85 citations · 273 across the 108 of their papers we have counts for
20 papers · 1 filter
High-Quality Mask Tuning Matters for Open-Vocabulary Segmentation
Quan-Sheng Zeng, Yunheng Li, Daquan Zhou +3
Open-vocabulary image segmentation has been advanced through the synergy between mask generators and vision-language models like Contrastive Language-Image Pre-training (CLIP). Pre…
GeoSplatting: Towards Geometry Guided Gaussian Splatting for Physically-based Inverse Rendering
Kai Ye, Chong Gao, Guanbin Li +2
Recent 3D Gaussian Splatting (3DGS) representations have demonstrated remarkable performance in novel view synthesis; further, material-lighting disentanglement on 3DGS warrants re…
Let Video Teaches You More: Video-to-Image Knowledge Distillation using DEtection TRansformer for Medical Video Lesion Detection
Yuncheng Jiang, Zixun Zhang, Jun Wei +5
AI-assisted lesion detection models play a crucial role in the early screening of cancer. However, previous image-based models ignore the inter-frame contextual information present…
SAM2-UNet: Segment Anything 2 Makes Strong Encoder for Natural and Medical Image Segmentation
Xinyu Xiong, Zihuang Wu, Shuangyi Tan +6
Image segmentation plays an important role in vision understanding. Recently, the emerging vision foundation models continuously achieved superior performance on various tasks. Fol…
ToDER: Towards Colonoscopy Depth Estimation and Reconstruction with Geometry Constraint Adaptation
Zhenhua Wu, Yanlin Jin, Liangdong Qiu +3
Visualizing colonoscopy is crucial for medical auxiliary diagnosis to prevent undetected polyps in areas that are not fully observed. Traditional feature-based and depth-based reco…
Intensity Confusion Matters: An Intensity-Distance Guided Loss for Bronchus Segmentation
Haifan Gong, Wenhao Huang, Huan Zhang +5
Automatic segmentation of the bronchial tree from CT imaging is important, as it provides structural information for disease diagnosis. Despite the merits of previous automatic bro…
AlignSAM: Aligning Segment Anything Model to Open Context via Reinforcement Learning
Duojun Huang, Xinyu Xiong, Jie Ma +4
Powered by massive curated training data, Segment Anything Model (SAM) has demonstrated its impressive generalization capabilities in open-world scenarios with the guidance of prom…
UniFL: Improve Latent Diffusion Model via Unified Feedback Learning
Jiacheng Zhang, Jie Wu, Yuxi Ren +9
Latent diffusion models (LDM) have revolutionized text-to-image generation, leading to the proliferation of various advanced models and diverse downstream applications. However, de…
NeRF-HuGS: Improved Neural Radiance Fields in Non-static Scenes Using Heuristics-Guided Segmentation
Jiahao Chen, Yipeng Qin, Lingjie Liu +2
Neural Radiance Field (NeRF) has been widely recognized for its excellence in novel view synthesis and 3D scene reconstruction. However, their effectiveness is inherently tied to t…
OVER-NAV: Elevating Iterative Vision-and-Language Navigation with Open-Vocabulary Detection and StructurEd Representation
Ganlong Zhao, Guanbin Li, Weikai Chen +1
Recent advances in Iterative Vision-and-Language Navigation (IVLN) introduce a more meaningful and practical paradigm of VLN by maintaining the agent's memory across tours of scene…
Annotation-Efficient Polyp Segmentation via Active Learning
Duojun Huang, Xinyu Xiong, De-Jun Fan +3
Deep learning-based techniques have proven effective in polyp segmentation tasks when provided with sufficient pixel-wise labeled data. However, the high cost of manual annotation…
Semi- and Weakly-Supervised Learning for Mammogram Mass Segmentation with Limited Annotations
Xinyu Xiong, Churan Wang, Wenxue Li +1
Accurate identification of breast masses is crucial in diagnosing breast cancer; however, it can be challenging due to their small size and being camouflaged in surrounding normal…
Decoupled Pseudo-labeling for Semi-Supervised Monocular 3D Object Detection
Jiacheng Zhang, Jiaming Li, Xiangru Lin +6
We delve into pseudo-labeling for semi-supervised monocular 3D object detection (SSM3OD) and discover two primary issues: a misalignment between the prediction quality of 3D and 2D…
Mask-Enhanced Segment Anything Model for Tumor Lesion Semantic Segmentation
Hairong Shi, Songhao Han, Shaofei Huang +6
Tumor lesion segmentation on CT or MRI images plays a critical role in cancer diagnosis and treatment planning. Considering the inherent differences in tumor lesion segmentation da…
Large Multimodal Agents: A Survey
Junlin Xie, Zhihong Chen, Ruifei Zhang +2
Large language models (LLMs) have achieved superior performance in powering text-based AI agents, endowing them with decision-making and reasoning abilities akin to humans. Concurr…
Cell Graph Transformer for Nuclei Classification
Wei Lou, Guanbin Li, Xiang Wan +1
Nuclei classification is a critical step in computer-aided diagnosis with histopathology images. In the past, various methods have employed graph neural networks (GNN) to analyze c…
UniCell: Universal Cell Nucleus Classification via Prompt Learning
Junjia Huang, Haofeng Li, Xiang Wan +1
The recognition of multi-class cell nuclei can significantly facilitate the process of histopathological diagnosis. Numerous pathological datasets are currently available, but thei…
Inter-Domain Mixup for Semi-Supervised Domain Adaptation
Jichang Li, Guanbin Li, Yizhou Yu
Semi-supervised domain adaptation (SSDA) aims to bridge source and target domain distributions, with a small number of target labels available, achieving better classification perf…
Adaptive Betweenness Clustering for Semi-Supervised Domain Adaptation
Jichang Li, Guanbin Li, Yizhou Yu
Compared to unsupervised domain adaptation, semi-supervised domain adaptation (SSDA) aims to significantly improve the classification performance and generalization capability of t…
ECC-PolypDet: Enhanced CenterNet with Contrastive Learning for Automatic Polyp Detection
Yuncheng Jiang, Zixun Zhang, Yiwen Hu +6
Accurate polyp detection is critical for early colorectal cancer diagnosis. Although remarkable progress has been achieved in recent years, the complex colon environment and concea…