Zhiqiang Yuan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Zhiqiang Yuan has a total of 59 co-authors. Here are the top co-authors by number of shared publications:
- Xian Sun
Chinese Academy of Sciences
10 shared publications - Wenkai Zhang
Chinese Academy of Sciences, Aerospace Information Research Institute, Beijing, China
9 shared publications Hongqi Wang
Aerospace Information Research Institute and Key Laboratory of Network Information System Technology (NIST), Institute of Electronics, Chinese Academy of Sciences, Beijing, China
7 shared publicationsJialiang Chen
Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China
4 shared publications- Jie Zhou
WeChat AI, Tencent Inc., Beijing, China
4 shared publications - Jinchao Zhang
WeChat AI, Tencent Inc., Beijing, China
4 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 12969-12978
RAVA: Retrieval-Augmented Viewpoint Alignment for Subject-Driven Image Generation
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 12969-12978
Open AccessRAVA: Retrieval-Augmented Viewpoint Alignment for Subject-Driven Image Generation
- 26 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. PP (01628828) , 1-17
CoDA: Color Distribution Probing for Efficient and Generalizable AI-Generated Image Detection
AI-generated image detection faces a persistent trade-off between generalization and efficiency: lightweight artifact-based methods often degrade on unseen generators or domains, whereas more robust large-scale models are computationally expensive. Meanwhile, existing benchmarks mainly focus on cross-model evaluation in photorealistic settings, leaving cross-domain robustness underexplored. To address this gap, we introduce FakeForm, a large-scale benchmark with approximately 370,000 images across 62 diverse domains for both cross-model and cross-domain evaluation. Motivated by this broader setting, we revisit color-distribution probing as an efficient complementary cue for AI-generated image detection. We observe that, especially for photographic content, real photographs tend to exhibit smoother and more stable color patterns, whereas synthetic images often show characteristic color imbalances introduced by neural generation. Based on this observation, we propose CoDA, a compact 1.48M-parameter detector built on a Noise-Quantization Probe, together with a theoretical analysis linking probe responses to color non-uniformity. Experiments show that CoDA achieves state-of-the-art performance on standard benchmarks and the best results on the challenging cross-domain evaluation of FakeForm, while remaining highly competitive in cross-model photorealistic settings. These results suggest that persistent generative artifacts can provide a practical foundation for efficient and robust AI-generated image detection. The models and FakeForm benchmark will be made publicly available.
- 26 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. PP (01628828) , 1-17
CoDA: Color Distribution Probing for Efficient and Generalizable AI-Generated Image Detection
AI-generated image detection faces a persistent trade-off between generalization and efficiency: lightweight artifact-based methods often degrade on unseen generators or domains, whereas more robust large-scale models are computationally expensive. Meanwhile, existing benchmarks mainly focus on cross-model evaluation in photorealistic settings, leaving cross-domain robustness underexplored. To address this gap, we introduce FakeForm, a large-scale benchmark with approximately 370,000 images across 62 diverse domains for both cross-model and cross-domain evaluation. Motivated by this broader setting, we revisit color-distribution probing as an efficient complementary cue for AI-generated image detection. We observe that, especially for photographic content, real photographs tend to exhibit smoother and more stable color patterns, whereas synthetic images often show characteristic color imbalances introduced by neural generation. Based on this observation, we propose CoDA, a compact 1.48M-parameter detector built on a Noise-Quantization Probe, together with a theoretical analysis linking probe responses to color non-uniformity. Experiments show that CoDA achieves state-of-the-art performance on standard benchmarks and the best results on the challenging cross-domain evaluation of FakeForm, while remaining highly competitive in cross-model photorealistic settings. These results suggest that persistent generative artifacts can provide a practical foundation for efficient and robust AI-generated image detection. The models and FakeForm benchmark will be made publicly available.
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 6654-6662
ArtFRD: A Fisher-Rao Mixture Metric for Generative Model Aesthetic Evaluation
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 6654-6662
Open AccessArtFRD: A Fisher-Rao Mixture Metric for Generative Model Aesthetic Evaluation
- Open Access
Frequency Compensated Diffusion Model for Real-scene Dehazing
Due to distribution shift, deep learning based methods for image dehazing suffer from performance degradation when applied to real-world hazy images. In this paper, we consider a dehazing framework based on conditional diffusion models for improved generalization to real haze. First, we find that optimizing the training objective of diffusion models, i.e., Gaussian noise vectors, is non-trivial. The spectral bias of deep networks hinders the higher frequency modes in Gaussian vectors from being learned and hence impairs the reconstruction of image details. To tackle this issue, we design a network unit, named Frequency Compensation block (FCB), with a bank of filters that jointly emphasize the mid-to-high frequencies of an input signal. We demonstrate that diffusion models with FCB achieve significant gains in both perceptual and distortion metrics. Second, to further boost the generalization performance, we propose a novel data synthesis pipeline, HazeAug, to augment haze in terms of degree and diversity. Within the framework, a solid baseline for blind dehazing is set up where models are trained on synthetic hazy-clean pairs, and directly generalize to real data. Extensive evaluations show that the proposed dehazing diffusion model significantly outperforms state-of-the-art methods on real-world images. Our code is at https://github.com/W-Jilly/frequency-compensated-diffusion-model-pytorch.
