10 papers
MicroWorld: Empowering Multimodal Large Language Models to Bridge the Microscopic Domain Gap with Multimodal Attributed Property Graph
Manyu Li, Ruian He, Chenxi Ma +2
Multimodal large language models (MLLMs) show remarkable potential for scientific reasoning, yet their performance in specialized domains such as microscopy remains limited by the…
MicroVQA++: High-Quality Microscopy Reasoning Dataset with Weakly Supervised Graphs for Multimodal Large Language Model
Manyu Li, Ruian He, Chenxi Ma +2
Multimodal Large Language Models are increasingly applied to biomedical imaging, yet scientific reasoning for microscopy remains limited by the scarcity of large-scale, high-qualit…
MM-Skin: Enhancing Dermatology Vision-Language Model with an Image-Text Dataset Derived from Textbooks
Wenqi Zeng, Yuqi Sun, Chenxi Ma +2
Medical vision-language models (VLMs) have shown promise as clinical assistants across various medical fields. However, specialized dermatology VLM capable of delivering profession…
Unifying Segment Anything in Microscopy with Vision-Language Knowledge
Manyu Li, Ruian He, Zixian Zhang +3
Accurate segmentation of regions of interest in biomedical images holds substantial value in image analysis. Although several foundation models for biomedical segmentation have cur…
Scaling Laws for Data-Efficient Visual Transfer Learning
Wenxuan Yang, Qingqu Wei, Chenxi Ma +2
Current scaling laws for visual AI models focus predominantly on large-scale pretraining, leaving a critical gap in understanding how performance scales for data-constrained downst…
Non-Uniform Class-Wise Coreset Selection for Vision Model Fine-tuning
Hanyu Zhang, Zhen Xing, Ruian He +4
Coreset selection aims to identify a small yet highly informative subset of data, thereby enabling more efficient model training while reducing storage overhead. Recently, this cap…
Multi-Modality Deep Network for JPEG Artifacts Reduction
Xuhao Jiang, Weimin Tan, Qing Lin +3
In recent years, many convolutional neural network-based models are designed for JPEG artifacts reduction, and have achieved notable progress. However, few methods are suitable for…
Geometry-Aware Reference Synthesis for Multi-View Image Super-Resolution
Ri Cheng, Yuqi Sun, Bo Yan +2
Recent multi-view multimedia applications struggle between high-resolution (HR) visual experience and storage or bandwidth constraints. Therefore, this paper proposes a Multi-View…
Perception-Oriented Stereo Image Super-Resolution
Chenxi Ma, Bo Yan, Weimin Tan +1
Recent studies of deep learning based stereo image super-resolution (StereoSR) have promoted the development of StereoSR. However, existing StereoSR models mainly concentrate on im…
Rethinking Super-Resolution as Text-Guided Details Generation
Chenxi Ma, Bo Yan, Qing Lin +2
Deep neural networks have greatly promoted the performance of single image super-resolution (SISR). Conventional methods still resort to restoring the single high-resolution (HR) s…