137 citations · 189 across the 26 of their papers we have counts for
11 papers · 1 filter
Training Multi-Image Vision Agents via End2End Reinforcement Learning
Chengqi Dong, Chuhuai Yue, Hang He +7
Recent VLM-based agents aim to replicate OpenAI O3's "thinking with images" via tool use, yet most open-source methods restrict inputs to a single image, limiting their applicabili…
Equivariant Sampling for Improving Diffusion Model-based Image Restoration
Chenxu Wu, Qingpeng Kong, Peiang Zhao +5
Recent advances in generative models, especially diffusion models, have significantly improved image restoration (IR) performance. However, existing problem-agnostic diffusion mode…
MedReason-R1: Learning to Reason for CT Diagnosis with Reinforcement Learning and Local Zoom
Yifan Li, Fenghe Tang, Yingtai Li +1
General-purpose large Vision-Language Models (VLMs) demonstrate strong capabilities in generating detailed descriptions for natural images. However, their performance in the medica…
U-Bench: A Comprehensive Understanding of U-Net through 100-Variant Benchmarking
Fenghe Tang, Chengqi Dong, Wenxin Ma +7
Over the past decade, U-Net has been the dominant architecture in medical image segmentation, leading to the development of thousands of U-shaped variants. Despite its widespread a…
SimCroP: Radiograph Representation Learning with Similarity-driven Cross-granularity Pre-training
Rongsheng Wang, Fenghe Tang, Qingsong Yao +8
Medical vision-language pre-training shows great potential in learning representative features from massive paired radiographs and reports. However, in computed tomography (CT) sca…
LGMSNet: Thinning a medical image segmentation model via dual-level multiscale fusion
Chengqi Dong, Fenghe Tang, Rongge Mao +2
Medical image segmentation plays a pivotal role in disease diagnosis and treatment planning, particularly in resource-constrained clinical settings where lightweight and generaliza…
Mobile U-ViT: Revisiting large kernel and U-shaped ViT for efficient medical image segmentation
Fenghe Tang, Bingkun Nian, Jianrui Ding +6
In clinical practice, medical image analysis often requires efficient execution on resource-constrained mobile devices. However, existing mobile models-primarily optimized for natu…
U-RWKV: Lightweight medical image segmentation with direction-adaptive RWKV
Hongbo Ye, Fenghe Tang, Peiang Zhao +4
Achieving equity in healthcare accessibility requires lightweight yet high-performance solutions for medical image segmentation, particularly in resource-limited settings. Existing…
Pre-Trained LLM is a Semantic-Aware and Generalizable Segmentation Booster
Fenghe Tang, Wenxin Ma, Zhiyang He +3
With the advancement of Large Language Model (LLM) for natural language processing, this paper presents an intriguing finding: a frozen pre-trained LLM layer can process visual tok…
AA-CLIP: Enhancing Zero-shot Anomaly Detection via Anomaly-Aware CLIP
Wenxin Ma, Xu Zhang, Qingsong Yao +6
Anomaly detection (AD) identifies outliers for applications like defect and lesion detection. While CLIP shows promise for zero-shot AD tasks due to its strong generalization capab…
Hi-End-MAE: Hierarchical encoder-driven masked autoencoders are stronger vision learners for medical image segmentation
Fenghe Tang, Qingsong Yao, Wenxin Ma +3
Medical image segmentation remains a formidable challenge due to the label scarcity. Pre-training Vision Transformer (ViT) through masked image modeling (MIM) on large-scale unlabe…