Open AccessFrequency Compensated Diffusion Model for Real-scene Dehazing
Due to distribution shift, deep learning based methods for image dehazing suffer from performance degradation when applied to real-world hazy images. In this paper, we consider a dehazing framework based on conditional diffusion models for improved generalization to real haze. First, we find that optimizing the training objective of diffusion models, i.e., Gaussian noise vectors, is non-trivial. The spectral bias of deep networks hinders the higher frequency modes in Gaussian vectors from being learned and hence impairs the reconstruction of image details. To tackle this issue, we design a network unit, named Frequency Compensation block (FCB), with a bank of filters that jointly emphasize the mid-to-high frequencies of an input signal. We demonstrate that diffusion models with FCB achieve significant gains in both perceptual and distortion metrics. Second, to further boost the generalization performance, we propose a novel data synthesis pipeline, HazeAug, to augment haze in terms of degree and diversity. Within the framework, a solid baseline for blind dehazing is set up where models are trained on synthetic hazy-clean pairs, and directly generalize to real data. Extensive evaluations show that the proposed dehazing diffusion model significantly outperforms state-of-the-art methods on real-world images. Our code is at https://github.com/W-Jilly/frequency-compensated-diffusion-model-pytorch.
- 22 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 20 (1545598X) , 1-5
SeLo v2: Toward for Higher and Faster Semantic Localization
Semantic localization (SeLo) refers to locating the most relevant position in the Remote Sensing (RS) image based on the semantic information contained in the retrieved text, which is an emerging task based on cross-modal retrieval. SeLo achieves pixel-level semantic retrieval through caption-level annotations, which plays an important role in RS image-text retrieval. Although there are some researches on SeLo tasks at present, the current SeLo framework is still quite violent, which consumes a lot of resources. In this paper, based on the existing work, we conduct a more in-depth exploration and propose SeLo v2, which greatly improves the speed and accuracy of the SeLo task. First, based on the characteristics of regional consistency of remote sensing images, a multilevel likelihood expansion (MLE) is proposed to reduce the number of cross-modal similarity calculations, and the speed of SeLo task is greatly improved by combining single-scale clipping with multi-point multi-scale expansion. Next, to enhance the accuracy, we come up with the chaotic self-feeding mechanism (CSM), which performs semantic frequency enhancement to fully extract the semantic information contained in the caption, making the generated SeLo map more detailed and accurate. Compared with the initial SeLo framework, SeLo v2 has better semantic localization performance with only half the time consumed, which shows the great advantages of SeLo v2 in terms of time and accuracy. The proposed SeLo v2 is available at Link.
- 22 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 20 (1545598X) , 1-5
SeLo v2: Toward for Higher and Faster Semantic Localization
Semantic localization (SeLo) refers to locating the most relevant position in the Remote Sensing (RS) image based on the semantic information contained in the retrieved text, which is an emerging task based on cross-modal retrieval. SeLo achieves pixel-level semantic retrieval through caption-level annotations, which plays an important role in RS image-text retrieval. Although there are some researches on SeLo tasks at present, the current SeLo framework is still quite violent, which consumes a lot of resources. In this paper, based on the existing work, we conduct a more in-depth exploration and propose SeLo v2, which greatly improves the speed and accuracy of the SeLo task. First, based on the characteristics of regional consistency of remote sensing images, a multilevel likelihood expansion (MLE) is proposed to reduce the number of cross-modal similarity calculations, and the speed of SeLo task is greatly improved by combining single-scale clipping with multi-point multi-scale expansion. Next, to enhance the accuracy, we come up with the chaotic self-feeding mechanism (CSM), which performs semantic frequency enhancement to fully extract the semantic information contained in the caption, making the generated SeLo map more detailed and accurate. Compared with the initial SeLo framework, SeLo v2 has better semantic localization performance with only half the time consumed, which shows the great advantages of SeLo v2 in terms of time and accuracy. The proposed SeLo v2 is available at Link.
