Yanpeng Sun
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yanpeng Sun has a total of 27 co-authors. Here are the top co-authors by number of shared publications:
- Zechao Li
Nanjing University of Science and Technology
12 shared publications - Jinhui Tang
Nanjing Forestry University, Nanjing, China
3 shared publications - Haiqi Zhang
Nanjing University of Science and Technology
2 shared publications - Hao Tang
Centre for Smart Health, The Hong Kong Polytechnic University, Hong Kong, SAR, China
2 shared publications Jingdong Wang
Visual Technology Department, Baidu, Beijing, China
2 shared publications- Lu Jin
School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China
2 shared publications
Latest Publications
- 23 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (6) , 8675-8686
FineG-RAG: Fine-Grained Retrieval-Augmented Generation for Multimodal Large Language Models
Fine-grained visual recognition refers to the ability to distinguish subtle differences between visually similar objects— a fundamental yet challenging capability for Multimodal Large Language Models (MLLMs). In this paper, we observe that even strong open-source MLLMs, such as Qwen2-VL and InternVL2, still struggle with accurately identifying fine-grained categories. These models often fail to attend to subtle but critical details for precise discrimination. To unlock this potential, we propose FineG-RAG, a retrieval-augmented generation pipeline designed to enhance the fine-grained recognition capabilities of MLLMs. FineG-RAG integrates external fine-grained knowledge into the recognition process via a generalized retriever. To support this, we construct fine-grained visual-language knowledge database containing representative images with wide visual diversity and expert-crafted attribute descriptions from multiple perspectives. Relevant fine-grained knowledge is retrieved from this database and fed into a visual-language augmented prompt, which provides rich multimodal context to guide MLLMs in generating accurate labels. To better evaluate the fine-grained recognition capabilities of MLLMs, we design a multiple-choice evaluation strategy based on publicly four fine-grained datasets. Extensive experiments demonstrate that FineG-RAG consistently outperforms baseline methods, achieving superior recognition accuracy across a range of off-the-shelf, open-source MLLMs.
- 23 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (6) , 8675-8686
FineG-RAG: Fine-Grained Retrieval-Augmented Generation for Multimodal Large Language Models
Fine-grained visual recognition refers to the ability to distinguish subtle differences between visually similar objects— a fundamental yet challenging capability for Multimodal Large Language Models (MLLMs). In this paper, we observe that even strong open-source MLLMs, such as Qwen2-VL and InternVL2, still struggle with accurately identifying fine-grained categories. These models often fail to attend to subtle but critical details for precise discrimination. To unlock this potential, we propose FineG-RAG, a retrieval-augmented generation pipeline designed to enhance the fine-grained recognition capabilities of MLLMs. FineG-RAG integrates external fine-grained knowledge into the recognition process via a generalized retriever. To support this, we construct fine-grained visual-language knowledge database containing representative images with wide visual diversity and expert-crafted attribute descriptions from multiple perspectives. Relevant fine-grained knowledge is retrieved from this database and fed into a visual-language augmented prompt, which provides rich multimodal context to guide MLLMs in generating accurate labels. To better evaluate the fine-grained recognition capabilities of MLLMs, we design a multiple-choice evaluation strategy based on publicly four fine-grained datasets. Extensive experiments demonstrate that FineG-RAG consistently outperforms baseline methods, achieving superior recognition accuracy across a range of off-the-shelf, open-source MLLMs.
- 6 March 2026
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 134 (4) , 145
CylindFormer: Image-to-Point Cloud Registration with Cylindrical Transformer
- 6 March 2026
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 134 (4) , 145
CylindFormer: Image-to-Point Cloud Registration with Cylindrical Transformer
- Top Cited Papers
- 20 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 28 (15209210) , 3739-3754
Visual Position Prompt for MLLM Based Visual Grounding
Although Multimodal Large Language Models (MLLMs) excel at various image-related tasks, they encounter challenges in precisely aligning coordinates with spatial information within images, particularly in position-aware tasks such as visual grounding. This limitation arises from two key factors. First, MLLMs lack explicit spatial references, making it difficult to associate textual descriptions with precise image locations. Second, their feature extraction processes prioritize global context over fine-grained spatial details, leading to weak localization capability. To address these issues, we introduce VPP-LLaVA, an MLLM enhanced with Visual Position Prompt (VPP) to improve its grounding capability. VPP-LLaVA integrates two complementary mechanisms: the global VPP overlays a learnable, axis-like tensor onto the input image to provide structured spatial cues, while the local VPP incorporates position-aware queries to support fine-grained localization. To effectively train our model with spatial guidance, we further introduce VPP-SFT, a curated dataset of 0.6 M high-quality visual grounding samples. Designed in a compact format, it enables efficient training and is significantly smaller than datasets used by other MLLMs (e.g., 21 M samples in MiniGPT-v2), yet still provides a strong performance boost. The resulting model, VPP-LLaVA, not only achieves state-of-the-art results on standard visual grounding benchmarks but also demonstrates strong zero-shot generalization to challenging unseen datasets.
