pang, Wei Ji, Baicheng Sheng, Jiaming Zuo, Lihe Zhang, Huchuan Lu [Interpretation by CVHub (8,000 + views)] International Conference on Machine Learning (ICML), 2024. Code arXiv
CVPR 2024	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, Huchuan Lu [Interpretation by 极市平台] [Interpretation by X3000 INSPECTION] IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024. Code arXiv
CVPR 2024 Highlight	Multi-view Aggregation Network for Dichotomous Image Segmentation Qian Yu, Xiaoqi Zhao, Youwei Pang, Lihe Zhang, Huchuan Lu IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024. Highlight Code arXiv
ECCV 2024	Open-Vocabulary Camouflaged Object Segmentation Youwei Pang, Xiaoqi Zhao, Jiaming Zuo, Lihe Zhang, Huchuan Lu [Interpretation by CVHub (7,000 + views)] European Conference on Computer Vision (ECCV), 2024. Code arXiv
IJCV 2024	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. Code arXiv
IJCV 2024	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. Code arXiv
TPAMI 2024	ZoomNeXt: A Unified Collaborative Pyramid Network for Camouflaged Object Detection Youwei Pang, Xiaoqi Zhao, Tian-Zhu Xiang, Lihe Zhang, Huchuan Lu IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2024. Code arXiv

MICCAI Challenge	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 [Interpretation by 极市平台 (6,000 + views)] [Interpretation by CVHub (4,000 + views)] 🏆The second place (2/100) in the MICCAI 2022 Challenge: Glaucoma Oct Analysis and Layer Segmentation (GOALS). Code arXiv
CVPR Challenge	3rd Place Solution for PVUW2023 VSS Track: A Large Model for Semantic Segmentation on VSPW Shijie Chang, Zeqi Hao, Ben Kang, Xiaoqi Zhao, Jiawen Zhu, Zhenyu Chen, Lihe Zhang, Lu Zhang, Huchuan Lu 🏆The third place in video semantic segmentation track of the CVPR 2023 PVUW challenge. Code arXiv
TIP 2023	CAVER: Cross-Modal View-Mixed Transformer for Bi-Modal Salient Object Detection Youwei Pang, Xiaoqi Zhao, Lihe Zhang, Huchuan Lu ESI Highly Cited Paper (1%) IEEE Transactions on Image Processing (TIP), 2023. Code arXiv
ICCV 2023	Isomer: Isomerous Transformer for Zero-shot Video Object Segmentation Yichen Yuan, Yifan Wang, Lijun Wang, Xiaoqi Zhao, Huchuan Lu, Yu Wang, Weibo Su, Lei Zhang IEEE International Conference on Computer Vision (ICCV), 2023. Code arXiv

TIP 2022	Joint Learning of Salient Object Detection, Depth Estimation and Contour Extraction Xiaoqi Zhao, Youwei Pang, Lihe Zhang, Huchuan Lu IEEE Transactions on Image Processing (TIP), 2022. Code arXiv
AAAI 2022	Self-Supervised Pretraining for RGB-D Salient Object Detection Xiaoqi Zhao, Youwei Pang, Lihe Zhang, Huchuan Lu, Xiang Ruan [Interpretation by 极市平台 (3,000 + views)] Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI), 2022. Code arXiv
CVPR 2022	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 Conference on Computer Vision and Pattern Recognition (CVPR), 2022. Code arXiv

MM 2021 Oral	Multi-Source Fusion and Automatic Predictor Selection for Zero-Shot Video Object Segmentation Xiaoqi Zhao, Youwei Pang, Jiaxing Yang, Lihe Zhang, Huchuan Lu [Interpretation by 极市平台 (2,000 + views)] ACM International Conference on Multimedia (MM), 2021. Oral Code arXiv
MICCAI 2021	Automatic Polyp Segmentation via Multi-scale Subtraction Network Xiaoqi Zhao, Lihe Zhang, Huchuan Lu 🔥Top 1% Most Cited MICCAI 2021 Papers & 🏆Ranking Top 1 in Colonoscopy Diagnosis Field [Link] International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), 2021. Code arXiv

ECCV 2020 Oral	Suppress and Balance: A Simple Gated Network for Salient Object Detection Xiaoqi Zhao, Youwei Pang, Lihe Zhang, Huchuan Lu, Lei Zhang 🔥Top 3% Most Cited ECCV 2020 Papers & 🏆Ranking Top 1 in Visual Saliency Field [Link] European Conference on Computer Vision (ECCV), 2020. Oral Code arXiv
ECCV 2020	A Single Stream Network for Robust and Real-time RGB-D Salient Object Detection Xiaoqi Zhao, Youwei Pang, Lihe Zhang, Huchuan Lu, Lei Zhang European Conference on Computer Vision (ECCV), 2020. Code arXiv
ECCV 2020	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. Code arXiv
CVPR 2020	Multi-scale Interactive Network for Salient Object Detection Youwei Pang, Xiaoqi Zhao, Lihe Zhang, Huchuan Lu 🔥Top 4% Most Cited CVPR 2020 Papers & 🏆Ranking Top 1 in Visual Saliency Field [Link] IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020. Code arXiv