Search Results for author:
Found 5 papers, 1 papers with code
DSDRNet: Disentangling Representation and Reconstruct Network for Domain Generalization
Domain generalization faces challenges due to the distribution shift between training and testing sets, and the presence of unseen target domains.
Cross-Modal Adapter: Parameter-Efficient Transfer Learning Approach for Vision-Language Models
While some methods overcome the need for training by leveraging image modality cache and retrieval, they overlook the text modality's importance and cross-modal cues for the efficient adaptation of parameters in visual-language models.
Soft-Prompting with Graph-of-Thought for Multi-modal Representation Learning
It is a step-by-step linear reasoning process that adjusts the length of the chain to improve the performance of generated prompts.
OmniForce: On Human-Centered, Large Model Empowered and Cloud-Edge Collaborative AutoML System
Automated machine learning (AutoML) seeks to build ML models with minimal human effort.
DEAL: Difficulty-aware Active Learning for Semantic Segmentation
To deal with this problem, we propose a semantic Difficulty-awarE Active Learning (DEAL) network composed of two branches: the common segmentation branch and the semantic difficulty branch.