- 20 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 28 (15209210) , 3739-3754
Top Cited PapersVisual Position Prompt for MLLM Based Visual Grounding
Although Multimodal Large Language Models (MLLMs) excel at various image-related tasks, they encounter challenges in precisely aligning coordinates with spatial information within images, particularly in position-aware tasks such as visual grounding. This limitation arises from two key factors. First, MLLMs lack explicit spatial references, making it difficult to associate textual descriptions with precise image locations. Second, their feature extraction processes prioritize global context over fine-grained spatial details, leading to weak localization capability. To address these issues, we introduce VPP-LLaVA, an MLLM enhanced with Visual Position Prompt (VPP) to improve its grounding capability. VPP-LLaVA integrates two complementary mechanisms: the global VPP overlays a learnable, axis-like tensor onto the input image to provide structured spatial cues, while the local VPP incorporates position-aware queries to support fine-grained localization. To effectively train our model with spatial guidance, we further introduce VPP-SFT, a curated dataset of 0.6 M high-quality visual grounding samples. Designed in a compact format, it enables efficient training and is significantly smaller than datasets used by other MLLMs (e.g., 21 M samples in MiniGPT-v2), yet still provides a strong performance boost. The resulting model, VPP-LLaVA, not only achieves state-of-the-art results on standard visual grounding benchmarks but also demonstrates strong zero-shot generalization to challenging unseen datasets.
- 12 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (5) , 6374-6389
SSP-SAM: SAM With Semantic-Spatial Prompt for Referring Expression Segmentation
The Segment Anything Model (SAM) excels at general image segmentation but has limited ability to understand natural language, which restricts its direct application in Referring Expression Segmentation (RES). Toward this end, we propose SSP-SAM, a framework that fully utilizes SAM’s segmentation capabilities by integrating a Semantic-Spatial Prompt (SSP) encoder. Specifically, we incorporate both visual and linguistic attention adapters into the SSP encoder, which highlight salient objects within the visual features and discriminative phrases within the linguistic features. This design enhances the referent representation for the prompt generator, resulting in high-quality SSPs that enable SAM to generate precise masks guided by language. Although not specifically designed for Generalized RES (GRES), where the referent may correspond to zero, one, or multiple objects, SSP-SAM naturally supports this more flexible setting without additional modifications. Extensive experiments on widely used RES and GRES benchmarks confirm the superiority of our method. Notably, our approach generates segmentation masks of high quality, achieving strong precision even at strict thresholds such as Pr@0.9. Further evaluation on the PhraseCut dataset demonstrates improved performance in open-vocabulary scenarios compared to existing state-of-the-art RES methods. The code and checkpoints are available at: https://github.com/WayneTomas/SSP-SAM.
- 12 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (5) , 6374-6389
SSP-SAM: SAM With Semantic-Spatial Prompt for Referring Expression Segmentation
The Segment Anything Model (SAM) excels at general image segmentation but has limited ability to understand natural language, which restricts its direct application in Referring Expression Segmentation (RES). Toward this end, we propose SSP-SAM, a framework that fully utilizes SAM’s segmentation capabilities by integrating a Semantic-Spatial Prompt (SSP) encoder. Specifically, we incorporate both visual and linguistic attention adapters into the SSP encoder, which highlight salient objects within the visual features and discriminative phrases within the linguistic features. This design enhances the referent representation for the prompt generator, resulting in high-quality SSPs that enable SAM to generate precise masks guided by language. Although not specifically designed for Generalized RES (GRES), where the referent may correspond to zero, one, or multiple objects, SSP-SAM naturally supports this more flexible setting without additional modifications. Extensive experiments on widely used RES and GRES benchmarks confirm the superiority of our method. Notably, our approach generates segmentation masks of high quality, achieving strong precision even at strict thresholds such as Pr@0.9. Further evaluation on the PhraseCut dataset demonstrates improved performance in open-vocabulary scenarios compared to existing state-of-the-art RES methods. The code and checkpoints are available at: https://github.com/WayneTomas/SSP-SAM.
