activity
20212024
most citedMeta Learning to Bridge Vision and Language Models for Multimodal Few-Shot Learning

8 citations · 25 across the 18 of their papers we have counts for

collaborators

13 papers

cs.LG20232 cited

Episodic Multi-Task Learning with Heterogeneous Neural Processes

Jiayi Shen, Xiantong Zhen, Qi +2

This paper focuses on the data-insufficiency problem in multi-task learning within an episodic training setup. Specifically, we explore the potential of heterogeneous information a…

cs.CV2023

Order-preserving Consistency Regularization for Domain Adaptation and Generalization

Mengmeng Jing, Xiantong Zhen, Jingjing Li +1

Deep learning models fail on cross-domain challenges if the model is oversensitive to domain-specific attributes, e.g., lightning, background, camera angle, etc. To alleviate this…

cs.CL2023

Knowledge Graph Embeddings for Multi-Lingual Structured Representations of Radiology Reports

Tom van Sonsbeek, Xiantong Zhen, Marcel Worring

The way we analyse clinical texts has undergone major changes over the last years. The introduction of language models such as BERT led to adaptations for the (bio)medical domain l…

cs.CV2023

Learning Cross-Modal Affinity for Referring Video Object Segmentation Targeting Limited Samples

Guanghui Li, Mingqi Gao, Heng Liu +2

Referring video object segmentation (RVOS), as a supervised learning task, relies on sufficient annotated data for a given scene. However, in more realistic scenarios, only minimal…

cs.CV20232 cited

Knowledge-Aware Prompt Tuning for Generalizable Vision-Language Models

Baoshuo Kan, Teng Wang, Wenpeng Lu +3

Pre-trained vision-language models, e.g., CLIP, working with manually designed prompts have demonstrated great capacity of transfer learning. Recently, learnable prompts achieve st…

cs.LG20231 cited

MetaModulation: Learning Variational Feature Hierarchies for Few-Shot Learning with Fewer Tasks

Wenfang Sun, Yingjun Du, Xiantong Zhen +3

Meta-learning algorithms are able to learn a new task using previously learned knowledge, but they often require a large number of meta-training tasks which may not be readily avai…