- 19 April 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 61 (01962892) , 1-12
Efficient and Controllable Remote Sensing Fake Sample Generation Based on Diffusion Model
In this paper, we propose an efficient remote sensing fake sample generation (RSFSG) framework based on the diffusion model, so as to generate controllable samples consistent with real scenes. Firstly, in order to alleviate the huge time consumption caused by the large parameters of the diffusion model, we come up with a multi-frequency dynamic knowledge distillation based on the consistent power spectrum of predicted Gaussian noise. The proposed multi-frequency knowledge transfer balances the ununiform output of the lightweight model by learning different frequency outputs during diffusion process at different stages. Secondly, to address the problem of slow training of diffusion models, we propose a progressive training strategy (PTS), inspired by the fitting mechanism of deep networks from low to high frequencies. PTS enables fast fitting of diffusion models by enabling the model to learn from low frequency information such as color at low resolution, and gradually move to high resolution images full of details such as texture. The established above two method achieve well generation performance under lightweight parameters, within almost half of the training time consumption. Extensive evaluations demonstrate that the proposed model significantly outperforms the state-of-the-art methods on RS controllable fake sample generation. With in our knowledge, we are the first work to introduce the diffusion model into the RSFSG task and obtain well performance, the code and the corresponding pre-trained files have released at Link.
- 19 April 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 61 (01962892) , 1-12
Efficient and Controllable Remote Sensing Fake Sample Generation Based on Diffusion Model
In this paper, we propose an efficient remote sensing fake sample generation (RSFSG) framework based on the diffusion model, so as to generate controllable samples consistent with real scenes. Firstly, in order to alleviate the huge time consumption caused by the large parameters of the diffusion model, we come up with a multi-frequency dynamic knowledge distillation based on the consistent power spectrum of predicted Gaussian noise. The proposed multi-frequency knowledge transfer balances the ununiform output of the lightweight model by learning different frequency outputs during diffusion process at different stages. Secondly, to address the problem of slow training of diffusion models, we propose a progressive training strategy (PTS), inspired by the fitting mechanism of deep networks from low to high frequencies. PTS enables fast fitting of diffusion models by enabling the model to learn from low frequency information such as color at low resolution, and gradually move to high resolution images full of details such as texture. The established above two method achieve well generation performance under lightweight parameters, within almost half of the training time consumption. Extensive evaluations demonstrate that the proposed model significantly outperforms the state-of-the-art methods on RS controllable fake sample generation. With in our knowledge, we are the first work to introduce the diffusion model into the RSFSG task and obtain well performance, the code and the corresponding pre-trained files have released at Link.
- Open Access
- 10 February 2023
- Published by MDPI AG in Remote Sensing
- Vol. 15 (4) , 986
Weakly Supervised Semantic Segmentation in Aerial Imagery via Cross-Image Semantic Mining
Weakly Supervised Semantic Segmentation (WSSS) with only image-level labels reduces the annotation burden and has been rapidly developed in recent years. However, current mainstream methods only employ a single image’s information to localize the target and do not account for the relationships across images. When faced with Remote Sensing (RS) images, limited to complex backgrounds and multiple categories, it is challenging to locate and differentiate between the categories of targets. As opposed to previous methods that mostly focused on single-image information, we propose CISM, a novel cross-image semantic mining WSSS framework. CISM explores cross-image semantics in multi-category RS scenes for the first time with two novel loss functions: the Common Semantic Mining (CSM) loss and the Non-common Semantic Contrastive (NSC) loss. In particular, prototype vectors and the Prototype Interactive Enhancement (PIE) module were employed to capture semantic similarity and differences across images. To overcome category confusions and closely related background interferences, we integrated the Single-Label Secondary Classification (SLSC) task and the corresponding single-label loss into our framework. Furthermore, a Multi-Category Sample Generation (MCSG) strategy was devised to balance the distribution of samples among various categories and drastically increase the diversity of images. The above designs facilitated the generation of more accurate and higher-granularity Class Activation Maps (CAMs) for each category of targets. Our approach is superior to the RS dataset based on extensive experiments and is the first WSSS framework to explore cross-image semantics in multi-category RS scenes and obtain cutting-edge state-of-the-art results on the iSAID dataset by only using image-level labels. Experiments on the PASCAL VOC2012 dataset also demonstrated the effectiveness and competitiveness of the algorithm, which pushes the mean Intersection-Over-Union (mIoU) to 67.3% and 68.5% on the validation and test sets of PASCAL VOC2012, respectively.