- 3 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 48 (3) , 2296-2311
Refine, Control and Distill: A Text-to-Image Framework for Faithful Image Generation
While text-to-image diffusion models exhibit outstanding results, they struggle to faithfully generate key subjects with corresponding attributes in prompts, challenges known as catastrophic neglect and attribute binding. Previous works typically utilize attention adjustments to solve the above problems, whereas we observe that they may still generate unfaithful images. In this paper, we carefully analyze the text-to-image process and pinpoint three pivotal bottlenecks that hinder image faithful generation: (1) unequal responses of neglected subjects in text embedding, (2) competition and entanglement between subjects’ attention, and (3) suboptimal quality of intermediate features from U-Net. Based on the aforementioned observations, we propose a Refine, Control, and Distill (RCD) framework built upon the stable diffusion model to alleviate the negative effects raised by the bottlenecks mentioned above, respectively. Specifically, we achieve the above goals through a text embedding refinement module, three region-level attention control losses, and self-distillation of intermediate semantic features in the denoising process. Our approach exhibits promising capability in generating faithful and high-quality images and outperforms state-of-the-art methods through extensive quantitative and qualitative evaluations on recent advanced base diffusion models.
- 3 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 48 (3) , 2296-2311
Refine, Control and Distill: A Text-to-Image Framework for Faithful Image Generation
While text-to-image diffusion models exhibit outstanding results, they struggle to faithfully generate key subjects with corresponding attributes in prompts, challenges known as catastrophic neglect and attribute binding. Previous works typically utilize attention adjustments to solve the above problems, whereas we observe that they may still generate unfaithful images. In this paper, we carefully analyze the text-to-image process and pinpoint three pivotal bottlenecks that hinder image faithful generation: (1) unequal responses of neglected subjects in text embedding, (2) competition and entanglement between subjects’ attention, and (3) suboptimal quality of intermediate features from U-Net. Based on the aforementioned observations, we propose a Refine, Control, and Distill (RCD) framework built upon the stable diffusion model to alleviate the negative effects raised by the bottlenecks mentioned above, respectively. Specifically, we achieve the above goals through a text embedding refinement module, three region-level attention control losses, and self-distillation of intermediate semantic features in the denoising process. Our approach exhibits promising capability in generating faithful and high-quality images and outperforms state-of-the-art methods through extensive quantitative and qualitative evaluations on recent advanced base diffusion models.
- 24 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 23 (2) , 2198-2214
Gradient Pruning Interactive Attack for Vision-Language Pre-Training Models
Vision-Language Pre-training (VLP) models exhibit pronounced vulnerability to multimodal adversarial examples, necessitating rigorous robustness research, particularly for transferable attacks in black-box scenarios. Current research predominantly enhances attack transferability across VLP models by diversifying image and text inputs. However, during adversarial example generation, these methods often prioritize amplifying inter-modal semantic discrepancies (i.e., modality-discrepancy features) while overlooking model-specific semantic features critical to transferable attacks. To address this limitation, we pro pose a transferable Gradient Pruning Interactive Attack (GPI Attack), which integrates gradient-pruned image perturbations with semantic-oriented text perturbations through modality interaction. For image attacks, extreme backpropagated gradients may cause adversarial examples to highlight certain model specific features, leading to poor transferability. To suppress this feature, the textual modality guides the pruning of extreme gradients within intermediate VLP blocks, and these pruned gradients are subsequently employed to direct the generation of adversarial images. For text attacks, we consolidate the perturbation process solely at the embedding level, which reduces semantic discrepancies across hierarchical structures and significantly enhances the generalizability of adversarial texts. Experimental results demonstrate the effectiveness of GPI-Attack in image text retrieval tasks on multimodal datasets such as Flickr30K and MSCOCO. Additionally, the proposed gradient pruning technique is plug-and-play, showing performance improvements even when applied to baseline methods, indicating its potential as a valuable enhancement for attack performance.
- 24 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 23 (2) , 2198-2214
Gradient Pruning Interactive Attack for Vision-Language Pre-Training Models
Vision-Language Pre-training (VLP) models exhibit pronounced vulnerability to multimodal adversarial examples, necessitating rigorous robustness research, particularly for transferable attacks in black-box scenarios. Current research predominantly enhances attack transferability across VLP models by diversifying image and text inputs. However, during adversarial example generation, these methods often prioritize amplifying inter-modal semantic discrepancies (i.e., modality-discrepancy features) while overlooking model-specific semantic features critical to transferable attacks. To address this limitation, we pro pose a transferable Gradient Pruning Interactive Attack (GPI Attack), which integrates gradient-pruned image perturbations with semantic-oriented text perturbations through modality interaction. For image attacks, extreme backpropagated gradients may cause adversarial examples to highlight certain model specific features, leading to poor transferability. To suppress this feature, the textual modality guides the pruning of extreme gradients within intermediate VLP blocks, and these pruned gradients are subsequently employed to direct the generation of adversarial images. For text attacks, we consolidate the perturbation process solely at the embedding level, which reduces semantic discrepancies across hierarchical structures and significantly enhances the generalizability of adversarial texts. Experimental results demonstrate the effectiveness of GPI-Attack in image text retrieval tasks on multimodal datasets such as Flickr30K and MSCOCO. Additionally, the proposed gradient pruning technique is plug-and-play, showing performance improvements even when applied to baseline methods, indicating its potential as a valuable enhancement for attack performance.
