10 papers
Distributional Vision-Language Alignment by Cauchy-Schwarz Divergence
Wenzhe Yin, Zehao Xiao, Pan Zhou +4
Vision-language alignment is crucial for various downstream tasks such as cross-modal generation and retrieval. Previous multimodal approaches like CLIP utilize InfoNCE to maximize…
Towards Uniformity and Alignment for Multimodal Representation Learning
Wenzhe Yin, Pan Zhou, Zehao Xiao +4
Multimodal representation learning aims to construct a shared embedding space in which heterogeneous modalities are semantically aligned. Despite strong empirical results, InfoNCE-…
Equivariant Multiscale Learned Invertible Reconstruction for Cone Beam CT: From Simulated to Real Data
Nikita Moriakov, Efstratios Gavves, Jonathan H. Mason +3
Cone Beam CT (CBCT) is an important imaging modality nowadays, however lower image quality of CBCT compared to more conventional Computed Tomography (CT) remains a limiting factor…
Probabilistic Prototype Calibration of Vision-Language Models for Generalized Few-shot Semantic Segmentation
Jie Liu, Jiayi Shen, Pan Zhou +2
Generalized Few-Shot Semantic Segmentation (GFSS) aims to extend a segmentation model to novel classes with only a few annotated examples while maintaining performance on base clas…
Physics-Guided Radiotherapy Treatment Planning with Deep Learning
Stefanos Achlatis, Efstratios Gavves, Jan-Jakob Sonke
Radiotherapy (RT) is a critical cancer treatment, with volumetric modulated arc therapy (VMAT) being a commonly used technique that enhances dose conformity by dynamically adjustin…
Probabilistic Interactive 3D Segmentation with Hierarchical Neural Processes
Jie Liu, Pan Zhou, Zehao Xiao +4
Interactive 3D segmentation has emerged as a promising solution for generating accurate object masks in complex 3D scenes by incorporating user-provided clicks. However, two critic…