- 10 February 2023
- Published by MDPI AG in Remote Sensing
- Vol. 15 (4) , 986
Open AccessWeakly Supervised Semantic Segmentation in Aerial Imagery via Cross-Image Semantic Mining
Weakly Supervised Semantic Segmentation (WSSS) with only image-level labels reduces the annotation burden and has been rapidly developed in recent years. However, current mainstream methods only employ a single image’s information to localize the target and do not account for the relationships across images. When faced with Remote Sensing (RS) images, limited to complex backgrounds and multiple categories, it is challenging to locate and differentiate between the categories of targets. As opposed to previous methods that mostly focused on single-image information, we propose CISM, a novel cross-image semantic mining WSSS framework. CISM explores cross-image semantics in multi-category RS scenes for the first time with two novel loss functions: the Common Semantic Mining (CSM) loss and the Non-common Semantic Contrastive (NSC) loss. In particular, prototype vectors and the Prototype Interactive Enhancement (PIE) module were employed to capture semantic similarity and differences across images. To overcome category confusions and closely related background interferences, we integrated the Single-Label Secondary Classification (SLSC) task and the corresponding single-label loss into our framework. Furthermore, a Multi-Category Sample Generation (MCSG) strategy was devised to balance the distribution of samples among various categories and drastically increase the diversity of images. The above designs facilitated the generation of more accurate and higher-granularity Class Activation Maps (CAMs) for each category of targets. Our approach is superior to the RS dataset based on extensive experiments and is the first WSSS framework to explore cross-image semantics in multi-category RS scenes and obtain cutting-edge state-of-the-art results on the iSAID dataset by only using image-level labels. Experiments on the PASCAL VOC2012 dataset also demonstrated the effectiveness and competitiveness of the algorithm, which pushes the mean Intersection-Over-Union (mIoU) to 67.3% and 68.5% on the validation and test sets of PASCAL VOC2012, respectively.
- 24 November 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 60 (01962892) , 1-17
Weakly Supervised Semantic Segmentation in Aerial Imagery via Explicit Pixel-Level Constraints
In recent years, image-level weakly supervised semantic segmentation (WSSS) has developed rapidly in natural scenes due to the easy availability of classification tags. However, limited to complex backgrounds, multi-category scenes, and dense small targets in remote sensing (RS) images, relatively little research has been conducted in this field. To alleviate the impact of the above problems in RS scenes, a self-supervised Siamese network based on an explicit pixel-level constraints framework is proposed, which greatly improves the quality of class activation maps and the positioning accuracy in multi-category RS scenes. Specifically, there are three novel devices in this paper to promote performance to a new level: (a) A pixel-soft classification loss is proposed, which realizes explicit constraints on pixels during the image-level training; (b) A pixel global awareness module, which captures high-level semantic context and low-level pixel spatial information, is constructed to improve the consistency and accuracy of RS object segmentation; (c) A dynamic multi-scale fusion module with a gating mechanism is devised, which enhances feature representation and improves the positioning accuracy of RS objects, particularly on small and dense objects. Experiments on two RS challenge datasets demonstrate that these proposed modules achieve new state-of-the-art results by only using image-level labels, which improve mIoU to 36.79% on iSAID and 45.43% on ISPRS in the WSSS task. To the best of our knowledge, this is the first work to perform image-level WSSS on multi-class RS scenes.
- 24 November 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 60 (01962892) , 1-17
Weakly Supervised Semantic Segmentation in Aerial Imagery via Explicit Pixel-Level Constraints
In recent years, image-level weakly supervised semantic segmentation (WSSS) has developed rapidly in natural scenes due to the easy availability of classification tags. However, limited to complex backgrounds, multi-category scenes, and dense small targets in remote sensing (RS) images, relatively little research has been conducted in this field. To alleviate the impact of the above problems in RS scenes, a self-supervised Siamese network based on an explicit pixel-level constraints framework is proposed, which greatly improves the quality of class activation maps and the positioning accuracy in multi-category RS scenes. Specifically, there are three novel devices in this paper to promote performance to a new level: (a) A pixel-soft classification loss is proposed, which realizes explicit constraints on pixels during the image-level training; (b) A pixel global awareness module, which captures high-level semantic context and low-level pixel spatial information, is constructed to improve the consistency and accuracy of RS object segmentation; (c) A dynamic multi-scale fusion module with a gating mechanism is devised, which enhances feature representation and improves the positioning accuracy of RS objects, particularly on small and dense objects. Experiments on two RS challenge datasets demonstrate that these proposed modules achieve new state-of-the-art results by only using image-level labels, which improve mIoU to 36.79% on iSAID and 45.43% on ISPRS in the WSSS task. To the best of our knowledge, this is the first work to perform image-level WSSS on multi-class RS scenes.
- Open Access
- 3 November 2022
- Published by Elsevier in International Journal of Applied Earth Observation and Geoinformation
- Vol. 115
MCRN: A Multi-source Cross-modal Retrieval Network for remote sensing
- 3 November 2022
- Published by Elsevier in International Journal of Applied Earth Observation and Geoinformation
- Vol. 115
Open AccessMCRN: A Multi-source Cross-modal Retrieval Network for remote sensing