- 29 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 20 (15566013) , 5663-5677
Modality-Specific Interactive Attack for Vision-Language Pre-Training Models
Recent advances have heightened the interest in the adversarial transferability of Vision-Language Pre-training (VLP) models. However, most existing strategies constrained by two persistent limitations: suboptimal utilization of cross-modal interactive information, and inherent discrepancies across hierarchical textual representation. To address these challenges, we propose the Modality-Specific Interactive Attack (MSI-Attack), a novel approach that integrates semantic-level image perturbations with embedding-level text perturbations, all while maintaining minimal inter-modal constraints. In our image attack methodology, we introduce Multi-modal Integrated Gradients (MIG) to guide perturbations toward the core semantics of images, enriched by their associated deeply text information. This technique enhances transferability by capturing consistent features across various models, thereby effectively misleading similar-model perception areas. Additionally, we employ a momentum iteration strategy in conjunction with MIG, which amalgamates current and historical gradients to expedite the perturbation updates. For text attacks, we streamline the perturbation process by operating exclusively at the embedding level. This reduces semantic gaps across hierarchical structures and significantly enhances the generalizability of adversarial text. Moreover, we delve deeper into how semantic perturbations with varying degrees of similarity affect the overall attack effectiveness. Our experimental results on image-text retrieval tasks using the multi-modal datasets Flickr30K and MSCOCO underscore the efficacy of MSI-Attack. Our method achieves superior performance, setting a new state-of-the-art benchmark, all without the need for additional mechanisms.
- 29 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 20 (15566013) , 5663-5677
Modality-Specific Interactive Attack for Vision-Language Pre-Training Models
Recent advances have heightened the interest in the adversarial transferability of Vision-Language Pre-training (VLP) models. However, most existing strategies constrained by two persistent limitations: suboptimal utilization of cross-modal interactive information, and inherent discrepancies across hierarchical textual representation. To address these challenges, we propose the Modality-Specific Interactive Attack (MSI-Attack), a novel approach that integrates semantic-level image perturbations with embedding-level text perturbations, all while maintaining minimal inter-modal constraints. In our image attack methodology, we introduce Multi-modal Integrated Gradients (MIG) to guide perturbations toward the core semantics of images, enriched by their associated deeply text information. This technique enhances transferability by capturing consistent features across various models, thereby effectively misleading similar-model perception areas. Additionally, we employ a momentum iteration strategy in conjunction with MIG, which amalgamates current and historical gradients to expedite the perturbation updates. For text attacks, we streamline the perturbation process by operating exclusively at the embedding level. This reduces semantic gaps across hierarchical structures and significantly enhances the generalizability of adversarial text. Moreover, we delve deeper into how semantic perturbations with varying degrees of similarity affect the overall attack effectiveness. Our experimental results on image-text retrieval tasks using the multi-modal datasets Flickr30K and MSCOCO underscore the efficacy of MSI-Attack. Our method achieves superior performance, setting a new state-of-the-art benchmark, all without the need for additional mechanisms.
- Top Cited Papers
- 31 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 34 (10577149) , 2147-2160
Exploring Effective Factors for Improving Visual In-Context Learning
The In-Context Learning (ICL) is to understand a new task via a few demonstrations (aka. prompt) and predict new inputs without tuning the models. While it has been widely studied in NLP, it is still a relatively new area of research in computer vision. To reveal the factors influencing the performance of visual in-context learning, this paper shows that Prompt Selection and Prompt Fusion are two major factors that have a direct impact on the inference performance of visual in-context learning. Prompt selection is the process of selecting the most suitable prompt for query image. This is crucial because high-quality prompts assist large-scale visual models in rapidly and accurately comprehending new tasks. Prompt fusion involves combining prompts and query images to activate knowledge within large-scale visual models. However, altering the prompt fusion method significantly impacts its performance on new tasks. Based on these findings, we propose a simple framework prompt-SelF to improve visual in-context learning. Specifically, we first use the pixel-level retrieval method to select a suitable prompt, and then use different prompt fusion methods to activate diverse knowledge stored in the large-scale vision model, and finally, ensemble the prediction results obtained from different prompt fusion methods to obtain the final prediction results. We conducted extensive experiments on single-object segmentation and detection tasks to demonstrate the effectiveness of prompt-SelF. Remarkably, prompt-SelF has outperformed OSLSM method-based meta-learning in 1-shot segmentation for the first time. This indicated the great potential of visual in-context learning. The source code and models will be available at https://github.com/syp2ysy/prompt-SelF.
- 31 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 34 (10577149) , 2147-2160
Top Cited PapersExploring Effective Factors for Improving Visual In-Context Learning
The In-Context Learning (ICL) is to understand a new task via a few demonstrations (aka. prompt) and predict new inputs without tuning the models. While it has been widely studied in NLP, it is still a relatively new area of research in computer vision. To reveal the factors influencing the performance of visual in-context learning, this paper shows that Prompt Selection and Prompt Fusion are two major factors that have a direct impact on the inference performance of visual in-context learning. Prompt selection is the process of selecting the most suitable prompt for query image. This is crucial because high-quality prompts assist large-scale visual models in rapidly and accurately comprehending new tasks. Prompt fusion involves combining prompts and query images to activate knowledge within large-scale visual models. However, altering the prompt fusion method significantly impacts its performance on new tasks. Based on these findings, we propose a simple framework prompt-SelF to improve visual in-context learning. Specifically, we first use the pixel-level retrieval method to select a suitable prompt, and then use different prompt fusion methods to activate diverse knowledge stored in the large-scale vision model, and finally, ensemble the prediction results obtained from different prompt fusion methods to obtain the final prediction results. We conducted extensive experiments on single-object segmentation and detection tasks to demonstrate the effectiveness of prompt-SelF. Remarkably, prompt-SelF has outperformed OSLSM method-based meta-learning in 1-shot segmentation for the first time. This indicated the great potential of visual in-context learning. The source code and models will be available at https://github.com/syp2ysy/prompt-SelF.
- Open Access
Improving Multi-modal Large Language Model through Boosting Vision Capabilities
We focus on improving the visual understanding capability for boosting the vision-language models. We propose \textbf{Arcana}, a multiModal language model, which introduces two crucial techniques. First, we present Multimodal LoRA (MM-LoRA), a module designed to enhance the decoder. Unlike traditional language-driven decoders, MM-LoRA consists of two parallel LoRAs -- one for vision and one for language -- each with its own parameters. This disentangled parameters design allows for more specialized learning in each modality and better integration of multimodal information. Second, we introduce the Query Ladder adapter (QLadder) to improve the visual encoder. QLadder employs a learnable ``\textit{ladder}'' structure to deeply aggregates the intermediate representations from the frozen pretrained visual encoder (e.g., CLIP image encoder). This enables the model to learn new and informative visual features, as well as remaining the powerful capabilities of the pretrained visual encoder. These techniques collectively enhance Arcana's visual perception power, enabling it to leverage improved visual information for more accurate and contextually relevant outputs across various multimodal scenarios. Extensive experiments and ablation studies demonstrate the effectiveness and generalization capability of our Arcana. The code and re-annotated data are available at \url{https://arcana-project-page.github.io}.
Open AccessImproving Multi-modal Large Language Model through Boosting Vision Capabilities
We focus on improving the visual understanding capability for boosting the vision-language models. We propose \textbf{Arcana}, a multiModal language model, which introduces two crucial techniques. First, we present Multimodal LoRA (MM-LoRA), a module designed to enhance the decoder. Unlike traditional language-driven decoders, MM-LoRA consists of two parallel LoRAs -- one for vision and one for language -- each with its own parameters. This disentangled parameters design allows for more specialized learning in each modality and better integration of multimodal information. Second, we introduce the Query Ladder adapter (QLadder) to improve the visual encoder. QLadder employs a learnable ``\textit{ladder}'' structure to deeply aggregates the intermediate representations from the frozen pretrained visual encoder (e.g., CLIP image encoder). This enables the model to learn new and informative visual features, as well as remaining the powerful capabilities of the pretrained visual encoder. These techniques collectively enhance Arcana's visual perception power, enabling it to leverage improved visual information for more accurate and contextually relevant outputs across various multimodal scenarios. Extensive experiments and ablation studies demonstrate the effectiveness and generalization capability of our Arcana. The code and re-annotated data are available at \url{https://arcana-project-page.github.io}.